{"type":"permission-mode","permissionMode":"acceptEdits","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503"}
{"parentUuid":null,"isSidechain":false,"attachment":{"type":"hook_success","hookName":"SessionStart:startup","toolUseID":"2d851e88-9897-43e8-993d-b94948c5c08c","hookEvent":"SessionStart","content":"","stdout":"{\n  \"hookSpecificOutput\": {\n    \"hookEventName\": \"SessionStart\",\n    \"additionalContext\": \"<EXTREMELY_IMPORTANT>\\nYou have superpowers.\\n\\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\\n\\n---\\nname: using-superpowers\\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\\n---\\n\\n<SUBAGENT-STOP>\\nIf you were dispatched as a subagent to execute a specific task, skip this skill.\\n</SUBAGENT-STOP>\\n\\n<EXTREMELY-IMPORTANT>\\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\\n\\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\\n\\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\\n</EXTREMELY-IMPORTANT>\\n\\n## Instruction Priority\\n\\nSuperpowers skills override default system prompt behavior, but **user instructions always take precedence**:\\n\\n1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority\\n2. **Superpowers skills** — override default system behavior where they conflict\\n3. **Default system prompt** — lowest priority\\n\\nIf CLAUDE.md, GEMINI.md, or AGENTS.md says \\\"don't use TDD\\\" and a skill says \\\"always use TDD,\\\" follow the user's instructions. The user is in control.\\n\\n## How to Access Skills\\n\\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\\n\\n**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.\\n\\n**In other environments:** Check your platform's documentation for how skills are loaded.\\n\\n## Platform Adaptation\\n\\nSkills use Claude Code tool names. Non-CC platforms: see `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.\\n\\n# Using Skills\\n\\n## The Rule\\n\\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\\n\\n```dot\\ndigraph skill_flow {\\n    \\\"User message received\\\" [shape=doublecircle];\\n    \\\"About to EnterPlanMode?\\\" [shape=doublecircle];\\n    \\\"Already brainstormed?\\\" [shape=diamond];\\n    \\\"Invoke brainstorming skill\\\" [shape=box];\\n    \\\"Might any skill apply?\\\" [shape=diamond];\\n    \\\"Invoke Skill tool\\\" [shape=box];\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" [shape=box];\\n    \\\"Has checklist?\\\" [shape=diamond];\\n    \\\"Create TodoWrite todo per item\\\" [shape=box];\\n    \\\"Follow skill exactly\\\" [shape=box];\\n    \\\"Respond (including clarifications)\\\" [shape=doublecircle];\\n\\n    \\\"About to EnterPlanMode?\\\" -> \\\"Already brainstormed?\\\";\\n    \\\"Already brainstormed?\\\" -> \\\"Invoke brainstorming skill\\\" [label=\\\"no\\\"];\\n    \\\"Already brainstormed?\\\" -> \\\"Might any skill apply?\\\" [label=\\\"yes\\\"];\\n    \\\"Invoke brainstorming skill\\\" -> \\\"Might any skill apply?\\\";\\n\\n    \\\"User message received\\\" -> \\\"Might any skill apply?\\\";\\n    \\\"Might any skill apply?\\\" -> \\\"Invoke Skill tool\\\" [label=\\\"yes, even 1%\\\"];\\n    \\\"Might any skill apply?\\\" -> \\\"Respond (including clarifications)\\\" [label=\\\"definitely not\\\"];\\n    \\\"Invoke Skill tool\\\" -> \\\"Announce: 'Using [skill] to [purpose]'\\\";\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" -> \\\"Has checklist?\\\";\\n    \\\"Has checklist?\\\" -> \\\"Create TodoWrite todo per item\\\" [label=\\\"yes\\\"];\\n    \\\"Has checklist?\\\" -> \\\"Follow skill exactly\\\" [label=\\\"no\\\"];\\n    \\\"Create TodoWrite todo per item\\\" -> \\\"Follow skill exactly\\\";\\n}\\n```\\n\\n## Red Flags\\n\\nThese thoughts mean STOP—you're rationalizing:\\n\\n| Thought | Reality |\\n|---------|---------|\\n| \\\"This is just a simple question\\\" | Questions are tasks. Check for skills. |\\n| \\\"I need more context first\\\" | Skill check comes BEFORE clarifying questions. |\\n| \\\"Let me explore the codebase first\\\" | Skills tell you HOW to explore. Check first. |\\n| \\\"I can check git/files quickly\\\" | Files lack conversation context. Check for skills. |\\n| \\\"Let me gather information first\\\" | Skills tell you HOW to gather information. |\\n| \\\"This doesn't need a formal skill\\\" | If a skill exists, use it. |\\n| \\\"I remember this skill\\\" | Skills evolve. Read current version. |\\n| \\\"This doesn't count as a task\\\" | Action = task. Check for skills. |\\n| \\\"The skill is overkill\\\" | Simple things become complex. Use it. |\\n| \\\"I'll just do this one thing first\\\" | Check BEFORE doing anything. |\\n| \\\"This feels productive\\\" | Undisciplined action wastes time. Skills prevent this. |\\n| \\\"I know what that means\\\" | Knowing the concept ≠ using the skill. Invoke it. |\\n\\n## Skill Priority\\n\\nWhen multiple skills could apply, use this order:\\n\\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\\n\\n\\\"Let's build X\\\" → brainstorming first, then implementation skills.\\n\\\"Fix this bug\\\" → debugging first, then domain-specific skills.\\n\\n## Skill Types\\n\\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\\n\\n**Flexible** (patterns): Adapt principles to context.\\n\\nThe skill itself tells you which.\\n\\n## User Instructions\\n\\nInstructions say WHAT, not HOW. \\\"Add X\\\" or \\\"Fix Y\\\" doesn't mean skip workflows.\\n\\n\\n</EXTREMELY_IMPORTANT>\"\n  }\n}\n","stderr":"","exitCode":0,"command":"\"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd\" session-start","durationMs":197},"type":"attachment","uuid":"47ec8781-09f8-41ae-8346-354ba9188487","timestamp":"2026-04-24T12:37:28.855Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"47ec8781-09f8-41ae-8346-354ba9188487","isSidechain":false,"attachment":{"type":"hook_success","hookName":"SessionStart:startup","toolUseID":"2d851e88-9897-43e8-993d-b94948c5c08c","hookEvent":"SessionStart","content":"Previous session summary:\n# Session: 2026-04-18\n**Date:** 2026-04-18\n**Started:** 19:19\n**Last Updated:** 20:16\n**Project:** butler\n**Branch:** unknown\n**Worktree:** /root/projects/butler\n\n---\n<!-- ECC:SUMMARY:START -->\n## Session Summary\n\n### Tasks\n- 为什么我在macbook上的obsidian写的文章，同步到本机是在这个目录：/root/vault/obsidian_vault/obsidian/obsidian/。我记得以前已经改成了/root/vault/obsidian_vault/obsidian/Documents/obsidian\n- webdav同步的配置是怎么样的？\n- 能不能都改成 Documents/obsidian/\n- openclaw的数据写入Documents/obsidian，现在这个变成符号链接的下面，应该也是ok的吧\n\n### Files Modified\n- /root/projects/butler/scripts/init_vault_indexer.py\n- /root/.openclaw/workspace/TOOLS.md\n- /root/vault/README.md\n- /root/.claude/projects/-root-projects-butler/memory/MEMORY.md\n\n### Tools Used\nBash, Grep, Read, Agent, AskUserQuestion, TaskCreate, TaskUpdate, Edit, Write\n\n### Stats\n- Total user messages: 4\n<!-- ECC:SUMMARY:END -->\n\n### Notes for Next Session\n-\n\n### Context to Load\n```\n[relevant files]\n```\n\nProject type: {\"languages\":[\"python\"],\"frameworks\":[],\"primary\":\"python\",\"projectDir\":\"/root/projects/meeting\"}","stdout":"Previous session summary:\n# Session: 2026-04-18\n**Date:** 2026-04-18\n**Started:** 19:19\n**Last Updated:** 20:16\n**Project:** butler\n**Branch:** unknown\n**Worktree:** /root/projects/butler\n\n---\n<!-- ECC:SUMMARY:START -->\n## Session Summary\n\n### Tasks\n- 为什么我在macbook上的obsidian写的文章，同步到本机是在这个目录：/root/vault/obsidian_vault/obsidian/obsidian/。我记得以前已经改成了/root/vault/obsidian_vault/obsidian/Documents/obsidian\n- webdav同步的配置是怎么样的？\n- 能不能都改成 Documents/obsidian/\n- openclaw的数据写入Documents/obsidian，现在这个变成符号链接的下面，应该也是ok的吧\n\n### Files Modified\n- /root/projects/butler/scripts/init_vault_indexer.py\n- /root/.openclaw/workspace/TOOLS.md\n- /root/vault/README.md\n- /root/.claude/projects/-root-projects-butler/memory/MEMORY.md\n\n### Tools Used\nBash, Grep, Read, Agent, AskUserQuestion, TaskCreate, TaskUpdate, Edit, Write\n\n### Stats\n- Total user messages: 4\n<!-- ECC:SUMMARY:END -->\n\n### Notes for Next Session\n-\n\n### Context to Load\n```\n[relevant files]\n```\n\nProject type: {\"languages\":[\"python\"],\"frameworks\":[],\"primary\":\"python\",\"projectDir\":\"/root/projects/meeting\"}\n","stderr":"[SessionStart] Found 1 recent session(s)\n[SessionStart] Latest: /root/.claude/sessions/2026-04-18-butler-session.tmp\n[SessionStart] Package manager: npm (default)\n[SessionStart] No package manager preference found.\n[PackageManager] No package manager preference detected.\nSupported package managers: npm, pnpm, yarn, bun\n\nTo set your preferred package manager:\n  - Global: Set CLAUDE_PACKAGE_MANAGER environment variable\n  - Or add to ~/.claude/package-manager.json: {\"packageManager\": \"pnpm\"}\n  - Or add to package.json: {\"packageManager\": \"pnpm@8\"}\n  - Or add a lock file to your project (e.g., pnpm-lock.yaml)\n\n[SessionStart] Project detected — languages: python\n","exitCode":0,"command":"bash -lc 'input=$(cat); for root in \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME/.claude/plugins/everything-claude-code\" \"$HOME/.claude/plugins/everything-claude-code@everything-claude-code\" \"$HOME/.claude/plugins/marketplace/everything-claude-code\"; do if [ -n \"$root\" ] && [ -f \"$root/scripts/hooks/run-with-flags.js\" ]; then printf \"%s\" \"$input\" | node \"$root/scripts/hooks/run-with-flags.js\" \"session:start\" \"scripts/hooks/session-start.js\" \"minimal,standard,strict\"; exit $?; fi; done; for parent in \"$HOME/.claude/plugins\" \"$HOME/.claude/plugins/marketplace\"; do if [ -d \"$parent\" ]; then candidate=$(find \"$parent\" -maxdepth 2 -type f -path \"*/scripts/hooks/run-with-flags.js\" 2>/dev/null | head -n 1); if [ -n \"$candidate\" ]; then root=$(dirname \"$(dirname \"$(dirname \"$candidate\")\")\"); printf \"%s\" \"$input\" | node \"$root/scripts/hooks/run-with-flags.js\" \"session:start\" \"scripts/hooks/session-start.js\" \"minimal,standard,strict\"; exit $?; fi; fi; done; echo \"[SessionStart] WARNING: could not resolve ECC plugin root; skipping session-start hook\" >&2; printf \"%s\" \"$input\"; exit 0'","durationMs":799},"type":"attachment","uuid":"1db09db0-a7b5-4812-b18f-71b72a74cab6","timestamp":"2026-04-24T12:37:29.452Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"1db09db0-a7b5-4812-b18f-71b72a74cab6","isSidechain":false,"attachment":{"type":"hook_additional_context","content":["<EXTREMELY_IMPORTANT>\nYou have superpowers.\n\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\n\n---\nname: using-superpowers\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\n---\n\n<SUBAGENT-STOP>\nIf you were dispatched as a subagent to execute a specific task, skip this skill.\n</SUBAGENT-STOP>\n\n<EXTREMELY-IMPORTANT>\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\n\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\n\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\n</EXTREMELY-IMPORTANT>\n\n## Instruction Priority\n\nSuperpowers skills override default system prompt behavior, but **user instructions always take precedence**:\n\n1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority\n2. **Superpowers skills** — override default system behavior where they conflict\n3. **Default system prompt** — lowest priority\n\nIf CLAUDE.md, GEMINI.md, or AGENTS.md says \"don't use TDD\" and a skill says \"always use TDD,\" follow the user's instructions. The user is in control.\n\n## How to Access Skills\n\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\n\n**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.\n\n**In other environments:** Check your platform's documentation for how skills are loaded.\n\n## Platform Adaptation\n\nSkills use Claude Code tool names. Non-CC platforms: see `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.\n\n# Using Skills\n\n## The Rule\n\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\n\n```dot\ndigraph skill_flow {\n    \"User message received\" [shape=doublecircle];\n    \"About to EnterPlanMode?\" [shape=doublecircle];\n    \"Already brainstormed?\" [shape=diamond];\n    \"Invoke brainstorming skill\" [shape=box];\n    \"Might any skill apply?\" [shape=diamond];\n    \"Invoke Skill tool\" [shape=box];\n    \"Announce: 'Using [skill] to [purpose]'\" [shape=box];\n    \"Has checklist?\" [shape=diamond];\n    \"Create TodoWrite todo per item\" [shape=box];\n    \"Follow skill exactly\" [shape=box];\n    \"Respond (including clarifications)\" [shape=doublecircle];\n\n    \"About to EnterPlanMode?\" -> \"Already brainstormed?\";\n    \"Already brainstormed?\" -> \"Invoke brainstorming skill\" [label=\"no\"];\n    \"Already brainstormed?\" -> \"Might any skill apply?\" [label=\"yes\"];\n    \"Invoke brainstorming skill\" -> \"Might any skill apply?\";\n\n    \"User message received\" -> \"Might any skill apply?\";\n    \"Might any skill apply?\" -> \"Invoke Skill tool\" [label=\"yes, even 1%\"];\n    \"Might any skill apply?\" -> \"Respond (including clarifications)\" [label=\"definitely not\"];\n    \"Invoke Skill tool\" -> \"Announce: 'Using [skill] to [purpose]'\";\n    \"Announce: 'Using [skill] to [purpose]'\" -> \"Has checklist?\";\n    \"Has checklist?\" -> \"Create TodoWrite todo per item\" [label=\"yes\"];\n    \"Has checklist?\" -> \"Follow skill exactly\" [label=\"no\"];\n    \"Create TodoWrite todo per item\" -> \"Follow skill exactly\";\n}\n```\n\n## Red Flags\n\nThese thoughts mean STOP—you're rationalizing:\n\n| Thought | Reality |\n|---------|---------|\n| \"This is just a simple question\" | Questions are tasks. Check for skills. |\n| \"I need more context first\" | Skill check comes BEFORE clarifying questions. |\n| \"Let me explore the codebase first\" | Skills tell you HOW to explore. Check first. |\n| \"I can check git/files quickly\" | Files lack conversation context. Check for skills. |\n| \"Let me gather information first\" | Skills tell you HOW to gather information. |\n| \"This doesn't need a formal skill\" | If a skill exists, use it. |\n| \"I remember this skill\" | Skills evolve. Read current version. |\n| \"This doesn't count as a task\" | Action = task. Check for skills. |\n| \"The skill is overkill\" | Simple things become complex. Use it. |\n| \"I'll just do this one thing first\" | Check BEFORE doing anything. |\n| \"This feels productive\" | Undisciplined action wastes time. Skills prevent this. |\n| \"I know what that means\" | Knowing the concept ≠ using the skill. Invoke it. |\n\n## Skill Priority\n\nWhen multiple skills could apply, use this order:\n\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\n\n\"Let's build X\" → brainstorming first, then implementation skills.\n\"Fix this bug\" → debugging first, then domain-specific skills.\n\n## Skill Types\n\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\n\n**Flexible** (patterns): Adapt principles to context.\n\nThe skill itself tells you which.\n\n## User Instructions\n\nInstructions say WHAT, not HOW. \"Add X\" or \"Fix Y\" doesn't mean skip workflows.\n\n\n</EXTREMELY_IMPORTANT>"],"hookName":"SessionStart","toolUseID":"SessionStart","hookEvent":"SessionStart"},"type":"attachment","uuid":"3186ca6d-9189-4641-a9e5-cf923efd79ef","timestamp":"2026-04-24T12:37:29.452Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"type":"file-history-snapshot","messageId":"7edc5c91-08df-45fa-a084-5734fc624ed8","snapshot":{"messageId":"7edc5c91-08df-45fa-a084-5734fc624ed8","trackedFileBackups":{},"timestamp":"2026-04-24T12:37:31.944Z"},"isSnapshotUpdate":false}
{"parentUuid":"3186ca6d-9189-4641-a9e5-cf923efd79ef","isSidechain":false,"promptId":"a7e48d8f-5200-4b5a-a234-944f3acf5419","type":"user","message":{"role":"user","content":"are you ok"},"uuid":"7edc5c91-08df-45fa-a084-5734fc624ed8","timestamp":"2026-04-24T12:37:31.943Z","permissionMode":"acceptEdits","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"7edc5c91-08df-45fa-a084-5734fc624ed8","isSidechain":false,"attachment":{"type":"skill_listing","content":"- update-config: Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.\n- keybindings-help: Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json. Examples: \"rebind ctrl+s\", \"add a chord shortcut\", \"change the submit key\", \"customize keybindings\".\n- simplify: Review changed code for reuse, quality, and efficiency, then fix any issues found.\n- fewer-permission-prompts: Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.\n- claude-api: Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements).\nTRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project.\nSKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.\n- gstack: Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with\nelements, verify page state, diff before/after actions, take annotated screenshots, check\nresponsive layouts, test forms and uploads, handle dialogs, and assert element states.\n~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a\nuser flow, or file a bug with evidence.\n- browse: Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with\nelements, verify page state, diff before/after actions, take annotated screenshots, check\nresponsive layouts, test forms and uploads, handle dialogs, and assert element states.\n~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a\nuser flow, or file a bug with evidence.\n- design-consultation: Design consultation: understands your product, researches the landscape, proposes a\ncomplete design system (aesthetic, typography, color, layout, spacing, motion), and\ngenerates font+color preview pages. Creates DESIGN.md as your project's design source\nof truth. For existing sites, use /plan-design-review to infer the system instead.\n- design-review: Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,\nAI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues\nin source code, committing each fix atomically and re-verifying with before/after\nscreenshots. For plan-mode design review (before implementation), use /plan-design-review.\n- document-release: Post-ship documentation update. Reads all project docs, cross-references the\ndiff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,\npolishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION.\n- gstack-upgrade: Upgrade gstack to the latest version. Detects global vs vendored install,\nruns the upgrade, and shows what's new.\n- plan-ceo-review: CEO/founder-mode plan review. Rethink the problem, find the 10-star product,\nchallenge premises, expand scope when it creates a better product. Four modes:\nSCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick\nexpansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).\n- plan-design-review: Designer's eye plan review — interactive, like CEO and Eng review.\nRates each design dimension 0-10, explains what would make it a 10,\nthen fixes the plan to get there. Works in plan mode. For live site\nvisual audits, use /design-review.\n- plan-eng-review: Eng manager-mode plan review. Lock in the execution plan — architecture,\ndata flow, diagrams, edge cases, test coverage, performance. Walks through\nissues interactively with opinionated recommendations.\n- qa: Systematically QA test a web application and fix bugs found. Runs QA testing,\nthen iteratively fixes bugs in source code, committing each fix atomically and\nre-verifying. Use when asked to \"qa\", \"QA\", \"test this site\", \"find bugs\",\n\"test and fix\", or \"fix what's broken\". Three tiers: Quick (critical/high only),\nStandard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores,\nfix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.\n- qa-only: Report-only QA testing. Systematically tests a web application and produces a\nstructured report with health score, screenshots, and repro steps — but never\nfixes anything. Use when asked to \"just report bugs\", \"qa report only\", or\n\"test but don't fix\". For the full test-fix-verify loop, use /qa instead.\n- retro: Weekly engineering retrospective. Analyzes commit history, work patterns,\nand code quality metrics with persistent history and trend tracking.\nTeam-aware: breaks down per-person contributions with praise and growth areas.\n- review: Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust\nboundary violations, conditional side effects, and other structural issues.\n- setup-browser-cookies: Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the\nheadless browse session. Opens an interactive picker UI where you select which\ncookie domains to import. Use before QA testing authenticated pages.\n- ship: Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.\n- meeting: Multi-agent debate meeting — simulates a boardroom discussion with multiple\nexpert personas (Munger, Bezos, Grove, Horowitz, etc.) debating a topic from\ndifferent angles. Use when the user wants to \"hold a meeting\", \"start a debate\",\n\"discuss a topic with experts\", or \"run a multi-agent meeting\".\nAlways clarify topic, context, participants, and preferences BEFORE starting.\n- superpowers:brainstorm: Deprecated - use the superpowers:brainstorming skill instead\n- superpowers:execute-plan: Deprecated - use the superpowers:executing-plans skill instead\n- superpowers:write-plan: Deprecated - use the superpowers:writing-plans skill instead\n- everything-claude-code:aside: Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.\n- everything-claude-code:tdd: Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.\n- everything-claude-code:learn-eval: Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).\n- everything-claude-code:skill-create: Analyze local git history to extract coding patterns and generate SKILL.md files. Local version of the Skill Creator GitHub App.\n- everything-claude-code:kotlin-test: Enforce TDD workflow for Kotlin. Write Kotest tests first, then implement. Verify 80%+ coverage with Kover.\n- everything-claude-code:kotlin-review: Comprehensive Kotlin code review for idiomatic patterns, null safety, coroutine safety, and security. Invokes the kotlin-reviewer agent.\n- everything-claude-code:kotlin-build: Fix Kotlin/Gradle build errors, compiler warnings, and dependency issues incrementally. Invokes the kotlin-build-resolver agent for minimal, surgical fixes.\n- everything-claude-code:save-session: Save current session state to a dated file in ~/.claude/sessions/ so work can be resumed in a future session with full context.\n- everything-claude-code:resume-session: Load the most recent session file from ~/.claude/sessions/ and resume work with full context from where the last session ended.\n- everything-claude-code:instinct-status: Show learned instincts (project + global) with confidence\n- everything-claude-code:python-review: Comprehensive Python code review for PEP 8 compliance, type hints, security, and Pythonic idioms. Invokes the python-reviewer agent.\n- everything-claude-code:prompt-optimize: Analyze a draft prompt and output an optimized, ECC-enriched version ready to paste and run. Does NOT execute the task — outputs advisory analysis only.\n- everything-claude-code:instinct-import: Import instincts from file or URL into project/global scope\n- everything-claude-code:promote: Promote project-scoped instincts to global scope\n- everything-claude-code:instinct-export: Export instincts from project/global scope to a file\n- everything-claude-code:projects: List known projects and their instinct statistics\n- everything-claude-code:gradle-build: Fix Gradle build errors for Android and KMP projects\n- everything-claude-code:go-test: Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.\n- everything-claude-code:go-review: Comprehensive Go code review for idiomatic patterns, concurrency safety, error handling, and security. Invokes the go-reviewer agent.\n- everything-claude-code:plan: Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.\n- everything-claude-code:go-build: Fix Go build errors, go vet warnings, and linter issues incrementally. Invokes the go-build-resolver agent for minimal, surgical fixes.\n- everything-claude-code:evolve: Analyze instincts and suggest or generate evolved structures\n- everything-claude-code:e2e: Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.\n- everything-claude-code:claw: Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.\n- superpowers:writing-skills: Use when creating new skills, editing existing skills, or verifying skills work before deployment\n- superpowers:writing-plans: Use when you have a spec or requirements for a multi-step task, before touching code\n- superpowers:verification-before-completion: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always\n- superpowers:using-superpowers: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\n- superpowers:using-git-worktrees: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification\n- superpowers:test-driven-development: Use when implementing any feature or bugfix, before writing implementation code\n- superpowers:systematic-debugging: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes\n- superpowers:subagent-driven-development: Use when executing implementation plans with independent tasks in the current session\n- superpowers:requesting-code-review: Use when completing tasks, implementing major features, or before merging to verify work meets requirements\n- superpowers:receiving-code-review: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation\n- superpowers:finishing-a-development-branch: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup\n- superpowers:executing-plans: Use when you have a written implementation plan to execute in a separate session with review checkpoints\n- superpowers:dispatching-parallel-agents: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies\n- superpowers:brainstorming: You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.\n- everything-claude-code:x-api: X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.\n- everything-claude-code:visa-doc-translate: Translate visa application documents (images) to English and create a bilingual PDF with original and translation\n- everything-claude-code:videodb: See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.\n- everything-claude-code:video-editing: AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.\n- everything-claude-code:verification-loop: A comprehensive verification system for Claude Code sessions.\n- everything-claude-code:tdd-workflow: Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.\n- everything-claude-code:swiftui-patterns: SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.\n- everything-claude-code:swift-protocol-di-testing: Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.\n- everything-claude-code:swift-concurrency-6-2: Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types.\n- everything-claude-code:swift-actor-persistence: Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.\n- everything-claude-code:strategic-compact: Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.\n- everything-claude-code:springboot-verification: Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.\n- everything-claude-code:springboot-tdd: Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.\n- everything-claude-code:springboot-security: Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.\n- everything-claude-code:django-patterns: Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.\n- everything-claude-code:deployment-patterns: Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.\n- everything-claude-code:deep-research: Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.\n- everything-claude-code:database-migrations: Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate).\n- everything-claude-code:springboot-patterns: Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.\n- everything-claude-code:customs-trade-compliance: Codified expertise for customs documentation, tariff classification, duty optimization, restricted party screening, and regulatory compliance across multiple jurisdictions. Informed by trade compliance specialists with 15+ years experience. Includes HS classification logic, Incoterms application, FTA utilization, and penalty mitigation. Use when handling customs clearance, tariff classification, trade compliance, import/export documentation, or duty optimization.\n- everything-claude-code:skill-stocktake: Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.\n- everything-claude-code:agent-harness-construction: Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.\n- everything-claude-code:security-scan: Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.\n- everything-claude-code:crosspost: Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.\n- everything-claude-code:cpp-testing: Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.\n- everything-claude-code:cpp-coding-standards: C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.\n- everything-claude-code:kotlin-ktor-patterns: Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.\n- everything-claude-code:cost-aware-llm-pipeline: Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.\n- everything-claude-code:kotlin-exposed-patterns: JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.\n- everything-claude-code:security-review: Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.\n- everything-claude-code:kotlin-coroutines-flows: Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.\n- everything-claude-code:continuous-learning-v2: Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.\n- everything-claude-code:search-first: Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.\n- everything-claude-code:jpa-patterns: JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.\n- everything-claude-code:java-coding-standards: Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.\n- everything-claude-code:continuous-learning: Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.\n- everything-claude-code:returns-reverse-logistics: Codified expertise for returns authorization, receipt and inspection, disposition decisions, refund processing, fraud detection, and warranty claims management. Informed by returns operations managers with 15+ years experience. Includes grading frameworks, disposition economics, fraud pattern recognition, and vendor recovery processes. Use when handling product returns, reverse logistics, refund decisions, return fraud detection, or warranty claims.\n- everything-claude-code:iterative-retrieval: Pattern for progressively refining context retrieval to solve the subagent context problem\n- everything-claude-code:continuous-agent-loop: Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.\n- everything-claude-code:regex-vs-llm-structured-text: Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.\n- everything-claude-code:investor-outreach: Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.\n- everything-claude-code:investor-materials: Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.\n- everything-claude-code:content-hash-cache-pattern: Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.\n- everything-claude-code:ralphinho-rfc-pipeline: RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.\n- everything-claude-code:content-engine: Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.\n- everything-claude-code:inventory-demand-planning: Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years experience managing hundreds of SKUs. Includes forecasting method selection, ABC/XYZ analysis, seasonal transition management, and vendor negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.\n- everything-claude-code:quality-nonconformance: Codified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier quality management in regulated manufacturing. Informed by quality engineers with 15+ years experience across FDA, IATF 16949, and AS9100 environments. Includes NCR lifecycle management, CAPA systems, SPC interpretation, and audit methodology. Use when investigating non-conformances, performing root cause analysis, managing CAPAs, interpreting SPC data, or handling supplier quality issues.\n- everything-claude-code:perl-patterns: Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.\n- everything-claude-code:configure-ecc: Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.\n- everything-claude-code:nutrient-document-processing: Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.\n- everything-claude-code:nanoclaw-repl: Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.\n- everything-claude-code:market-research: Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.\n- everything-claude-code:logistics-exception-management: Codified expertise for handling freight exceptions, shipment delays, damages, losses, and carrier disputes. Informed by logistics professionals with 15+ years operational experience. Includes escalation protocols, carrier-specific behaviors, claims procedures, and judgment frameworks. Use when handling shipping exceptions, freight claims, delivery issues, or carrier disputes.\n- everything-claude-code:liquid-glass-design: iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI, UIKit, and WidgetKit.\n- everything-claude-code:kotlin-testing: Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.\n- everything-claude-code:kotlin-patterns: Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.\n- everything-claude-code:golang-testing: Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.\n- everything-claude-code:perl-security: Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.\n- everything-claude-code:compose-multiplatform-patterns: Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.\n- everything-claude-code:python-testing: Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.\n- everything-claude-code:golang-patterns: Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.\n- everything-claude-code:backend-patterns: Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.\n- everything-claude-code:frontend-slides: Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.\n- everything-claude-code:coding-standards: Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.\n- everything-claude-code:autonomous-loops: Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.\n- everything-claude-code:python-patterns: Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.\n- everything-claude-code:frontend-patterns: Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.\n- everything-claude-code:article-writing: Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.\n- everything-claude-code:prompt-optimizer: Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says \"optimize prompt\", \"improve my prompt\", \"how to write a prompt for\", \"help me prompt\", \"rewrite this prompt\", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: \"优化prompt\", \"改进prompt\", \"怎么写prompt\", \"帮我优化这个指令\". DO NOT TRIGGER when: user wants the task executed directly, or says \"just do it\" / \"直接做\". DO NOT TRIGGER when user says \"优化代码\", \"优化性能\", \"optimize performance\", \"optimize this code\" — those are refactoring/performance tasks, not prompt optimization.\n- everything-claude-code:foundation-models-on-device: Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.\n- everything-claude-code:fal-ai-media: Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.\n- everything-claude-code:exa-search: Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.\n- everything-claude-code:clickhouse-io: ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.\n- everything-claude-code:eval-harness: Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles\n- everything-claude-code:enterprise-agent-ops: Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.\n- everything-claude-code:api-design: REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.\n- everything-claude-code:project-guidelines-example: Example project-specific skill template based on a real production application.\n- everything-claude-code:claude-api: Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.\n- everything-claude-code:energy-procurement: Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis, hedging strategies, load profiling, and sustainability reporting frameworks. Use when procuring energy, optimizing tariffs, managing demand charges, evaluating PPAs, or developing energy strategies.\n- everything-claude-code:android-clean-architecture: Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.\n- everything-claude-code:e2e-testing: Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.\n- everything-claude-code:production-scheduling: Codified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines.\n- everything-claude-code:postgres-patterns: PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.\n- everything-claude-code:docker-patterns: Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.\n- everything-claude-code:dmux-workflows: Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.\n- everything-claude-code:django-verification: Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.\n- everything-claude-code:carrier-relationship-management: Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.\n- everything-claude-code:plankton-code-quality: Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.\n- everything-claude-code:ai-first-engineering: Engineering operating model for teams where AI agents generate a large share of implementation output.\n- everything-claude-code:django-tdd: Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.\n- everything-claude-code:blueprint: Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says \"just do it\".\n- everything-claude-code:perl-testing: Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.\n- everything-claude-code:agentic-engineering: Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.\n- everything-claude-code:django-security: Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.\n- init: Initialize a new CLAUDE.md file with codebase documentation\n- review: Review a pull request\n- security-review: Complete a security review of the pending changes on the current branch","skillCount":159,"isInitial":true},"type":"attachment","uuid":"6c9ad782-e36b-4797-8e72-afee48e08c46","timestamp":"2026-04-24T12:37:31.943Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"type":"last-prompt","lastPrompt":"are you ok","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503"}
{"type":"permission-mode","permissionMode":"acceptEdits","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503"}
{"parentUuid":"6c9ad782-e36b-4797-8e72-afee48e08c46","isSidechain":false,"type":"system","subtype":"api_error","level":"error","error":{"status":503,"headers":{"content-type":"application/json; charset=utf-8","transfer-encoding":"chunked","connection":"keep-alive","cache-control":"no-cache","date":"Fri, 24 Apr 2026 12:37:32 GMT","via":"1.1 Caddy, ens-cache1.l2hk12[345,0,DP], ens-cache5.sg31[377,0,DP], ens-cache5.sg31[381,0]","timing-allow-origin":"*","set-cookie":["acw_tc=2b6d269917770342519605462e30142e7b1a85e51c4e2dcf7162e7f801;path=/;HttpOnly;Max-Age=3600","cdn_sec_tc=2b6d269917770342519605462e30142e7b1a85e51c4e2dcf7162e7f801;path=/;HttpOnly;Max-Age=3600"],"server":"ESA","x-site-cache-status":"DYNAMIC","x-oneapi-request-id":"202604241237322051342708268d9d6QOsBrUBS","eagleid":"2b6d269917770342519605462e"},"requestID":null,"error":{"error":{"message":"Service Unavailable","type":"error"},"type":"error"},"type":"error"},"retryInMs":570.2921580553007,"retryAttempt":1,"maxRetries":10,"timestamp":"2026-04-24T12:37:32.352Z","uuid":"4c25ea99-cf60-4acf-acb6-1473c72d4529","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"4c25ea99-cf60-4acf-acb6-1473c72d4529","isSidechain":false,"type":"system","subtype":"api_error","level":"error","error":{"status":503,"headers":{"content-type":"application/json; charset=utf-8","transfer-encoding":"chunked","connection":"keep-alive","cache-control":"no-cache","date":"Fri, 24 Apr 2026 12:37:33 GMT","via":"1.1 Caddy, ens-cache24.l2hk12[346,0,DP], ens-cache30.sg31[379,0,DP], ens-cache30.sg31[379,0]","timing-allow-origin":"*","set-cookie":["acw_tc=2b6d26b217770342529323461e7770e4c4f32527aa0460c01e5d45c7b3;path=/;HttpOnly;Max-Age=3600","cdn_sec_tc=2b6d26b217770342529323461e7770e4c4f32527aa0460c01e5d45c7b3;path=/;HttpOnly;Max-Age=3600"],"server":"ESA","x-site-cache-status":"DYNAMIC","x-oneapi-request-id":"202604241237331448505498268d9d6vGT5OFZE","eagleid":"2b6d26b217770342529323461e"},"requestID":null,"error":{"error":{"message":"Service Unavailable","type":"error"},"type":"error"},"type":"error"},"retryInMs":1130.9134995699649,"retryAttempt":2,"maxRetries":10,"timestamp":"2026-04-24T12:37:33.310Z","uuid":"c845b376-6846-4329-8243-02e5c4408e7b","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"c845b376-6846-4329-8243-02e5c4408e7b","isSidechain":false,"type":"system","subtype":"api_error","level":"error","error":{"status":503,"headers":{"content-type":"application/json; charset=utf-8","transfer-encoding":"chunked","connection":"keep-alive","cache-control":"no-cache","date":"Fri, 24 Apr 2026 12:37:34 GMT","via":"1.1 Caddy, ens-cache24.l2hk12[307,0,DP], ens-cache30.sg31[338,0,DP], ens-cache30.sg31[339,0]","timing-allow-origin":"*","set-cookie":["acw_tc=2b6d26b217770342544484729e0f40337ce4e4e90c6db4cf512bcc0e91;path=/;HttpOnly;Max-Age=3600","cdn_sec_tc=2b6d26b217770342544484729e0f40337ce4e4e90c6db4cf512bcc0e91;path=/;HttpOnly;Max-Age=3600"],"server":"ESA","x-site-cache-status":"DYNAMIC","x-oneapi-request-id":"202604241237346367379208268d9d6vO7mBxEz","eagleid":"2b6d26b217770342544484729e"},"requestID":null,"error":{"error":{"message":"Service Unavailable","type":"error"},"type":"error"},"type":"error"},"retryInMs":2091.6094941885794,"retryAttempt":3,"maxRetries":10,"timestamp":"2026-04-24T12:37:34.786Z","uuid":"42fb00e3-be08-4797-9cac-bff74ab3d7a7","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"42fb00e3-be08-4797-9cac-bff74ab3d7a7","isSidechain":false,"type":"system","subtype":"api_error","level":"error","error":{"status":503,"headers":{"content-type":"application/json; charset=utf-8","transfer-encoding":"chunked","connection":"keep-alive","cache-control":"no-cache","date":"Fri, 24 Apr 2026 12:37:37 GMT","via":"1.1 Caddy, ens-cache14.l2hk12[358,0,DP], ens-cache30.sg31[395,0,DP], ens-cache30.sg31[396,0]","timing-allow-origin":"*","set-cookie":["acw_tc=2b6d26b217770342568886782e1edc92c25ab2c7a43630ff5eafe22e24;path=/;HttpOnly;Max-Age=3600","cdn_sec_tc=2b6d26b217770342568886782e1edc92c25ab2c7a43630ff5eafe22e24;path=/;HttpOnly;Max-Age=3600"],"server":"ESA","x-site-cache-status":"DYNAMIC","x-oneapi-request-id":"202604241237371318486978268d9d6NbYCYKRX","eagleid":"2b6d26b217770342568886782e"},"requestID":null,"error":{"error":{"message":"Service Unavailable","type":"error"},"type":"error"},"type":"error"},"retryInMs":4836.080903617839,"retryAttempt":4,"maxRetries":10,"timestamp":"2026-04-24T12:37:37.282Z","uuid":"d14c6baa-75ae-486c-be39-5f927897eb1f","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"type":"last-prompt","lastPrompt":"are you ok","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503"}
{"type":"permission-mode","permissionMode":"acceptEdits","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503"}
{"type":"file-history-snapshot","messageId":"487f2b13-477a-4e79-a904-e7a8cb6e1438","snapshot":{"messageId":"487f2b13-477a-4e79-a904-e7a8cb6e1438","trackedFileBackups":{},"timestamp":"2026-04-24T12:37:45.135Z"},"isSnapshotUpdate":false}
{"parentUuid":"3186ca6d-9189-4641-a9e5-cf923efd79ef","isSidechain":false,"promptId":"cc385079-8fd0-463d-a19c-b95f49e02e43","type":"user","message":{"role":"user","content":"<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"},"isMeta":true,"uuid":"a1b67111-fcc3-4653-aabb-573217b2598e","timestamp":"2026-04-24T12:37:45.131Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"a1b67111-fcc3-4653-aabb-573217b2598e","isSidechain":false,"promptId":"cc385079-8fd0-463d-a19c-b95f49e02e43","type":"user","message":{"role":"user","content":"<command-name>/exit</command-name>\n            <command-message>exit</command-message>\n            <command-args></command-args>"},"uuid":"487f2b13-477a-4e79-a904-e7a8cb6e1438","timestamp":"2026-04-24T12:37:45.131Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}
{"parentUuid":"487f2b13-477a-4e79-a904-e7a8cb6e1438","isSidechain":false,"promptId":"cc385079-8fd0-463d-a19c-b95f49e02e43","type":"user","message":{"role":"user","content":"<local-command-stdout>See ya!</local-command-stdout>"},"uuid":"ef765fdc-eb78-429d-8150-2b4f33012892","timestamp":"2026-04-24T12:37:45.131Z","userType":"external","entrypoint":"cli","cwd":"/root/projects/meeting","sessionId":"acb9fcd2-918c-4235-8a63-558b899a3503","version":"2.1.119","gitBranch":"main"}