持續整合/部署

Generate comprehensive network infrastructure reports including health status, performance analysis, security audits, and capacity planning recommendations.

Apply critical git safety protocols before any git operations, especially in collaborative environments. Use when performing git commands, managing files, or making destructive changes.

Generate polished one-pagers for CollectiveGood across three audience types: investors,academic collaborators, and commercial partners. Incorporates competitive positioning,strategy documents, and market intelligence to produce consistent, compelling materials.

Fetch up-to-date library documentation directly into context to prevent hallucinated APIs and outdated code examples. Use when user says "use docs", "fetch docs for [library]", "check [library] docs", or asks about a library's API, methods, or usage patterns and current documentation would be helpful. Also use proactively when generating code for libraries where version-specific accuracy matters.

Analyze gaps between codebase and PRD documentation, generate discrepancies report. Use this skill when you need to sync documentation with implementation, find undocumented features, or identify unbuilt requirements.

Guides structured evaluation of design options with trade-off analysis. Use this skill when choosing architectures, selecting technologies, evaluating implementation approaches, or making design decisions.

Build MCP (Model Context Protocol) servers with tools, prompts, and resources. Use when developing MCP servers, implementing tools/prompts/resources, debugging MCP issues, writing tests, or deploying servers. Covers SDK patterns, validation, and best practices.

Configure transaction isolation levels to prevent race conditions and handle concurrent access. Use when dealing with concurrent updates, financial operations, inventory management, or when users mention race conditions, dirty reads, phantom reads, or concurrent modifications.

Check decisions against beliefs, wisdom, and intentions. Use before significant actions to ensure coherence with accumulated knowledge.

Complete 6-step self-healing development loop per .council/AGENTS.md. Use for any feature implementation from start to finish.

Teaches when to use local state vs global state (Context) in React 19. Use when deciding state management strategy, avoiding prop drilling, or architecting component state.

Write minimal strategic tests during development focusing on core user flows and critical paths, deferring comprehensive edge case testing until after feature completion. Use this skill when writing tests for completed features, testing critical user workflows, implementing integration tests, creating end-to-end tests with Playwright, writing unit tests for core logic, or determining testing strategy and priorities. Apply when working on test files (*.test.ts, *.spec.ts, *.test.tsx), Playwright test files (e2e/*.spec.ts), test configuration, or when deciding what to test during feature development. This skill ensures minimal tests during active development (complete the feature first), focus exclusively on core user flows and critical paths (skip non-critical utilities), deferred edge case and validation testing until dedicated testing phases, behavior testing over implementation details (test WHAT not HOW), descriptive test names that explain the behavior and expected outcome, mocked external dependencies (d

MCP orchestration via TypeScript execution for efficient multi-tool workflows. Use Code Mode for ALL MCP tool calls (ClickUp, Notion, Figma, Webflow, Chrome DevTools, etc.). Provides 98.7% context reduction, 60% faster execution, and type-safe invocation. Mandatory for external tool integration.

Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, tools, and workflows. Generates production-ready MCP servers with TypeScript/Python SDKs, configuration templates, and Claude Desktop integration. Includes testing workflow with MCP Inspector. Not for modifying existing MCP servers or non-MCP integrations.

Transform one piece of content into platform-optimized assets across LinkedIn, Twitter/X, Instagram, TikTok, and YouTube. Use when someone has existing content (blog post, newsletter, podcast, video) and wants to maximize distribution. Covers format specs, hook formulas, algorithm signals, and creator-tested patterns for each platform. Triggers on: repurpose this, turn this into social posts, atomize this content, create social content from, LinkedIn post from this, thread from this. Outputs platform-specific content ready to publish.

Customizes Docusaurus for the Physical AI & Humanoid Robotics textbook with specialized UI/UX, dark mode, accessibility features, and interactive elements.

Map IC'ALPS Hardware and Software pipeline stages with double granularity (No-go, Abandonnée, Perdue, Gagnée). Use for deal stage mapping and business logic.

Manage the PR review feedback loop: monitor CI checks, fetch review comments, and iterate on fixes.Use when: (1) pushing changes to a PR and waiting for CI/reviews, (2) user says "new reviews available",(3) iterating on PR feedback from Gemini, Cursor, Claude, or other reviewers, (4) monitoring PR status.Supports multiple review bots: Gemini Code Assist, Cursor Bugbot, and Claude agent fallback.Automatically detects priority levels from different bot formats and handles rate limits.RECOMMENDED: Spawn a Task agent (subagent_type: general-purpose) to execute the review loop autonomously.See "Recommended Usage: Run as Task Agent" section for the prompt template.CRITICAL: When using this skill, NEVER use raw git commit/push commands. ALWAYS use commit-and-push.sh script.The user has NOT granted permission for raw git commands - only the script is allowed.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends AI's capabilities with specialized knowledge, workflows, or tool integrations.

Visual generation converges toward accepting first output ("looks good enough") and following technical specifications rigidly. This produces generic aesthetics and misses Gemini 3's reasoning capabilities. This skill provides multi-turn reasoning partnership methodology with professional quality standards.