技術寫作

Azure DevOps Wiki management skill. Use when working with Azure DevOps wikis for: (1) Creating and organizing wiki pages - provisioned or code-as-wiki, (2) Markdown formatting - TOC, Mermaid diagrams, YAML metadata, code blocks, (3) Wiki structure - .order files, subpages, attachments, (4) Best practices - naming conventions, navigation, searchability, (5) CLI operations - az devops wiki commands, (6) Git-based wiki workflows - clone, edit offline, push changes. Supports both provisioned wikis and published code wikis.

Mandatory spec folder workflow orchestrating documentation level selection (0-3), template selection, and folder creation for all file modifications through hook-assisted enforcement and context auto-save.

Use this skill at the end of a task to ensure documentation matches the code.

Guide experienced developers through GREEN phase of TDD cycle - writing minimal implementation to pass failing tests

Confluence documentation including pages, spaces, templates, and Atlassian integration. Activate for wiki pages, documentation, knowledge bases, and team collaboration.

Reverse-engineer specifications from undocumented code. Use for legacy systems or creating documentation from implementations.

Automated code review using external AI tools (codex and/or gemini-cli). Use this skill after writing or editing code to get a second opinion from other AI models, then implement their recommendations with user approval.

Implement Semantic Retrieval Optimization for AI search visibility. Use when performing SRO audits, building entity maps, designing SCN architecture, writing retrieval-optimized content, implementing schema markup, calibrating trust signals, analyzing query intent, assessing technical eligibility, or creating AI-ready content strategies. Triggers on semantic SEO, entity mapping, SCN, E-E-A-T, AI search optimization, passage engineering, knowledge graph, trust signals, or retrieval optimization requests.

4-layer knowledge capture system for development sessions. Use when user says /mem (quick capture), /distill (extract patterns), /td (post-task retrospective with Before/After context), /improve (work on pending items), or /commit (atomic commits via TDG). Manages docs/learnings/, docs/knowledge-base/, and docs/retrospective/ directories.

Use when refining an architecture or design document based on new learnings, before a rewrite. Use when you have an existing doc and related docs to cross-check against. Use when you need systematic section-by-section validation of decisions.

Comprehensive code documentation standards and guidelines for maintaining up-to-date documentation across Python, HTML, CSS, and JavaScript codebases. Use when creating or modifying code to ensure proper documentation practices and maintainable code.

Enhanced documentation unified validation with AI-powered features

Autonomous agent creation skill that generates specialized agent definitions from templates. Use when you need to create new Claude Code agents for specific tasks like code review, deployment automation, testing, documentation, security analysis, or general-purpose research. This skill automates the creation of agent definition files (.md) with proper structure, workflow instructions, and tool access patterns following Miyabi framework standards.

Creates comprehensive ServiceNow change request documentation when users request CR creation, need to generate change requests, ask to prepare deployment documentation, or mention creating release documentation. Automatically analyzes git history, queries functional requirements from BigQuery, generates technical change summaries, and creates properly formatted YAML files for L'Oréal BTDP deployments.

Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission rules aligned with official documentation.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

This skill should be used when creating Galaxy Hub news posts, writing content for galaxyproject.org/news, or converting content to Galaxy Hub markdown format.

Write strategic, behavior-focused tests for core user flows and critical functionality using Vitest for unit tests and Playwright for end-to-end testing. Use this skill when writing test files, testing utilities, or implementing test coverage for critical paths. When working on Vitest test files (.test.ts, .spec.ts), Playwright E2E test suites, test setup and configuration files (vitest.config.ts, test-setup.ts), mock implementations for external dependencies, testing utility functions or test helpers, component test files using React Testing Library, API route test files, or integration tests for Content Collections and data fetching logic.

"Am I *doing* or just *describing* that I should do?" - Counters documentation-over-action patterns. Triggers when: (1) about to say "should create", "need to fix", "I recommend" instead of acting, (2) end of work blocks before reporting completion, (3) reporting success while failures exist, (4) creating docs/plans without executing, (5) explaining fixes instead of implementing. Enforces ACT FIRST, DOCUMENT AFTER. Does NOT trigger for: genuine planning phases, user-requested documentation, or blocked situations requiring input.

CSS/XPath selector best practices for web automation (dropdowns, dynamic tables, nested components). Use when: writing selectors, handling dynamic content, React apps, robust attributes, dynamic element handling, selector maintenance.