Documentation

Trove is a minimal logging facade for Clojure/Script supporting both traditional and structured logging. Use when writing libraries that need logging without forcing a backend choice, or when you need rich data-oriented logging with flexible filtering.

Prevent SQL injection by using $queryRaw tagged templates instead of $queryRawUnsafe. Use when writing raw SQL queries or dynamic queries.

OpenAPI/Swagger 사양, 인증 패턴, 버전 관리 전략 및 모범 사례를 사용하여 RESTful 및 GraphQL API를 설계하고 문서화합니다. 사용 사례: (1) API 사양 생성, (2) REST 엔드포인트 설계, (3) GraphQL 스키마 설계, (4) API 인증 및 권한 부여, (5) API 버전 관리 전략, (6) 문서 생성

Logs architectural decisions to docs/DECISIONS.md in ADR format.Use when: making significant architectural or technology choices.Integrates with /craft and /why commands.

Auto-check and update key documentation before Git commits to keep docs in sync with code.LOAD THIS SKILL WHEN: Before git commit/push | User says "準備提交", "sync docs", "發布", "release" | code changes affect documentation.CAPABILITIES: Update README, CHANGELOG, ROADMAP, ARCHITECTURE, Memory Bank; minimal changes; semantic versioning; Keep a Changelog format.

Write comments explaining WHAT and WHY, never temporal context or history

Lightweight search utility for Toss / Apps-in-Toss llms-full.txt docs, caching sources and ranking snippets with keyword + similarity (Korean-aware) scoring.

Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.

Review workscript node implementations for alignment with NODE_DEVELOPMENT_BLUEPRINT.md and consistency with the new-node skill. Use when reviewing node code, auditing node implementations, checking for compliance with single-edge return pattern, validating ai_hints metadata consistency, or ensuring thorough documentation of state interactions. Triggers on requests like "review this node", "check node compliance", "audit node implementation", or "validate node metadata".

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.

Generate images using Nano Banana Pro (Gemini 3 Pro Preview). Use when creating app icons, logos, UI graphics, marketing banners, social media images, illustrations, diagrams, or any visual assets. Triggers include phrases like 'generate an image', 'create a graphic', 'make an icon', 'design a logo', 'create a banner', or any request needing visual content.

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.