Documentation

Generate MDX blog posts or recaps from session logs in `sessions/articles`. Use when the user asks to turn daily session notes into publishable blog posts, define writing style or linking rules for those posts, or produce MDX drafts that follow the project's standards and file location.

Keep documentation in sync with code changes across README, docs sites, API docs, runbooks, and configuration. Use when the user asks to update docs, ensure docs match behavior, or prepare docs for a release/PR.

Generates documentation files including NotebookLM YAML and slide content. Use when user mentions ドキュメント, document, YAML, NotebookLM, スライド, slide, プレゼン. Do NOT load for: 実装作業, コード修正, レビュー, デプロイ.

Writing standards, React components, and MDX patterns for docs.cloudposse.com. Use when creating or editing documentation content.

Guides VibeCoder (non-technical users) through natural language development (legacy). Use when user mentions どうすればいい, 次は何, 使い方, 困った, help, what should I do. Do NOT load for: 技術者向け作業, 直接的な実装指示, レビュー.

Building, rendering library docs, and deploying docs.cloudposse.com. Use when working with the Docusaurus build process or regenerating auto-generated content.

CSS styles, color themes, and visual conventions for docs.cloudposse.com. Use when styling components, mermaid diagrams, or working with site theming.

Ingest new procedural memory (skills, patterns, docs) into the vector database.

Create, review, and refactor project documentation (README, AGENTS.md, architecture docs, runbooks, API docs) with deep codebase analysis, clear markdown structure, and diagrams/user flows. Use when asked to write or improve docs, audit existing documentation for accuracy or quality, generate diagrams/flows, or assess agent-first docs like AGENTS.md/PLANS.md for freshness and completeness.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.

Systematic approach for gathering authoritative, version-accurate documentation. Claude invokes this skill when research is needed before implementation. Ensures truth over speed while achieving both.

Bump project versions across configs, docs, and changelog usinggit-workspace-review context.Triggers: version bump, semver, release version, changelog update, versionupdate, package version, release preparationUse when: bumping project versions, updating changelogs, preparing releases,coordinating version changes across filesDO NOT use when: just documentation updates - use doc-updates.DO NOT use when: full PR preparation - use pr-prep.Use this skill for version management and release preparation.

Generate phased, dependency-ordered tasks from specs. Identifies parallelization opportunities.Triggers: task planning, dependency ordering, phased breakdown, parallel tasksUse when: converting specifications to implementation tasksDO NOT use when: writing specifications - use spec-writing.

Systematically uncover and fix bugs using language-specific expertise andreproducible evidence.Triggers: bug hunting, defect detection, debugging, fix verification, bug fix,regression check, error investigation, defect documentationUse when: deep bug hunting needed, documenting defects, verifying fixes,systematic debugging requiredDO NOT use when: test coverage audit - use test-review instead.DO NOT use when: architecture issues - use architecture-review.Use this skill for systematic bug hunting with evidence trails.

Detect codebase bloat through progressive analysis: dead code, duplication, complexity, and documentation bloat.Triggers: bloat detection, dead code, code cleanup, duplication, redundancy, codebase health, technical debt, unused codeUse when: preparing for refactoring, context usage is high, quarterly maintenance, pre-release cleanupDO NOT use when: actively developing new features, time-sensitive bug fixes.DO NOT use when: codebase is < 1000 lines (insufficient scale for bloat).Progressive 3-tier detection: quick scan → targeted analysis → deep audit.

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking,and quality assessment.Triggers: test audit, test coverage, test quality, TDD, BDD, test gaps,test improvement, coverage analysis, test remediationUse when: auditing test suites, analyzing coverage gaps, improving testquality, evaluating TDD/BDD complianceDO NOT use when: writing new tests - use parseltongue:python-testing.DO NOT use when: updating existing tests - use sanctum:test-updates.Use this skill for test suite evaluation and quality assessment.

Consolidate README content using language-aware exemplars, internal doc linkage,and reproducible evidence.Triggers: README update, documentation refresh, readme structure, exemplar research,language-aware docs, readme modernization, project documentationUse when: README requires structural refresh, adding features to documentation,aligning readme with exemplar standards, improving project presentationDO NOT use when: updating inline docs - use doc-updates.DO NOT use when: consolidating ephemeral reports - use doc-consolidation.Run git-workspace-review first to capture repo context.

Go conventions for hexagonal architecture, project structure, error handling, testing, and observability. Use when writing Go services.

detailed hook evaluation framework for Claude Code and Agent SDK hooks.Triggers: hook audit, hook security, hook performance, hook compliance,SDK hooks, hook evaluation, hook benchmarking, hook vulnerabilityUse when: auditing existing hooks for security vulnerabilities, benchmarkinghook performance, implementing hooks using Python SDK, understanding hookcallback signatures, validating hooks against compliance standardsDO NOT use when: deciding hook placement - use hook-scope-guide instead.DO NOT use when: writing hook rules from scratch - use hookify instead.DO NOT use when: validating plugin structure - use validate-plugin instead.Use this skill BEFORE deploying hooks to production.