技術寫作

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

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.

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.

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.

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.

Analyze and enhance Makefiles for complete user functionality coverage.Triggers: Makefile analysis, Makefile gaps, missing targets, plugin release,Makefile coverage, build targets, make dogfood, plugin qualityUse when: analyzing Makefile completeness before releasing plugins, identifyinggaps during plugin maintenance, scoring Makefiles against best practices,verifying Makefiles support standard developer workflowsDO NOT use when: writing initial Makefiles from scratch.DO NOT use when: debugging specific build target failures.DO NOT use when: creating custom non-standard build systems.Use this skill BEFORE releasing any plugin to verify Makefile coverage.

JS/TS conventions for syntax, modules, and types. Use when writing or reviewing JavaScript/TypeScript code.

Generate program dashboards, GitHub-ready comment digests, and CSV summariessourced from Minister's tracker data.Triggers: initiative pulse, status report, weekly update, stakeholder briefing,github dashboard, blocker radar, initiative health, program metricsUse when: creating status reports, weekly updates, stakeholder briefings,generating GitHub comment digests, tracking initiative healthDO NOT use when: release gates/readiness - use release-health-gates.DO NOT use when: project planning - use spec-kit:speckit-orchestrator.Outputs markdown digests and CSV exports for GitHub issues and PRs.

Evaluate and improve Claude skill quality through auditing.Triggers: skill audit, quality review, compliance check, improvement suggestions,token usage analysis, skill evaluation, skill assessment, skill optimization,skill standards, skill metrics, skill performanceUse when: reviewing skill quality, preparing skills for production, auditingexisting skills, generating improvement recommendations, checking compliancewith standards, analyzing token efficiency, benchmarking skill performanceDO NOT use when: creating new skills from scratch - use modular-skills instead.DO NOT use when: writing prose for humans - use writing-clearly-and-concisely.DO NOT use when: need architectural design patterns - use modular-skills.Use this skill BEFORE shipping any skill to production. Check even if unsure.

Generate terminal recordings using VHS (Charmbracelet) tape files.Executes tape files to produce GIF outputs of terminal sessions.Triggers: terminal recording, vhs tape, terminal demo, cli demoUse when: creating terminal recordings for tutorials and documentation

Guide to effective Claude Code skill authoring using TDD methodology andpersuasion principles.Triggers: skill authoring, skill writing, new skill, TDD skills, skill creation,skill best practices, skill validation, skill deployment, skill complianceUse when: creating new skills from scratch, improving existing skills withlow compliance rates, learning skill authoring best practices, validatingskill quality before deployment, understanding what makes skills effectiveDO NOT use when: evaluating existing skills - use skills-eval instead.DO NOT use when: analyzing skill architecture - use modular-skills instead.DO NOT use when: writing general documentation for humans.YOU MUST write a failing test before writing any skill. This is the Iron Law.

Methodology for summarizing changes, extracting insights, and identifying follow-up actions.Triggers: catchup, what changed, summarize changes, context acquisition, handoff,progress review, recent changes, git log analysis, sprint summaryUse when: resuming work after absence, preparing handoff documentation, reviewingsprint progress, analyzing git history for contextDO NOT use when: doing detailed diff analysis - use diff-analysis instead.DO NOT use when: full code review needed - use review-core instead.Use this skill to quickly understand "what changed and what matters".

Workflow for capturing evidence and citations to create reproducible analysesand audit trails.Triggers: evidence capture, citations, reproducible analysis, audit trail,documentation, evidence logging, findings documentationUse when: conducting any review that needs evidence trails, creating auditdocumentation, ensuring reproducibility of analysesDO NOT use when: quick informal checks without documentation needs.DO NOT use when: structured output is the focus - use structured-output.Use this skill as foundation for all evidence-based review workflows.

Create clear, testable specifications with user stories and acceptance criteria.Triggers: spec writing, feature specification, requirements, user storiesUse when: creating new specifications or writing acceptance criteriaDO NOT use when: generating implementation tasks - use task-planning.

Orchestrate tutorial generation from VHS tapes and Playwright specs to dual-tone markdown with GIF recording.Triggers: tutorial update, gif generation, tape recording, update tutorial, regenerate gifs, tutorial manifestUse when: regenerating tutorial GIFs, updating documentation demos, creating tutorials from tape filesDO NOT use when: only updating text - use doc-updates.DO NOT use when: only capturing browser - use scry:browser-recording directly.

Evaluate public API surfaces against internal guidelines and external exemplars.Triggers: API review, API design, consistency audit, API documentation,versioning, surface inventory, exemplar researchUse when: reviewing API design, auditing consistency, governing documentation,researching API exemplarsDO NOT use when: architecture review - use architecture-review.DO NOT use when: implementation bugs - use bug-review.Use this skill for API surface evaluation and design review.

Python testing with pytest, fixtures, mocking, and TDD workflows.Triggers: pytest, unit tests, test fixtures, mocking, TDD, test suite, coverage,test-driven development, testing patterns, parameterized testsUse when: writing unit tests, setting up test suites, implementing TDD,configuring pytest, creating fixtures, async testingDO NOT use when: evaluating test quality - use pensive:test-review instead.DO NOT use when: infrastructure test config - use leyline:pytest-config.Consult this skill for Python testing implementation and patterns.

Code quality practices: error handling, validation, logging, and DRY. Use when writing or reviewing code.

Systematic methodology to reduce skill file size through externalization,consolidation, and progressive loading patterns.Triggers: large skill, skill optimization, skill size, 300 lines, inline code,skill refactoring, skill context reduction, skill modularizationUse when: skills exceed 300 lines, multiple code blocks (10+) with similarfunctionality, heavy Python inline with markdown, functions >20 lines embeddedDO NOT use when: skill is under 300 lines and well-organized.DO NOT use when: creating new skills - use modular-skills instead.Consult this skill when skills-eval shows "Large skill file" warnings.