Explore skills
66,821 skills found
issue-implement
特定の GitHub issue への実装着手と PR 作成を依頼されたときに使う。issue 番号・URL・会話内で選んだ issue のいずれかを起点に、実装・commit・lint・受け入れ条件チェック・cross-review・PR 作成・CI 確認まで一気通貫で自動進行する。コードを書いてプルリクを出す作業全般が対象で、issue 選定相談・タイトル編集・クローズ操作・PR レビュー単体には使わない。
issue-pick
Use when the user has NOT yet decided which issue to work on and needs help choosing. This is the pre-decision advisory phase: the user is weighing multiple open issues and wants structured guidance — not implementation. Key triggers: asking which issue to prioritize or tackle next, identifying which issues are blocked vs. ready to start independently, selecting issues that fit limited capacity (s
auto-commit
Analyze pending git changes and write a structured, conventional-commit plan to COMMITS.md so the user can review and stage commits in batches before committing. Use whenever the user wants to group working-tree or staged changes into sensible commits, draft commit messages for a dirty working tree, or prepare a commit plan from a diff.
ci-audit
Audit the latest GitHub Actions workflow runs on the current branch/PR for warnings, errors, failures, deprecation notices, and other log noise — then fix what's fixable in-repo (workflow YAML, configs, source, tests). Hands commit + push back to the developer. Use after CI finishes and before merge, or whenever the user asks about failing/noisy CI — phrasings like "audit the PR", "why did CI fail
validate-skill
Validates Claude Code skills against official best practices from Anthropic documentation. Fetches latest documentation dynamically to ensure current standards. Checks frontmatter, structure, line count, descriptions, references, workflows, and provides actionable recommendations. Use when asked to validate skill, check skill quality, review skill, or audit skill compliance.
RecordsManager
Expert record keeping system with paperless-ngx integration, country-specific taxonomies, and intelligent document management. USE WHEN upload document, store file, organize records, find document, search papers, tag documents, delete records, retention check, archive documents, add entity, create trust, validate trust, workflow create, FTE check, connection test, system status, check status.
vallorcine
Run a full architecture decision session for a given problem
planning-worldbuilding
Decomposes a large worldbuilding task into a sequenced plan with concrete steps, target files, verification criteria, and dependency order. Use before building a new civilization, designing a planet, or any task spanning more than 3 files. Triggers on "plan this", "break this down", "how should we approach", "build plan for", or "what is the sequence". Does NOT write content — produces the plan on
verifying-completion
Runs a mandatory completion checklist before declaring any worldbuilding task finished. Catches missing frontmatter, broken cross-references, unlinked glossary terms, and deferral language. Use after writing any content, before reporting task complete, or when user says "is this done", "verify", "check my work", or "completion check". Does NOT write content — only verifies.
writing-science
Writes new science files following academic prose standards: third-person voice, present tense for laws, in-universe terminology, consistent equation formatting, citation format. Use when creating new physics, chemistry, biology, or science files, expanding existing science content, or when user says "write", "create", "draft", "formalize", or "derive" in a science context. Does NOT write civiliza
writing-style
Generates a WRITING.md file with YAML tokens for prose consistency — voice, tense, forbidden words, citation format, equation format, locked spellings — paired with usage rationale. Use when establishing prose standards, updating style rules, or when user says "WRITING.md", "style guide", "prose standards", "writing tokens", "voice", "style system", or "writing rules". Does NOT write content — gen
writing-worldbuilding
Writes new worldbuilding content: civilizations, characters, locations, factions, events, languages, or narrative elements. Use when creating new entries, expanding existing ones, or when user says "create", "write", "add", "flesh out", "build", or "expand" for any non-science content. Does NOT write science files — use /writing-science for that.