Classify a repository by app type and route it to the correct standards branch, policy profile, and verification gates.
Take a labeled snapshot of repo state (sha, open issue count, open PR count, latest release, drafts, uncommitted files) and optionally diff against a prior snapshot.
Enforce file organization, naming conventions, and app-type-specific project layouts. Use when creating, restructuring, or onboarding a repository.
Audit downstream repo alignment with upstream repomatic reference, covering workflows, configs, and conventions.
Generate dependency graphs, audit pyproject.toml declarations against version policy, explore unused dependency APIs that could simplify code, and modernize code against the…
Optimize GitHub topics for discoverability by analyzing competition on topic pages.
Report a bug as a GitHub Issue with description, reproduction steps, and initial analysis
Usage instructions for the health report generation command with examples and troubleshooting tips.
Manage and refine vision-powers reports: list, open, delete, search, and refine sections. Use when asked to list, open, delete, search, or update generated HTML reports.
Set up new repositories following Labee standards. Use this when initializing a new project repository.
Repurpose a YouTube video into an optimized Instagram post. Extracts video content, generates a caption and visual, shows a review, and publishes via Blotato.
以資深 PM 角色，從自然語言需求描述撰寫功能需求文件（FRD）或功能調整需求文件（CR-FRD）。 Use when user says "寫需求文件", "我有個新功能想法", "幫我整理需求", "write FRD", "new feature", "功能需求", "我要開發一個新功能", "需要一份需求文件", "幫我寫規格".
Use when: auditing a draft specification, requirements document, feature request, user story, or product brief for ambiguity: vague quantifiers, undefined terms, TBD placeholders,…
Adaptive-depth requirements analysis for AIDLC Inception. Simple features produce a 1-paragraph brief; complex features produce structured REQ-001/REQ-002 functional and…
Author, update, and validate functional and non-functional requirements as a source of truth using atomic requirement units with explicit user approval.
Interview-only sub-skill that produces a structured Q&A markdown block for /requirements-write to synthesize. Invoked by the /cortex-core:requirements orchestrator.
Consume approved requirements to drive planning, implementation, and validation with explicit traceability and mandatory HITL for ambiguity or tradeoffs.
git reset（HEAD / ブランチポインタの移動）の安全運用ルール。reset --hard は未コミット変更をどこにも残さず消せる唯一の日常操作であり、git reset を 1 つでも実行する前に必ず本スキルを参照する。「reset して」「巻き戻して」「直前のコミットを取り消して」「コミットをやり直したい」「変更を全部捨てて」「HEAD…
【已废弃】原 resignation-negotiation 的 typo 版本。请使用 resignation-negotiation。 本 skill 已废弃，仅为历史兼容保留。功能请使用 resignation-negotiation。 适用情形：用户提及resignation negoitation相关事项。
Evaluates resilience and fault tolerance, including failure modes, retries, timeouts, and graceful degradation. Use when reviewing reliability under failure conditions.
Resize images to social media aspect ratios using Kie.ai AI-powered remix. Intelligently adjusts composition without distorting or skewing.
低解像度住所（muni_centroid / oaza_chome）をWebで調査し、番地レベル（gaiku）の詳細住所を特定して address_overrides.yaml に登録する。出力CSVに muni_centroid や oaza_chome が残っている場合や、住所精度を改善したい場合に使用する。
Triage, fix, and resolve bot code review comments (CodeRabbit, Gemini Code Assist) on PRs. Use when asked to resolve bot reviews, given a PR URL, or on '/resolve-bot-reviews'.
Rebase a PR branch onto the primary branch, resolve any merge conflicts, and force-push to get it ready for merge.
Process PR review feedback in bulk — triage, fix in parallel, and reply with verdicts.
renovate が作った依存アップデート PR を、マージできる状態まで持っていく。そもそも上げてよいかを先に判断し、CI の失敗をコード起因・承認待ち・一時的な不調に切り分けて、追随が要るものを直す。検討したことは PR にコメントで残す。マージと approve はしない。ユーザーが「renovate の PR…
Read Meta/RESOLVER.md, parse rules and statuses, and answer a natural-language question by surfacing the matching rule(s). Trigger /resolver-query .
Launch a localhost browser dashboard showing live Claude process tree, memory use, MCP servers, and orphan count
Work through review comments on a GitHub PR. Use when asked to respond to PR comments or review feedback
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees.
Generate a structured response-to-referees document from a referee report and the revised manuscript.
ambari 大数据集群管理工具，当运维操作大数据集群相关服务（比如 hive_server, hive_metastore）时使用，该操作会触发一个异步的 RESTART 请求，捕获请求 ID，轮询 request_status 直至状态变为 COMPLETED（或 FAILED/ABORTED/TIMEDOUT），并输出最终的…
Search for Japanese restaurants using the `hpp` CLI (HotPepper Gourmet API). Use when the user wants to find a restaurant, plan a dinner, search for izakayas, or book a group meal…
Restore saved work progress from .bdk/save-progress/ to resume a previous session. Loads referenced plans, creates TaskList items for remaining work.
Resume an existing AEGIS phase-3 implementation from its canonical pointer after rechecking source, target and Enterprise Standards drift.
AUTO-TRIGGER: Apply this skill automatically when the user pastes or shares a job posting, job description, or any role they are considering applying for.
Retarget an active manuscript to a different journal by reconciling venue identity, files, bibliography, citations, and submission-facing metadata.
Normalize agent conversation titles onto a dated `MMDD｜TYPE｜subject` scheme — English by default, Chinese with `--lang=zh` — across Codex, Claude Code, and any client that exposes…
Brutally honest engineering retrospective. Analyzes git history for what actually happened — not what people think happened.
Make every signed-in account in the desktop app hold the same conversations, byte for byte. The app keeps one sidebar index per account and writes a rename, star, archive or…
Review a local diff or PR for unnecessary durable surface: new files, public types, interface methods, DTOs/view models, helpers, routes, DI registrations, services, repositories,…
Reverse brainstorm, make it worse, flip the problem, opposite approach. Ask "How could this get worse?" then invert answers into solutions.
Assess decision risk by classifying as one-way or two-way door — use when calibrating how much analysis a decision deserves before committing
Review kode backend NestJS/Knex sesuai checklist project. Gunakan saat user minta review modul, service, controller, repository, atau file backend apapun.
Audit and fix CLAUDE.md files using a tiered binary checklist based on official Anthropic best practices and community guidelines.
Review scientific/technical writing for coherence: overall structure, section-level flow, storyline consistency, and logical gaps.
Confirm a task was fully executed and the change works — static completeness audit followed by empirical runtime evidence.
Prüft Topic-JSON-Inhalte auf argumentative Qualität, Ausgewogenheit und intellektuelle Redlichkeit. Verwenden beim Erstellen neuer Themeninhalte, beim Hinzufügen von Abschnitten…
Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis.
Review codebase conventions — a specific domain or all domains in parallel. Use when asked to review or check conventions.
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree.
Создание review.md с секцией Контекст ревью — читает цепочку документов, запускает extract-svc-context.py, заполняет сервисные блоки.
Use when: enforcing review-fix cycle quality gates, verifying review findings are closed, checking merge readiness, validating fix evidence after a review round, deciding go/no-go…
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
Review the diff against the base branch. Use when asked to "review the diff", "check what changed", "review changes against main", "is this PR complete", or when evaluating…
Use when: resolving a stalled disagreement between reviewer and author in a code review thread, classifying a review dispute as fact versus standard versus preference, anchoring a…
Reviews a feature implementation by reading the chain artifacts (plan and result) and comparing against the original requirements.
Use when: writing, rewriting, or auditing code review findings, review comments, or PR feedback for quality: severity tag, evidence anchor, concrete expected fix, and an explicit…
ProcessFlow JSON の実行セマンティクスを専門レビュー (変数ライフサイクル / TX スコープ / runIf 連鎖 / 補償整合 / event 双方向 / 画面項目連携 / SQL alias 整合 / 業務 semantic gap)。Step 0.5 で 12 バリデータを機械実行 (#599 / #621)、Step 1 で 17…
Process follow-up files from autonomous runs (ops:batch-execute, ops:get-to-work). Walks through each item, presents options, takes action, and cleans up.