Generate a plain-language project overview, comprehensive engineer status update, and surgical documentation enhancement. Reads project docs, specs, dependencies, and git history.
KI-System-Inventar nach EU-KI-VO (VO 2024/1689) – erfasst je KI-System Rolle (Anbieter, Betreiber, Einführer, Händler, Bevollmächtigter, Produkthersteller) und Risikoklas — from…
Use when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumulated learnings to context files.
Utility: Detect and remove AI-generated code slop. Finds unnecessary comments, over-engineering, verbose error handling, premature abstractions. Solo operation, no team needed.
KI-Folgenabschätzung (FRIA nach Art. 27 KI-VO + DSFA nach Art. 35 DSGVO) erstellen – strukturierte Aufnahme, Risikoanalyse, Regulierungsklassifizierung nach KI-VO und DSG — from…
AI-DLC（AI-Driven Development Lifecycle）の統合オーケストレーター。 フェーズ（inception/construction/operations）の開始・継続、セットアップ、エクスプレスモード、フィードバック送信を統一的に実行する。 Use when the user says "インセプション進めて", "start…
Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go).
Create conventional commit messages by analyzing staged changes. Generates semantic commit messages following the Conventional Commits specification.
Generate and maintain project documentation. Creates a lean README as a landing page with detailed docs pages split by topic in the configured docs directory.
Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements.
Fix a specific bug or problem in the codebase. Supports two modes - immediate fix or plan-first. Without arguments executes existing FIX_PLAN.md.
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses.
Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions.
Refine and enhance an existing implementation plan with a second iteration. Re-analyzes the codebase, checks for gaps, missing tasks, wrong dependencies, and improves the plan…
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are…
Plan implementation for a feature or task. Two modes — fast (single quick plan) or full (richer plan with optional git branch/worktree flow).
Create knowledge references from URLs, documents, or files for use by AI agents. Fetch, process, and store structured references in the configured references directory (default:…
Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules.
Run a standalone read-only rules compliance gate against changed files or a git ref. Use when you need a dedicated project-rules check without a full review or verify pass.
Verify completed implementation against the plan. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met.
Генерация 5 привлекательных B2B-сегментов по методологии Advanced Jobs To Be Done. Используй когда пользователь хочет найти сегменты для B2B-продукта, провести сегментацию или…
Генерация 5 привлекательных B2C-сегментов по методологии Advanced Jobs To Be Done. Используй когда пользователь хочет найти сегменты для B2C-продукта, провести сегментацию…
Генерация Top-5 рискованных предположений (RAT — Risky Assumption Test) для продукта по методологии Advanced Jobs To Be Done.
Генерация способов рекрута респондентов для AJTBD-исследования. Используй когда пользователь хочет найти респондентов для интервью, организовать рекрут для исследования или…
生成符合 AKG 项目规范的 Issue 描述文件（Bug Report / RFC / Task）。 支持两种模式：用户描述生成、基于分支 diff 自动生成。 生成的 .md 和 .json 文件写入 .tmp/issue/，经规范校验后供用户确认和提交。
Alertas regulatorias (agente programado) — monitoriza el BOE, DOUE y boletines autonómicos para detectar cambios normativos relevantes.
Quick check if stored knowledge on a topic is still current. Lighter than /align — searches for recent changes and compares against existing knowledge.
Use when generating, vectorizing, or converting images to SVG — logos, icons, illustrations, or 'allow1'/'quiver' references.
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv…
Patch Psyche context after signoff with additional notes. Use when you performed work after /spt:signoff and need to update the context for the next Psyche incarnation.
PRIMARY skill creator. Use this by default when creating ANY skill. If user explicitly asks for a "Claude skill", "Claude-compatible skill", or "universal skill", use…
Use when a prompt is rough, vague, or under-specified and you want it rewritten to high quality before running it.
Guides structured reflection on an analysis design using its Insight Journal. Helps draw conclusions, identify gaps, and decide whether to conclude, refine, or branch.
Guides structured revision of an analysis design based on review comments. Reads review feedback via MCP, tracks progress per comment, and helps fix each issue.
Отображение статусов analysis chain цепочек (одна/все/dashboard). Используй для мониторинга прогресса analysis chain или обновления dashboard в README.
Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends.
Analyzes scenario execution failures using logs, screenshots, and error context to identify root cause. Use when: 실패 분석, 왜 실패, 에러 원인, analyze failure, 시나리오 오류.
Analyze existing MCP server implementation for optimization opportunities and best practice compliance. 分析現有MCP服務器實現，識別優化機會與最佳實踐合規性。
Groom a GitHub issue. Analyzes user intent, domain knowledge, competitive context, and workflow. Usage: /analyze-requirement [issue-number]
Phase 0d of the scenario-first cycle. Synthesises run results from a scenarios doc into a review file in d4d-source/1-reviews/ in the shape parse-review expects, then stops at the…
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues.
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues.
Use when scheduling social copy or reviewing a batch of posts/drafts to measure sentence- and post-length variation — flags metronomic rhythm and same-size posts.
Interactive collaborative analysis with documented discussions, inline exploration, and evolving understanding.
Apply critical rationalist epistemology (Popper, Deutsch) to evaluate reasoning, identify errors, and refine understanding.
Generate Jetpack Compose ad implementations for VslModuleAds SDK. Use for banner, native, interstitial, rewarded, app-open, splash ad formats.
Run MovieFinder project QA pipeline - detekt, unit tests, jacoco coverage report
Создать Anki карточки из фото с рукописными словами от Даши (репетитор немецкого)
Pattern notlarındaki Q&A bölümlerini Anki-uyumlu CSV formatına dönüştürür. patterns/, modern-patterns/, anti-patterns/ altındaki tüm .md dosyalarını tarar.
防止被公司蒸馏成数字员工。输入你的数据源，生成污染内容，让蒸馏出来的AI人格分裂。| Anti-distillation defense. Generate pollution content to break distillation.
Explore a friction point — when something doesn't exist that should. Use when hitting a wall during real work that isn't a bug (diagnose) or a design task (design).
Author User Needs (UN), Product Requirements (PR), and Software Requirements (SR) using EARS-12 patterns with full UN→PR→SR traceability.
Multi-SME review router. Fans out to specialist agents in .claude/agents/aor-sme-*.md and aggregates findings.
Spawn an ad-hoc SME on demand for a one-off review perspective. Optionally persist the SME for reuse.
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
Review and selectively apply proposals from .design/reflections/.md. Diffs each proposal, prompts user to accept/skip/edit, then writes changes.
GitHub PR 리뷰 코멘트를 가져와 분석 보고서를 마크다운 파일로 저장한 뒤, 사용자 승인 후 코드 수정까지 수행. "PR 리뷰 반영해줘", "코드리뷰 코멘트 처리해줘", "리뷰 적용해", "리뷰 피드백 수정해줘", "review comment 처리", "리뷰 보고서 만들어줘" 같은 요청에 반드시 이 스킬을 사용할…
Apply the marks in an Obelus bundle as a revision — minimal-diff edits to this paper's source.
Map a web UI and generate a Claude automation skill via parallel reconnaissance, synthesis, and iterative validation.