Go through PR review feedback one by one, prioritizing human comments over bot/CI comments. Use when the user says "pr loop", "review feedback", "go through PR comments", or wants…
GitHub PR URL을 인자로 받아 merge conflict(병합 충돌) 유무를 판정하고, 충돌이 없으면 즉시 종료한다. 충돌이 있으면 충돌 파일/원인 커밋을 추적해 어떤 PR/브랜치에서 유입된 변경인지 식별한 뒤, 양쪽 PR/이슈의 plans(또는 docs/plan) 문서를 찾아 의도한 구현을 모두 보존하는…
Address open GitHub PR review comments automatically. For each unresolved comment, classifies as MUST-FIX (edit code), ACK (reply only), or DISCUSS (ask back).
Run pre-PR verification (Biome lint+format + tests) for frontend, backend, or both — auto-detects from changed files
Use when: auditing your own change before requesting review, running a pre-review or pre-PR self-check, checking diff hygiene, leftover debug code, commented-out code, unrelated…
Convert the user's initial request into a fully-specified, unambiguous, execution-ready prompt through structured interaction.
Prepara lo studente a un esame con una semplice interrogazione conversazionale basata sui riassunti di un'intera materia SpaccaScuola.
Commits changes grouped by done-plans, rebases main, builds API and webapp, then creates or updates a PR. Replaces the commit command.
Creates zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint files.
Create text effects impossible with CSS alone — kinetic typography, flowing text around animated obstacles, calligrams, shrinkwrap chat bubbles, typographic ASCII art, glyph path…
Oriente une entreprise en difficulté vers le bon dispositif préventif et en prépare la demande : mandat ad hoc (L.611-3), conciliation (L.611-4 s., accord constaté ou homologué,…
Find the revenue-maximizing pricing/tier grid for a SaaS or data product and PROVE the ranking is robust — not just assert it.
Recommend a pricing strategy — model, price points, packaging, and elasticity guard-rails — grounded in Van Westendorp, value-based pricing, and anchoring/decoy frameworks
Printing Press CLI for Printing Press Golden. Purpose-built fixture for golden generation coverage.
Printing Press CLI for Printing Press Rich. Purpose-built fixture for rich auth env-var model coverage.
태스크 우선순위 및 실행 순서를 변경합니다. 사용자가 '우선순위 변경', '순서 변경', '먼저 실행'을 말하거나 /mst:priority를 호출할 때 사용. 태스크 상태 확인에는 /mst:inspect를, 태스크 취소에는 /mst:cancel을 사용.
프로그래머스/릿코드 문제 URL을 받아 풀이용 껍데기 Java 클래스를 생성한다. 사용자가 문제 URL을 주거나 "문제 풀 거야", "클래스 만들어줘" 등을 요청할 때 사용.
Document a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what, writing an SOP for…
GitHub Issue 번호를 받아 이슈 분석 → 구현 계획 → 워크트리 생성 → 구현 → 검증 → PR 생성 → CI/리뷰 모니터링 → 병합까지 전체 개발 사이클을 자동화합니다.
Bridge between Linear (execution) and Productive.io (customer value). Translates internal work into customer-facing service reports.
Interact with the ProductLift API — list, create, update, and delete posts, users, votes, comments, statuses, categories, tags, groups, and more.
Analyze GitHub issues against current codebase and perform automated triage with priority assessment
Run CPU and memory profiling with pprof to identify performance hotspots. Use when investigating high resource usage.
Главный координатор программы самосовершенствования. Управляет всеми специалистами, адаптирует расписание, отслеживает комплексный прогресс.
Longitudinal language learning progress report with metrics, trends, and insights
Creates and maintains project documentation for features, systems, and components. Discovers project structure dynamically to work across any technology stack.
Chat-first project memory reconstruction with timeline-first synthesis. Reads AI/chat/session history before git, generates timeline candidates with lanes, and persists resumable…
Create new GitHub issues following PROJECT_MANAGE.md conventions. Analyzes codebase to estimate size, suggests splitting if needed, sets project fields, and connects blocking…
Use when naming a project, repository, tool, or product and wanting a memorable, unique name
Use when a project needs multi-session retrospective analysis — after milestones, before starting a new phase, when vision drift is suspected, or every 3-5 sessions.
Review a project and its git/GitHub history to capture learnings, summarize findings, propose improvements, and hand off a first draft PR.
Inception wizard (50 questions, 9 categories) creating CLAUDE.md, speckit constitution, design system, and project brief.
Run a prompt against a golden dataset and report per-rubric regression vs the prior pinned version, not just an aggregate score
Pipeline de raffinement progressif pour prompts image. Transforme une idée brute en prompt optimisé, contraint par un style guide et adapté au générateur cible.
Transforme un prompt en prompt exécutable compatible avec le Task Management System (TaskCreate/TaskUpdate/TaskList)
Use when user asks to "create a skill", "make a command", "generate a prompt", "write a slash command", "build a Claude extension", or needs help crafting optimized skills and…
Use when turning rough instructions into optimized, evidence-based AI prompts for system prompts, task prompts, coding-agent instructions, tools, eval graders, subagent briefings,…
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full…
Generate self-consistent repair plans for mathematical proof issues found by /proofcheck, with literature-backed support.
When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale.
Universal property due-diligence skill across 103 countries. Pulls any or all of thirty-one sections per address — ten core…
Analizar la conversación para proponer business terms, definiciones y preferencias descubiertas a la capa de Stratio Governance del dominio.
Add a Heimdall lock block — protect files or directories behind an unlock phrase. Use when the user says "protect X", "lock X", "guard this file/folder", "don't let me edit X…
Provide convincing evidence that the code actually achieves its intended outcomes and does what it is expected to do runtime across all logical branches and edge cases.
Configure Claude Code alternative API providers — DeepSeek (priority), Z.ai/GLM, Qwen, MiniMax, OpenRouter. Creates shell aliases, manages API tokens, checks status.
Download Prow job artifacts, identify root cause of failure, and produce a structured error report
Automate the full lifecycle of resolving a GitHub issue and opening a pull request. Use when: the user wants to fix a GitHub issue end-to-end, create a branch from an issue,…
Audit project memory (.agents/MEMORY.md and ~/.claude/.../memory/MEMORY.md) against current code and remove stale claims to prevent bad signals in future sessions
Use when setting up automated weekly PageSpeed Insights tracking for a set of URLs — to catch performance regressions before users notice, or to validate that performance…
Printing Press CLI for Public Param Golden. Public parameter name golden fixture
Publish augur's atlas output to the docs website. Copies atlas, stories, and journeys to the docs repo and wires the project into the home page navigation.
Pull account data from Telegram (pushed from another Mac). Triggered by "pull accounts", "pull", "sync accounts".
Peleg review task management. Use when user mentions Peleg, review tasks, fibril formation, FF data, chunk work, threshold controls, terminology scan, or any task from the…
Comprehensive quality assurance - tests, linting, formatting, code analysis, and release build verification.
Adversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).
Q&A diritto del lavoro italiano: orario, ferie, trasferte, distacco, smart working, CCNL. Risposta breve con rimandi e verifica. Nessuna consulenza legale.
QA-*.md 체크리스트를 MCP Playwright 로 빠르게 실행하고 경량 리포트를 생성합니다. 단일 QA 파일 + 실행 증거만으로 7카테고리 인사이트 도출. Deep 모드의 AI 시각 판정·예측 QA·메타 분석은 미포함 — 그게 필요하면 /qa-run-deep 사용.
Interactive QA session where user reports bugs conversationally and agent files GitHub issues with domain language. Explores codebase in background for context.
Skill do @qa — Detector de Mentira 3 níveis, validação Two-Base, CNPJ, fórmulas, faturamento, classificação 3-tier.
QE audit: check recent commits for test coverage gaps, or bash/stress-test features to find bugs. Supports scheduling with every/now/next/stop.