Generate official Lembar Penilaian Penyelia (supervisor assessment form) DOCX per pedoman v6 — blank for hand-scoring or prefilled with scores
Audit de performance du code et de l'application. Analyse Lighthouse, bundle size, Core Web Vitals, et optimisations.
Review a Phase 2 mock build for conformance against the skeleton template and functional spec. Determines widget kind, runs shared and kind-specific checks, produces a PASS/FAIL…
Scannt Dateien und Logs auf personenbezogene Daten (PII) gemaess DSGVO — nutzt PiiSanitizer-Patterns
Detect the current pipeline stage for a work item and run the next stage. Handles approval gates by invoking /pipeline-approve.
Generate PKS (Cooperation Agreement / Perjanjian Kerja Sama) DOCX between UPI Cibiru RPL and a partner company
Critique a Claude implementation plan before approving execution. Spawns parallel persona subagents (Skeptic, Architect, Verifier) to evaluate the plan against the codebase and…
Brainstorming-enhanced PDCA planning with intent discovery and YAGNI review. Triggers: plan-plus, brainstorm, plan plus, intent, 브레인스토밍, 플랜플러스.
(What) Decompose work into ≤9 unit-works with CONTRACTs and clarity %. (When) New work request, or sub-decomposition of low-clarity units. (Why) CONTRACTs before execution.
Analyzes ticket complexity and maps dependencies against an existing codebase before sprint planning.
Adversarial cooperation loop — player implements, /verify reviews, creates PR, passes CI
Summarize what each contributor did in the past 24 hours — commits, PRs, issues, and reviews grouped by person. Multi-contributor version of /standup.
Stateful PR poller: tracks GitHub Actions CI, CodeRabbit, Codecov, and human reviews across polls. Loops with adaptive backoff internally.
Use when a product is ready to stand up a new pod (typically its first, when a PB item is ready to pull).
Use when a product's TL needs to record an architectural decision (ADR). Auto-numbers sequentially within the product, fills the canonical ADR template (context, drivers, options,…
Post Rune review findings to a GitHub PR as a formatted comment. Parses TOME.md findings, formats as collapsible markdown, posts via gh api.
Executive PR review from a CTO/CPO/Chief Data Scientist lens. Analyzes multiple PRs in parallel for strategic fit, risk, issue alignment, and operational readiness.
PR のタイトルと description をコミット履歴に基づいて最新の状態に更新する。テンプレートまたは既存フォーマットに準拠する。Use when PR の説明が古くなった、PR description を更新したい際に使用する。
Export presentation slides to PDF, individual PNGs, or speaker notes markdown. Use when the user wants to share, print, or distribute their presentation in a portable format.
(What) Execute ONE unit-work — fulfill CONTRACT, record Result, verify inline, retry on FAILURE. (When) After /plan-work, or resuming from /check-session. One unit per invocation.
명세서(sharpen 결과물)나 아이디어를 받아 제품 형태(Claude Code 스킬/스크립트/ 크롬익스텐션/로컬HTML/CLI/서비스 등)를 결정하고, 페이즈별 로드맵을 설계한다. 경량화 원칙과 보안 최소화를 적용하여 가장 작은 리소스로 문제를 해결하는 제품 형태를 찾는다.
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
Lightweight natural-language git commit helper. Interprets the argument as either a glob, a filter phrase ("except tests", "only new files"), a topic phrase ("the auth changes"),…
Execute a PRP plan file with per-task validation loops. Detects package manager, prepares git branch, runs 5 validation levels (static/unit/build/integration/edge), writes a…
Application performance optimization. Trigger when the user wants to improve speed, reduce latency, or optimize resources.
QA Phase execution — L1-L5 test planning, generation, execution, and reporting. Triggers: qa phase, QA test, qa run, QA 실행, QAフェーズ, QA阶段, fase QA, phase QA, QA-Phase, fase QA.
mypy 타입 검사 설정 및 관리 스킬. pyproject.toml에 mypy 설정을 구성하고 최적화한다. 정적 타입 검사 환경을 구축하여 타입 안전성을 확보한다.
Jupyter Notebook 품질 관리 스킬. nbstripout, nbdime, nbqa를 활용하여 노트북 품질을 관리한다. Data Science 프로젝트의 노트북 협업 환경을 구축한다.
Ruff 린터/포맷터 설정 및 관리 스킬. pyproject.toml에 Ruff 설정을 구성하고 최적화한다. Flake8, isort, Black을 대체하는 고속 린터/포맷터 환경을 구축한다.
Ralph Wiggum: Project Manager — Continuous ticket consumption, code review, and work generation loop.
Cache and reuse code from prior AI agent executions via Raysurfer. Search before coding, upload after success.
Drive the current PR or branch diff to a clean Review Council verdict by looping review → triage → fix → push until no new actionable findings remain
Load saved knowledge from ~/.claude/learnings/ into the current session context.
대화에서 학습한 내용을 분석하여 CLAUDE.md 업데이트를 추천하는 스킬. 10번 대화마다 자동으로 실행이 권장되며, 중요한 패턴, 결정, 워크플로우를 식별한다.
Audit a RecurseKit run for correctness. Reviews events, skipped files, and result quality.
Analyze agent/skill reference depth and generate missing domain-specific reference files.
Crear releases con tags, changelog y publicación. Soporta semantic versioning y GitHub Releases.
Renames an album or track, updating slugs, titles, and all mirrored paths. Use when the user wants to rename an album or track.
agentsウィンドウ(shogun:agents)のレイアウト・ペイン配置・変数を 初期状態に一発復元するスキル。ペイン消失・入替・CLI死亡時に使用。 TRIGGER: /reset-layout、ペイン復元、レイアウトリセット、ペイン消失、CLI死亡復旧 DO NOT TRIGGER:…
Batch resolve all unresolved PR review comments. Fetches review threads AND issue comments (bot feedback) with pagination.
Resolve a specific GitHub PR review comment. Supports review thread comments (line-level) and issue comments (PR-level from bots).
Resolve file-based TODOs using Agent Teams with verify-before-fix pipeline. Each TODO is reviewed before any fix is applied, preventing hallucinated fixes.
Finds an album by name and shows detailed status with next steps. Use when the user mentions an album name or wants to continue previous work. — from H-mmer/pentest-agents
Schedule a future resume of work — wraps Claude Code's /schedule for GSD continuity
Use when asked to review epic health, audit stalled children, check scope drift, find missing coverage, or assess closure readiness.
Nezávislé review naplánovaného milestonu s čistým kontextem — projde všechna jeho issues a posoudí tvar těl proti šabloně, ukotvení akceptačních kritérií v citovaných sekcích…
Manage Hazard and Risk records for projects on the regulated-industry track. Maintains a single normalized risk file (docs/.index/risk-file.yaml) holding hazard identification,…
Создание роли 1С из описания прав. Используй когда нужно создать новую роль с набором прав на объекты — from Nikolay-Shirokov/cc-1c-skills
Типизированно изменить права существующей роли 1С по логическому адресу, сохранив RLS, шаблоны и остальные права.
Этот скилл MUST быть вызван когда нужно создать новую роль 1С с набором прав на объекты. SHOULD также вызывать при настройке разграничения доступа для новой функциональности.
Компактная сводка прав роли 1С из Rights.xml — объекты, права, RLS, шаблоны ограничений. Используй для аудита прав — какие объекты и действия доступны, ограничения RLS — from…
Валидация роли 1С. Используй после создания или модификации роли для проверки корректности — from Nikolay-Shirokov/cc-1c-skills
Manage PDCA checkpoints and rollback — create, list, restore for safe recovery. Triggers: rollback, checkpoint, restore, undo, 롤백, 체크포인트, 복원.
Requirements-Synthesis Integration Loop (RSIL). Performs code-level gap analysis and creates remediation plans. Called after /synthesis ITERATE decision.
Use when loading, listing, composing, or validating graded evaluation rubrics — PASS/WARN/FAIL grading with weighted criteria and balanced PASS/FAIL anchor examples.
Execute an epic plan phase-by-phase, inline by default with opt-in worker spawns per task annotation
Capture the current session state — what was built, what worked, what failed, open questions, and exact next step — to a dated file at…
Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPOTENT brief (each run wakes memory-less and must dedup prior…
Use when asked to decompose a theme or goal into an EPIC with 3–8 child issues. Creates the EPIC file, pre-wired child stubs, and stages everything for git.
Analyze a URL for relevance to your projects. Fetches, summarizes, scores, and optionally logs to vault.