Distill a book, paper, or thesis into a folder of terse per-concept cheatsheets with a README index. Use whenever the user asks to "read this PDF and turn it into a doc set",…
Large-repo optimization skill for shard planning, bounded subagents, worktrees, and repo-audit-first execution.
Multi-session parallel orchestrator using Claude Code Agent Teams API and Codex CLI Subagents to launch, manage, and coordinate concurrent task execution across multiple…
Autonomous execution loop that processes a Beads epic task-by-task with fresh subagents, two-stage review, and circuit breaker safety. Use after plan-to-epic creates the epic.
Ralph autonomous coding loop with MiniMax subagent delegation. Managed loop (not recursive) with progress tracking, completion detection, and circuit breakers.
Korean apartment/officetel/villa/single-house real transaction price and rent lookups via k-skill-proxy. Based on tae0y's real-estate-mcp and MOLIT public data APIs.
Follow-up correction and skill-improvement workflow for Reatom guidance. Use when the user says earlier Reatom advice was wrong, asks why the work deviated from the expected…
Autonomously executes a decomposed rebar epic under strict held-out TDD, landing each code change as a stacked review.
>Ce skill donne accès à l'API de judilibre. Vous formulez votre demande en français, il interroge la base Judlibre et renvoie les réponses.
Review skills generated from recorded workflows before they are installed, shared, or treated as reusable automation.
Analyze and refine existing Claude Code Skills for conciseness and effectiveness. Use when asked to "review", "refine", "improve", "optimize" Skills, or when user mentions "skill…
Use when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between work phases — reviews skill-bus telemetry to identify…
Re-fetches metadata for catalog sources (`skill-sources.json`) and updates fields like `last_updated`, star counts, latest commit sha, and license.
Captures a promptfoo skill-eval baseline JSON for one sumo-qa skill and snapshots it to docs/qa/runs/eval-baselines/, with an automatic delta against the prior snapshot.
Modeling relationships between variables using regression. Covers simple linear regression, multiple regression, polynomial regression, logistic regression, model fitting — from…
Verwandte Community-Skills basierend auf aktueller Tätigkeit in anderen Plugins empfehlen. Prüft, ob die Community etwas Relevantes für eine Aufgabe gebaut hat, und erwäh — from…
专门用于深度分析和解读本地或 GitHub 源代码仓库的 Agent Skill。在 Claude Code 中全自动运行，包含质量 Review、迭代优化闭环、并行处理和 subAgent 支持。当用户说"帮我分析这个 GitHub 仓库"或"分析当前目录的代码"时，使用此技能。
Use immediately after receiving output from any subagent, tool chain, or dispatched task. Parses the raw return, enforces the schema declared in the brief, strips pleasantries and…
通过协作对话挖出用户真实业务痛点、在动手实现前先把需求搞对的心智——本仓 dev 流的需求发现闸（取代 superpowers:brainstorming，让 cc-master 的 dev meta-skill 自洽不外依赖）。Use when: 开始本仓任何 feature / skill /…
Stage B of /devflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by audit_bundle_cap), re-derive the…
Runs a session's fan-out — turns one large request into tiered, budgeted, recoverable units and dispatches them.
Iteratively refine code via N rounds of parallel subagent review and orchestrator-applied fixes. Use when the user says "let's do three rounds", "fix/review loop", "back-and-forth…
Revisar un archivo SKILL.md para verificar su conformidad con el estándar agentskills.io. Comprueba los campos del frontmatter YAML, las secciones obligatorias, los límites de…
Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.
Spawn an isolated judge subagent to evaluate reviewer predictions against real human reviews
Review filed implementation plans for architectural issues, duplication risks, and completeness. Spawned by planner as a subagent.
Creates new OpenClaw skills following best practices. Interactive workflow for use case definition, frontmatter generation, instruction writing, and validation.
Iterative RFC drafting workflow — draft in worktree, run parallel critic subagents, incorporate feedback over N rounds, present to user before any action
Edit HWP documents — insert/delete text, replace-all, create tables, set cell text — with the k-skill-rhwp CLI that wraps the @rhwp/core WASM engine (rhwp by Edward Kim).
Risk management specialist who assesses, analyzes, and mitigates financial and operational risks with expertise in quantitative risk modeling, compliance frameworks, and — from…
Comprehensive guide to robotics skill 33. Master the concepts, implementation, best practices, and real-world applications of robotics skill 33 in professional environments.
Comprehensive guide to robotics skill 42. Master the concepts, implementation, best practices, and real-world applications of robotics skill 42 in professional environments.
Comprehensive guide to robotics skill 44. Master the concepts, implementation, best practices, and real-world applications of robotics skill 44 in professional environments.
Master robotics specialized skill 148 with comprehensive coverage of concepts, implementation, optimization, and production best practices.
Perform code review using specialized subagents, producing a markdown report
Design role-specific or workflow-specific agent skill packs without collapsing everything into one prompt.
Minimal fixture skill for regression coverage of root-level SKILL.md discovery. Use when validating that find_skill_files picks up Anthropic-spec layout.
Use when a task is about to be dispatched — to codex exec, a subagent, or a workflow stage — and the model/effort choice is not already forced, instead of defaulting to the top…
A router rule can be live, healthy and match nothing anyone types: the pattern list omits the ordinary word, or a JSON escape left the pattern inert.
Audit ~/.claude/rules (always-loaded behavioral rules) for residency cost, staleness, redundancy, broken See-skill pointers, and substrate absorption, assigning…
Autonomous issue management - fetches open GitHub issues, analyzes priorities, detects dependencies, spawns parallel subagents, and verifies results.
Use Qwen Code as a repeatable terminal coding agent: install the CLI, authenticate a provider, run interactive or delegated coding sessions, and connect skills, MCP servers,…
Produces a compatibility catalog — skill-scan-report.md and skill-scan-catalog.json — classifying every SKILL.md in one or more GitHub repos or local paths as ready, normalizable,…
Read markdown files at configurable zoom levels. Use every time when you or subagents needs to read or gather information from markdown files instead of "Read"-tool.
MUSE Phase 6 scene-reviewer subagent 的职责层 — 场景级四档分流决策（PASS / PATCH / ROLLBACK / REWRITE）。吃 pipeline/scenes/scene_{id}.md + scene_card.md + A findings（必读）+ L1 lint report；B/C…
Execute development tasks from task files. Implements code in focused subagent sessions. Use when the user has task files to execute, wants to run through a task list, or asks to…
Produces a new SKILL.md file by converting a proven Dojo Seed into a fully-structured skill with philosophy, workflow, templates, and quality checklist.
Coordinate bulk playbook writing using parallel sub-agents — covers org discovery, prompt templates, model selection, batch dispatch, verification, and the parent-saves pattern…
Debug a specific session by inspecting its full event chain (PreToolUse, PostToolUse, Stop, SubagentStop, Compaction, APIError, TurnDuration, Notification events), agent hierarchy…
過去の Claude Code セッション群（~/.claude/projects/
/*.jsonl）を遡及的に一括発掘し、ユーザーが繰り返し下した判断・価値観を抽出して skill / rule に正本化するワークフロー。人間発話の抽出 jq パターン、既存資産（skills / rules / ADR /…
Dev/arge session tipi kilidi, paralel subagent kuralları, DONE: commit zorunluluğu
For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.
Analyze agentic coding sessions to discover friction patterns and generate skills, rules, and hooks. Use when running /insight across multiple sessions or optimizing AI assistant…
Diagnose and resolve shared skill evidence routing failures. Use when An Agent has a locally verified reusable engineering diagnosis or repair and the user explicitly authorizes…
Use only as the composed drive-to-merge stage of an APM batch orchestrator (batch-bug-shepherd, apm-issue-autopilot) that has already selected ONE open pull request in…
Ingeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el Estándar de Diamante. — from TuYv/ccpm
Cross-repo drift audit across AJ's sister repos (currently phalanx-fl, vFL, kourai-khryseai; configured in `~/.claude/techne.toml`).
Use when building popular support through benevolent governance or demonstrating virtue as a ruler. Applies Tang's three-sided net principle, self-reflection via public welfare,…
Use when comparing competing states or explaining why weaker parties prevail. Analyzes material resources, leadership quality, and intangible factors like popular support,…
Manages NFTs including minting, trading, ERC-721/1155 operations, marketplace integration, and token-bound accounts (ERC-6551).