Automated documentation generation, auditing, and remediation with structural anti-skip enforcement. Supports 3 workflows: Generation (greenfield/brownfield), Audit (4-di — from…
모든 스킬의 메타데이터를 자동 추출하여 skill-catalog.md를 동기화한다.
Discover rules from accumulated patches and add them to project rules or skill-context. Analyzes past mistakes, extracts prevention points, classifies them as coding rules (→…
**SKILL CREATOR v2.0** - '스킬 만들어', 'skill 만들어', '새 스킬', 'create skill' 요청 시 자동 발동. Anthropic 공식 베스트 프랙티스 기반 프로덕션급 스킬 생성. Progressive Disclosure, 토큰 최적화, 평가 기반 개발 지원.
Onboarding wizard that customizes this Claude Code setup for your specific project. Collects project details through a structured intake questionnaire, then fills all CUSTOMIZE…
Meta-skill para criar, editar, avaliar e otimizar skills do kit. Use quando adicionar nova skill, refatorar skill existente, ou medir qualidade de descoberta de skill (description…
Executes an approved agentmaster-plan plan and chains straight into the full code review. Use when the user has accepted a plan and wants it built — "execute the plan", "run the…
Cost-tiered adversarial code review. Use after implementer subagents complete a agentmaster-plan plan (the plan's review gate invokes this), or whenever the user wants a rigorous…
Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then…
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…
Analyze ~/.claude session files to find unused agent skills and reduce context token waste. Scans subagent JSONL files for injected skills and cross-references with agent…
Wraps each surfaced dimension as a self-contained 9-section autonomous-work-assignment envelope — scope, context, success criteria, allowed tools, return format, handoff — all the…
Audit a user's IWE installation. Runs scripts/iwe-audit.sh + MCP healthcheck + ritual smoke-test via sentinel mechanism (dry-run-contract.md), passes report to a VR.R.002 Auditor…
Run one repository's pull-request queue as the merge lane of the loop-lane three-session topology: a self-paced standing or drain loop that invokes /source-control:babysit-prs…
Apply the Buddhist Five Powers (Bala 5) as a practical subagent balance check before planning, coding, review, or recovery work.
Converts a technical book (PDF or EPUB) into a structured Claude Code skill — extracting frameworks, mental models, principles, techniques, and anti-patterns the author…
Spin up a swarm of expert subagents to build an interactive zero-to-hero course site on any topic — progressive modules, worked examples, exercises with solutions, checkpoints, a…
Scaffolds a primitive-pair — a matched `build-
` and `check-` skill sharing a single distilled principles doc under `_shared/references/`, plus one…
Scaffolds a Claude Code custom subagent definition — a `.md` file under `.claude/agents/` with a routing-oriented description, an explicit `tools` allowlist sized to the workflow,…
Fill in the Cadence team launch template for a new feature, render the launch prompt, and optionally spawn four coordinated subagents (data engineer, feature engineer, tester,…
Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation.
Design a skill-chain from a goal, or check an existing skill-chain manifest for structural and contract issues.
Audits pair-level integrity of a primitive-pair (the artifact `/build:build-skill-pair` produces) by walking the four required artifact slots — principles doc,…
Audits Claude Code custom subagent definitions against deterministic Tier-1 checks (location, frontmatter shape, naming, `tools` hygiene, prompt size, body structure, secret…
Audit Claude Code assets — skills, commands, subagents, hooks, and MCP servers — against best practices and optionally apply conservative conformance changes.
Coding Manager — orchestrator sesji pracy nad repozytorium. Pomaga wybrać co robić z backlogu, rozdziela zadania między równoległe worktree/subagenty, pisze plany pracy w…
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands.
Adapt skills, agents, subagents, workflows, commands, rules, templates, or any generic prompt from one coding agent/IDE/context to another while preserving original intent, hooks,…
Open an interactive Claude Code expert consultation grounded in the current project. Use when the user has questions about Claude Code setup, CLAUDE.md, subagents, MCP, models, or…
Dispatches a long-running task to a maxv-* subagent in background via Claude Code's Agent View (`claude --bg`).
Run the doc-gap-finder reducer subagent over the per-node enrichment sidecars + the concept catalog + the live documentation site.
Mesure la variance d'un évaluateur stochastique (skill-review par défaut) en lançant N runs parallèles via l'outil Agent, agrège les scores de façon déterministe et rend un…
Run the full explore workflow in an isolated forked subagent so verbose file reads and search output stay out of the main conversation; only a short summary returns, with findings…
Trivial inline design task. No subagents, no planning documents, no pipeline stages. Just do the thing described.
Voer een stappenplan van /fwd:steps-plan uit — attended, precies één stap per beurt. Per stap; falende test eerst (rood), minimale implementatie langs de Lazy Ladder (groen),…
Full story validation with factual verification via Val subagent. Dispatches the validator via the main-turn Agent tool and records the outcome via review-gate.sh using canonical…
Iterates a fresh ralph-worker subagent per attempt in a persistent worktree until
tag and verify command both confirm success.
Orchestrate worker subagents to execute an approved plan — the main window composes scope-fenced briefs, dispatches workers, verifies their returns against direct evidence, and…
Cluster related instincts by trigger family and lexical similarity, identify skill-creation candidates
Implement approved tasks using TDD with an independent reviewer gate per task. Executes directly in the main context (default) or via native subagent dispatch for parallelizable…
Evaluate a /map-* skill's trigger accuracy and cost. Use when asked to measure skill trigger accuracy, run an eval-set, or check token/duration cost via `mapify skill-eval`.
Coordinates a repo-wide mechanical migration (rename X → Y across N files, bump dependency version across a monorepo, port a deprecated API call site by site) by dispatching the…
Convert legacy subagents, slash commands, and rules to the unified Agent Skills format. Use when migrating agent resources, consolidating legacy directories, or standardi — from…
Delegate work to a subagent with mutual review gates. Parent owns the plan and the commit. Subagent owns the implementation. Neither proceeds without the other's agreement.
Integrate patterns from external sources (URLs or files) into local skills, agents, and plugins. Triggers on comparing external agent definitions against local equivalents,…
Spawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed deep delegation
Reduces Claude Code context bloat across three dimensions: (1) duplicate skill deduplication — clears .claude/ copies since Claude Code already reads from plugins/ directly; (2)…
Use when turning rough instructions into optimized, evidence-based AI prompts for system prompts, task prompts, coding-agent instructions, tools, eval graders, subagent briefings,…
Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination.
Execute an instruction-placement audit's findings behind an explicit per-item human gate. Consumes the findings artifact the audit skill produced.
既存スキルへの「こう直してほしい」要望を受け取って Notion 改善要望 DB にプッシュしたいとき、利用者発端のフィードバックループを起動したいときに使う。
Author a new transaction-specific SAP skill from multiple natural-language scenarios. Runs /sap-gui-probe for each scenario, then merges the resulting probe folders into one…
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
세션 종료 전 자동 정리 스킬. 4개 병렬 subagent가 문서 업데이트, 반복 패턴, 학습 포인트, 후속 작업을 동시 탐지하고, 1개 검증 subagent가 중복 제거 후 사용자에게 선택지를 제시한다. 트리거: /session-wrap, 세션 마무리, 세션 정리, 작업 마무리
Use when shaping vague, complex, or ambiguous ship-flow requests into a Shape Up pitch, including `/shape`, discussion, or skill-authoring work.
用于【都市悬疑】题材下的提纲审阅优化 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名，并明确要求加载并使用 `通用-大纲审阅优化闭环`，同时按总纲 / 分卷对象分流到对应题材审阅与设计 Skill。
用于围绕起点中文网或其他目标平台的同题材 TopN 榜单，锁定标杆作品并进行逐本深搜式竞对分析。适合搜索榜单、筛选强样本、阅读目录/公开正文/设定/书评/读者评论/读后感/拆解材料，并在 `竞对分析/` 中为每部作品分别落盘详细竞对分析报告。关键词：竞对分析、竞品分析、标杆作品拆解、TopN 榜单、同题材对标、榜单深搜、读者评论分析、单书竞对报告。
用于对指定提纲执行"审阅→修改→复审"的闭环，直到双轴评分（技法分 ≥ 6.0 / 留存分 ≥ 5.0）加权的综合评分连续两轮独立审阅在保留两位小数后均严格大于 9.20。适合大纲审阅优化 SOP、报告复用、回炉循环、评分门槛控制与最终回执收口。关键词：大纲审阅闭环、回炉到 9.20 以上、双轴评分、复审循环、主报告覆盖、提纲优化 SOP。
创建异能志怪题材章节正文、作者有话说与章节后记。用于按分卷大纲、人物传记、设定与写作研究，直接新写、重写或扩写都市异术超能 / 志怪连载章节；作为题材包装层与路由层，负责保留异能志怪标准入口名，并要求生成的 `## 作者有话说` 保持读者向小剧场与轻微异感。
用于在选定平台（七猫/起点/番茄/晋江等）与题材（科幻/悬疑/职场/爱情等）之后、设计大纲之前，完成项目级的战略初始化。 唯一目标：在指定的平台和题材约束下，确定最能吸引读者和最能赚钱的小说应当具备哪些要素。 核心方法：从已有宏观市场分析（写作研究/）和竞对分析数据出发自主决策——用户无需了解"什么套路最火"，本 Skill 根据研究结论 — from…