Use when forensically auditing a Claude Code skill/agent/command/workflow library against RULESET.md by a fixed mechanical protocol — probing every file against the…
跨境电商专业 skill 创建向导。把运营、选品、广告、物流、合规等专家脑子里的业务经验，通过 30-45 分钟的结构化访谈沉淀为 agent 可执行的高质量 skill。触发：帮我写一个 XX skill / 把我这个经验做成 skill / 封装一下我做 XX 的方法 / 把这套 SOP 变成技能 / 沉淀 XX 流程 / 生成专业 skill /…
Validate the skill-lab vault catalog (vaults/llm-wiki-skill-lab/wiki/skills/) against the live production skill directories at ~/Dev/ronan-skills/skills/ and…
List all active skill-bus subscriptions across global and project scopes, showing merge status, insert-level and subscription-level conditions, effective condition stacking, and…
Skill map viewer. Scans all installed skills and renders a visual overview — name, version, description, category at a glance.
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an…
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
管理相互隔离的私有 Skill 母库与公开 Skill 分享库。用于在选定仓库内新建、升级、查重、审计、打包、发布或恢复 Skill，并维护该仓库自己的版本、来源、许可证、GitHub Release、飞书说明、WorkBuddy 与 SkillHub 状态。两库各自是真源，公开版只能独立创作和审核；不建立复制、镜像、同步、自动导出或一键公开链路。
Reduces token usage from paid providers by offloading work to local LM Studio models. Use when: (1) Cutting costs—use local models for summarization, extraction, classification,…
Extracts procedural content from project docs into slash commands. Use when docs contain deploy, test, or troubleshoot procedures.
Creates slash commands from procedural doc sections. Use when transforming documentation prose into executable commands.
Reviews skills (D1-D11 + M1-M6 criteria) or .claude/commands for quality. Use when validating skill correctness before release.
Audit a skill against Anthropic skill-creator standards
Create, update, assign, and remove DB-canonical fork-local skills through the supported CLI. Use for fork AI-team capabilities that must survive snapshot/rebuild without engine…
Answer Logic Pro questions using the converted manuals in docs/manuals/. Delegates a search to an Explore subagent so the full guides (~5MB of markdown) stay out of main context.
Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion - keeps todo, checkpoint, resume, drift, and evidence…
Maintain Loom-compatible skills. Use when adding, tightening, reviewing, or auditing skill boundaries, activation descriptions, common triggers, templates, references, routing, or…
specialized protocol for Loop Engineering — auditing a workspace for repeatable tasks, ranking them with the 4-Condition Test, and building self-verifying Loop Orchestration…
Use when the user invokes `/loopd ` to start a loopd session. The argument is either `pm` (run the PM merge-orchestration round) or a worker name (run that worker's round in…
Base extraction rules for all lore subagents. Governs entity identification, contextual analysis, relationship mapping, and JSON output formatting.
用于撰写、补写、压缩、仿写、规范化交付中文毕业论文、毕业设计论文、技术报告和课程设计论文。用户提到论文、样文、学校模板、参考文献、摘要、图表、截图、Word 成稿、查重口吻优化，或需要基于真实项目代码生成论文正文时必须使用。本技能内置样文结构学习、样式提取、章节控字、参考文献筛选、Mermaid/PlantUML 图表处理、Chrome MCP…
Analyzes SKILL.md files against Agent Skills best practices. Reviews body size, description quality, progressive disclosure, frontmatter usage, and context efficiency.
Scaffold and build projects for the lythoskill ecosystem only. Creates thin-skill monorepos: heavy logic in npm packages (Starter), agent-facing instructions in lightweight…
User-acceptance-driven release workflow using heredoc patch files. Each iteration produces a timestamped pr--.sh that self-archives after execution.
Task management for session continuity. Use when coordinating multi-step work, managing subagent assignments, or preserving intent across compaction.
Forked-context maintainability reviewer — preloads verdict schema + premature-abstraction/dead-code/duplication/YAGNI lens.
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when…
cc-devflow 维护者专用。用于修改、发布或同步 cc-devflow 技能包，处理 .claude 源技能、.codex 镜像、公开 allowlist、npm publish、verify:publish、下游 refresh/explainer-comic 托管技能同步，以及只提交托管输出的 commit hygiene。
Erstgespraech-Triage fuer Wandeldarlehen: Rechtsform (GmbH oder UG), Beteiligte, vorhandener Gesellschafterbeschluss zur Kapitalerhoehung, Sprachen-Stack (bilingual DE/EN oder nur…
Drive a mandoc rendering-bug fix end-to-end — scope the bug class, dispatch a subagent in the mandoc source tree, validate via /eval-render audit + compare, and decide whether to…
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争.
The master conductor for all 630+ installed skills. Activates automatically on every task to determine which skills to apply, in what order, and how to combine them.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. TRIGGER when user explicitly says "create a skill", "write a new skill", "bu — from…
Generate N concept variations of a site / asset on localhost in parallel, foreground subagents. Default 2. Operator picks one to publish.
Run dial-gated Seven Sweeps + auxiliary gates against a brief or copy draft. Returns synthesized findings to the operator.
Search Clayrune for skills that might help the current task — including skills authored in OTHER projects that your session doesn't normally see.
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
تحويل خبرة التاجر إلى Skill آمنة وقابلة للتثبيت والنشر مع تحقق آلي ومراجعة وإصدار واضح. استخدمها عندما يريد تاجر أو خبير إضافة مهارة جديدة إلى Marketplace مهارات زد أو تحديث إصدار…
Check that required output artifacts exist and satisfy acceptance criteria Bound to ADRs: adr.skill-register-and-adr-binding-policy.draft.md,…
Send a user request to the correct agent sandbox based on dominant transformation Bound to ADRs: adr.skill-register-and-adr-binding-policy.draft.md,…
Orchestration loop - plan, delegate to parallel workers, verify, synthesize - with a premium advisor consulted off the hot path.
Create or review a SKILL.md file. Use when writing a new skill, auditing an existing one, or unsure how to structure skill content.
审计外部 SKILL.md / agent 仓库 / 自动化脚本的接入风险。用于判断某个 skill 是否应原样引入、拆解学习或禁止接入 longClaw。冲突优先级最高：当请求同时包含“接入审计”与“实现/排障”意图时，先触发本技能。
스킬 품질 자동 검증 도구. 생성된 스킬의 테스트 케이스를 실행하고 baseline 대비 개선을 측정합니다. A/B 테스트, 회귀 테스트, 체인 테스트 + 4차원 스코어링 루브릭을 단일 스킬에 내장하여 self-contained로 동작합니다.
Use when a user asks to use, run, delegate, or fulfill a task through a capability that may exist as an online Bot/MetaBot skill-service, especially when no local specialized…
Orchestrate a reference-implementation rewrite across source and target repos using campaigns, parity registry conventions, objectives, and subagent handoffs.
Dispatch the metis-task-reviewer subagent to judge a diff against the task description and plan. Returns a verdict with per-criterion evidence.
ML-based variable imputation for survey data - used in policyengine-us-data to fill missing values
スキルディレクトリを `.claude/skills/{name}` から `.agents/skills/{name}` へ移動し、 `.claude/skills/{name}` と `.codex/skills/{name}` の両方からシンボリックリンクを作成するマイグレーションスキル。 スキルの実体を `.agents/skills/`…
Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent.
Build, audit, or package Mission Control skills and plugin skill bundles. Use when the user wants reusable skills, skill metadata, skill tests, marketplace packaging, or…
Execute a phase from the MMPF plan. Implements tasks with atomic commits, TDD when appropriate, and subagent delegation. Writes DONE.md with verification results on completion.
Recommend the cost-optimal Claude model (Fable/Opus/Sonnet/Haiku) and effort level for a given task, and delegate to cheap subagents (sonnet-implementer / haiku-scout) when…
Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations, or optimizing token cost vs quality tradeoffs.
Create and manage AI subagent personas with distinct personalities. Use when a user requests to talk to a specific persona, when delegating a conversation to a character, or when…
Context-based skill auto-routing + federated skill composition. Analyzes user input to auto-select single or multiple skills and execute in order. First gateway for all requests.
WikiPathways enrichment using clusterProfiler and rWikiPathways. Use when analyzing gene lists against community-curated open-source pathways.
Configure pubsub topic setup operations. Auto-activating skill for GCP Skills. Triggers on: pubsub topic setup, pubsub topic setup Part of the GCP Skills skill category.
SEO configuration and best practices for TYPO3 v13/v14, including EXT:seo setup, sitemaps, meta tags, and structured data.
Configure eks cluster config operations. Auto-activating skill for AWS Skills. Triggers on: eks cluster config, eks cluster config Part of the AWS Skills skill category.