В каталоге 182 820 навыков в 14 категориях.
Decide with a person how two or more wiki pages relate — the same concept, one inside the other, related, distinct, or e...
WikiPathways enrichment using clusterProfiler and rWikiPathways. Use when analyzing gene lists against community-curated...
Triage Windows Event Logs across one or many servers. Pulls Critical/Error events (System + Application by default; Secu...
Reference system prompt and tool schemas for Windsurf. Use when imitating, comparing, or analyzing Windsurf's prompting...
Work-in-progress prompt workflow. Log, improve, and propose prompt patterns from the skills library with safe mutation g...
Generate a context handoff summary, clear the session, and resume in a fresh conversation. Detects environment and provi...
PMU observation pattern for agent health monitoring. Runs patrol loops, detects stalled agents, sends nudges, and escala...
Use when 王建硕 wants to decide whether a VoiceDrop article should get an AI 题图 (公众号封面), and which style of image prompt to...
Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring. Runs liv...
This skill should be run only when the user explicitly invokes it. Orchestrates end-to-end task implementation — underst...
Shared rules for unattended execution — only load when explicitly referenced by another command or skill. Never auto-tri...
Transform any intellectual work into AI-promptable systems. Use when user wants to automate business processes, create m...
Expert delegation specialist that creates comprehensive context packages for coding agents, analyzes requirements, ident...
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use t...
Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools...
Worker Self-Service Commands - start, done, status, block. Supports Sub-Orchestrator mode for hierarchical task decompos...
Focused task execution for persistent team workers. Use when implementing features, following scope constraints, using T...
Defines context handover format when workers hit turn limit. Posts structured handover to GitHub issue comments enabling...
Decide and execute native Codex worker delegation for the main coordinating agent. Use it for a substantial investigatio...
Author a deterministic Codex orchestration (codex exec + spawn_agents).
Shared lifecycle contract for manual/auto control-flow plus optional ai-proxy overlay recognition in workflow skills: au...
Multi-CLI collaborative planning with ACE context gathering, iterative cross-verification, and execution handoff
> Design and execute typed, multi-step workflows with approval gates.
Purpose: This skill defines the standard agent pipelines for different task types. The /ms command uses this skill to or...
Master workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, an...
Always-on workflow orchestration for Claude Code projects. Detects context and activates appropriate skills automaticall...
Orchestrate multiple Codex CLI workflows using done-signal files, optional locks, and simple dependencies.
Orchestrate the six-stage development workflow. Use when user asks "what stage am I at?", "what's next?", "workflow stat...
Orchestrates git workflow for Python feature/release/hotfix development. Loads and coordinates other skills based on cur...
Project workflow system - cost tracking, parallel execution, security gates, agent orchestration. Use when: start day, b...
Finalize the workflow by reflecting on the process, moving ADRs, closing issues, and preparing for merge. Stage 8 of the...
Returns the universal governance spec for custom workflow commands. Hard rules, briefing templates, launch mechanics, an...
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求...
Meta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive p...
Capture learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user...
Mandatory workflow for creating LLM-facing content. Follow the 4-step process (objective → draft → verify → adjust) befo...
Use when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory...
Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, opti...
Use this skill when reviewing, designing, or improving a workshop, lesson, training session, facilitation plan, talk, or...
Use when an agent is exploring a relayfile mount for the first time or trying to locate a specific resource (Notion page...
Expert workstream coordinator managing multiple concurrent tasks, tracking progress, detecting conflicts and stalls, ana...
Creates and manages git worktrees for parallel plan isolation. Handles monorepo (single worktree) and polyrepo (per-serv...
Delegate tasks to parallel worktree agents.
Manage multiple Claude Code instances across git worktrees. Check status, claim/release file locks, sync decisions, and...
Spawn an independent Claude instance in a git worktree to work on a task in parallel. Use when the user wants to delegat...
Create a git worktree for isolated parallel feature development. Lighter than fork-project — shares git history but zero...
Set up and orchestrate parallel Claude Code agents using git worktrees. Use this skill when the user wants to paralleliz...
Use this skill when the user asks about Worktrunk (wt), git worktree management, running parallel AI agents with worktre...
Train and deploy generative UI agents using behavioral programming constraints, A2A protocol for agent interoperability,...
Extract value from world transitions via Markov blanket arbitrage. WEV = PoA - 1. Paradigm Multiverse Finance integratio...
World memory is world remembering is world worlding - the autopoietic loop where memory enables remembering enables worl...
Sync work between AI agents. Log actions, manage sessions, detect conflicts.
Создание нового рабочего продукта (РП) с атомарной записью в 4 локальных места (+ условный пост-шаг во внешний трекер, е...
Use when creating a new PHPStan stubs package for a WordPress plugin, theme, or Composer package — scaffolding the full...
Handle UTF-8 and text encoding safely in WordPress plugins, especially on WP 6.9+ where wp_is_valid_utf8(), wp_scrub_utf...
Close the current Egregore session with a personal, canonical summary. Use for /wrap or when the user says they are done...
Full session close-out ritual — commit, export conversation, teaching narrative, handoff, memory harvest; use for "wrap...
Use ONLY when the user's latest message explicitly contains the `/wrap-up` command. Harvests everything a long session p...
Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure fini...
Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progre...
Write the brief a drive shows the person when it must reach them — what we understood, what we built, and where the gaps...
Use when drafting a medical research manuscript or any IMRAD section. Runs an 8-phase pipeline from outline to submissio...
Full-pipeline medical/scientific paper writing. 8-phase IMRAD workflow from outline to submission-ready manuscript. Supp...
Write notes and documentation to Serena memory. Use this skill when you need to persist information like technical debt,...
CRITICAL: Before deploying any subagent, spawn a reviewer agent with REVIEW.md to audit tools. Overly permissive tool ac...
Write skillprobe YAML tests for LLM skills. Use when asked to write tests, create test scenarios, test a skill, generate...
文案撰寫全套工作流：分析受眾語調、套用說服公式（AIDA/PAS/FAB）、產出部落格/Email/Landing Page/社群文案，並提供 SEO 優化建議。適合在撰寫行銷文案、內容行銷、或需要匹配特定品牌語調時使用。
Use when building multi-agent workflows with the relay broker-sdk - covers the WorkflowBuilder API, DAG step dependencie...
Remove AI-generated writing patterns from rebuttal prose to make it sound natural, direct, and authentically human-autho...
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organiza...
Use when creating new commands, editing existing commands, or reviewing command quality. Triggers on "write command", "n...
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering,...
Writing mode operational spec for the team lead. Returns lead identity, facilitator identity, ownership boundaries, edit...
Use when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performance
仅当使用者明确说"使用规则写作"、"按规则写"、"用写作规则"或等价表达时启用。启用后按十五条规则写中文：禁破折号、禁"不是A，是B"、打破三点式、删句首冗余连接词、杜绝强行升华、长短句交替且不用嵌套从句、只在文末收束、保留适当不确定性、必...
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Use when creating, updating, or improving agent skills.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Helps author concise, discoverable skills using TDD-style testing. Use when creating, editing, or verifying skills befor...
Use when creating/editing/verifying skills or `AGENTS.md` agent-instruction docs, especially when routing, trigger wordi...
writing-skills
Use when creating new skills, editing existing ones, or verifying skill quality before deployment.
Use when writing a new SKILL.md, revising an existing skill's instructions, or converting a repeated workflow into a reu...
TDD for process documentation - test with subagents before writing, iterate until bulletproof
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills...
Create and maintain AI agent skills for this project. Use when creating new skills, reviewing existing skills, or decidi...
Use when creating reusable process documentation. Apply TDD: baseline without skill → document failures → write skill →...
当你要创建新 skill、重写已有 skill，或把稳定 workflow 提炼为可复用 skill 时使用。
Evaluates fine-grained spatial-temporal understanding and instance-aware video-to-text captioning in pedestrian-centric...
Use when a user wants images, visual cards, diagrams, covers or a consistent visual style for an X.com/Twitter Post, Art...
AI 热点雷达 - 在新 AI 工具/关键词爆火前发现它们，抢注域名、建站套利。 触发条件： - 用户说「跑雷达」、「热点扫描」、「X 雷达」 - cron 每 12 小时自动触发（9:00, 21:00） 核心目标： 在 AI 关键词...
Create and edit X-ray transmission imagery from a brief or visual reference, preserving projection, material attenuation...
MUST read before searching X/Twitter with the x_search tool. When xAI is connected: date-bound every time-sensitive quer...
Use soft-prompted transformer architecture for multi-robot learning. Add learnable embodiment-specific prompt embeddings...
Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.
xAI Grok API authentication and setup. Use when configuring xAI API access, setting up API keys, or troubleshooting auth...
Explainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, sta...
xAI Grok model selection and capabilities guide. Use when choosing the right Grok model for your task, comparing model f...
Search Twitter/X in real-time using Grok API. Use when searching X posts, tracking trends, monitoring accounts, or analy...
Reference system prompt and tool schemas for Xcode AI. Use when imitating, comparing, or analyzing Xcode AI's prompting...