В каталоге 182 820 навыков в 14 категориях.
Set up the project file an AI agent keeps for work that runs over days or weeks: the goal, the definition of done, miles...
Review recorded agent-qa runs and memidex provenance to explain a QA verdict, identify missing evidence, and propose the...
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe ad...
Analyzes repeated agent failures or noisy routing and proposes evidence-backed changes to instructions, skills, gates, o...
Create step-by-step executable runbooks for AI agents. Use when building automation scripts, setup guides, or multi-step...
Plans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when...
Expert en scheduling v2 (cron, Celery Beat, Temporal, BullMQ, tâches récurrentes, timezones)
Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memo...
Use when a task involves selecting and composing several agent skills into a minimal, non-conflicting workflow for one t...
Use when an agent needs to save where it is in a long task so it can resume later, or when handing a task to another age...
Design resumable agent checkpoints that preserve task state, evidence, changed files, and idempotent next actions after...
把千问办公的 agent 任务沉淀到钉钉 AI表格，形成跨 agent、跨窗口的「任务台账 + 交接登记表」。 支持创建/初始化个人台账（定时增量同步）与团队接续台账（仅 handoff 触发写摘要，保护隐私）。 当用户需要创建团队 Age...
It is a specification for semantic workflows used by agents to plan, generate, formalize, summarize, and execute complex...
Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework
Use when a task involves designing typed, bounded tool interfaces that an agent can call safely and interpret reliably t...
Parse .trace.json files and correlate with backend events and tool calls. Use when debugging agent behavior, investigati...
Specialist subagent: Expert video production specialist for planning, shooting, editing, and delivering video content
Agent skill for workflow - invoke with $agent-workflow
Implement and review repository changes within local policy.
Keep template-backed files aligned across canonical template, dist template, and local convex copies.
Ship production code with AI agents through acceptance contracts, micro diffs, red green loops, and deterministic handof...
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality di...
Drive autonomous IDE workflows including refactors, TODO cleanup, and context-aware command palette actions; use when as...
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context...
Evaluate and improve repeated agentic software-development workflows using development traces, diffs, review feedback, i...
Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/...
Agentic Workflow Pattern
Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow def...
Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .ag...
Use when the user types /agentlas-browser <url-or-query>, /agentlas browser, or /hep-browser for browser-required tasks,...
Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an...
Review an agents-context-router diff, branch, commit or PR for correctness, repository rules, requested behavior, affect...
When the user explicitly asks to create or repair repository agent instructions — build a minimal AGENTS.md.
You are **AgentsOrchestrator**, the autonomous pipeline manager who runs complete development workflows from specificati...
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-...
Run, verify, and troubleshoot the Antigravity Agent Skills Vault & Skill.Sea automation pipeline (update.py, skillssh.py...
Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each ite...
Use when a task involves sharing or handing off selected workspace files through an authorized cloud workspace-sharing s...
Think like a human. Reason, plan, adapt, create, and know your limits.
Multi-cycle iteration management, document versioning, change requests, re-entry points, archival, and impact analysis....
Coordinate multiple agent sessions across machines, repos, tools, and runtimes using safe handoff packets, peer identity...
Comprehensive guide and reference for the Antigravity Customization System. Use to explain how customizations work, thei...
Use when driving AgentOps work natively in Google Antigravity with claims, validation, closeout, and persistence. Trigge...
Run a recurring AGY sidecar loop tick and capture agentapi evidence. Triggers: agy, sidecar, schedule, agentapi.
你是一个 严格可控的 SoT 文档流水线执行器（Pipeline Runner）：
<name>ai-ad-spec-kit</name>
AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI,...
Design, implement, and evaluate tool-using AI agents with explicit authority, typed tools, bounded loops, state, observa...
Use this skill when you need to test AI agent goals, state, planning, recovery, and safety boundaries; triggers include...
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected w...
Identify a feasible first business automation from real tasks, examples, volumes, and correction costs. Use for AI autom...
Write the build spec for an AI feature — components, prompt files, retrieval pipeline or tool definitions, configuration...
Use when the user wants an AI Systems Engineering Signal Radar: researching AI systems engineering trends, AI infrastruc...
- constraints: 限制條件（可選）
Designs session and task state for coding-agent runtimes: resume, checkpoints, compaction, cancellation, background and...
Design co-learning experiences using the Three Roles Framework (AI as Teacher/Student/Co-Worker). Use when teaching AI-d...
Support adversary-emulation and red-team analysis to stress-test plans and assumptions. Use when evaluating vulnerabilit...
Build AI help desk automation systems. TRIGGERS - Use when user needs help with ai-help-desk related tasks.
Use when a task involves planning or generating an image asset from a brief while controlling rights, likeness, and outp...
Teach AI literacy and civic literacy to anyone — especially populations traditionally excluded from technology education...
Implements intelligent ai ml with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant...
Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error han...
Jeff Su's AI-Native Workflow framework (4 Habits) mapped onto Nebuchadnezzar v3.4 pipeline infrastructure. Use when: (1)...
Design, specify, map, evaluate, or improve an AI assistant, LLM feature, copilot, chatbot, agent, recommendation, genera...
Official OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structur...
AI SDR Skill workflow skill. Use this skill when the user needs When the user wants to deploy AI sales development reps,...
Use when preparing daily standup notes or summarizing recent PR and commit activity for team updates.
Core principle: Understand and effectively coordinate with specialized AI agent teams, leveraging their unique capabilit...
Sets up a complete intake-to-approval pipeline for AI tool access requests. Creates a Jira issue type with structured fi...
Figure out which AI tool actually fits the task in front of you — chatbot, coding assistant, image model, agent, or none...
Evaluate AI vendors, tools, platforms, and agent systems for executive decision support. Use when Codex is asked to comp...
Use when a task involves planning or generating a short video asset with an explicit storyboard, format, and rights-safe...
Build automated voiceover-first video production pipelines using AI models — script generation via LLM cascade, TTS voic...
AI 工作资产化诊断器 / Assetization Router：当用户提供 AI 协作会话、重复任务、prompt、工作流描述、 团队 AI 使用场景或一次成功交付过程，并要求判断应该沉淀成 Prompt、Context Pack、Wo...
Initializes AIDD workspace scaffolding for the current project. Use when bootstrapping canonical `aidd/` templates.
Enforces loop-mode discipline for implement/review/qa (packs, scope, no questions). Use when loop stages require bounded...
Defines the shared policy contract for output format, read discipline, question format, and loop safety. Use when applyi...
Coordinate multi-step work across services the user has authorized through Aident Loadout, using live action schemas, co...
Use Aident Loadout to connect your AI agents to 1,000+ real-world apps and tools like Gmail, Slack, Linear, Notion, Fire...
Run the AI-DLC `delivery-planning` stage (inception phase) in isolation, without advancing the main workflow. Packages `...
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an...
Add project-specific rules and conventions to .ai-factory/RULES.md. Each invocation appends new rules. These rules are a...
AI HOT 中文 AI 资讯查询 Skill。让 Agent 用一句话拿到 aihot.virxact.com 上每天的 AI HOT 日报和全部 AI 动态(精选/全部/分类/时间窗/关键词搜索),无需 API Key、无需配 MCP...
Run automated post-release workflow (eval baselines, dashboard, docs) for AILANG releases. Executes 46-benchmark suite (...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) An operation or tool fails u...
Activate River (sm) for Scrum Master. Use for user story creation from PRD, story validation and completeness checking,...
Activate the AIOX Scrum Master agent (River). Use for user story creation from PRD, story validation and completeness ch...
Explain how to use the AIPP toolkit (this repo, also called aipp): installing it, linking it into a project, enabling sk...
Support air mission planning and ATO-cycle coordination. Use when building target nomination summaries, sortie prioritiz...
Airtable database automation - views, automations, integrations, and workflow triggers
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for cu...
Search the web and extract public page content through AIsa's Tavily-backed API relay. Use when: the user needs open-web...
Contribute changes back to repositories by opening structured issues (GitHub, GitLab, or Bitbucket). Supports both aitas...
Analyze a contribution issue, find related issues, and import as grouped or single task.
Create a new AI task file with automatic numbering and proper metadata. Supports interactive agent prompts, terminal fzf...
Explore the codebase interactively, then create a task for implementation.
Identify and merge related tasks into a single task, then optionally execute it.
Select the next AI task for implementation from the `aitasks/` directory.
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion call...
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data lo...