Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Multimodal UI understanding and single-step planning via OpenAI-compatible Responses APIs. Use when you need AIQuery/AIAssert and plan-next to extract UI element coordinates, validate UI assertions, summarize screenshots, or decide the next UI action from an image. External agents handle execution via adb/hdc and multi-step loops. Defaults to Doubao models but can be pointed at other multimodal providers via base URL, API key, and model name.
Manage Claude Code agent skills using the `asc` CLI tool. Use this skill when: (1) Listing available skills: "asc skills list", "what skills are available", "show me asc skills" (2) Installing skills: "asc skills install --name asc-cli", "install all skills", "add asc skills to my agent" (3) Viewing installed skills: "asc skills installed", "what skills do I have", "show my installed skills" (4) Removing a skill: "asc skills uninstall --name asc-auth", "remove a skill" (5) Checking for skill updates: "asc skills check", "are my skills up to date" (6) Updating skills: "asc skills update", "update my asc skills" (7) User asks "how do I install asc skills", "set up asc CLI skills", or "get the latest asc skills" (8) Troubleshooting skill installation or update issues (npx, skills CLI)
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts
Use when planning work (to create items and tasks), when starting implementation (to start and work tasks), when completing work (to mark tasks done), or to check backlog status. Manages .backlogmd/ (work/ and z-archive/); no shared manifest or backlog file. Item index.md has metadata, description, and CONTEXT for agents.
Choose, configure, and use Blender MCP integrations for live scene control or deterministic asset evaluation. Use when connecting Codex or Claude Code to an open Blender instance, deciding between Blender Lab MCP and community Blender MCP servers, troubleshooting Blender MCP connectivity, or evaluating whether MCP tools improve a Blender modeling workflow.
Claude Code + Codex parallel pipeline for bootstrapping Trellis coding specs. CC analyzes the repo with GitNexus (knowledge graph) + ABCoder (AST), creates Trellis task PRDs with full architectural context and MCP tool instructions, then Codex agents run those tasks in parallel to fill spec files. Use when: bootstrapping coding guidelines, setting up Trellis specs, 'bootstrap specs for codex', 'create spec tasks', 'CC + Codex spec pipeline', 'initialize coding guidelines with code intelligence'. Also triggers when user wants to set up GitNexus or ABCoder MCP for multi-agent spec generation.
Use to close the loop on agent quality — turn a failure signal into a verified fix. Triggers: "improve my agent", "self-improving agent", "auto-tune / iterate on my prompt", "fix my agent from test results" — and production-call bug fixing: "fix this prod call issue", "debug and fix call ID", "reproduce this production bug", "regression test before raising PR". Works on any stack: provider-dashboard agents (VAPI, Retell, ElevenLabs, Bland) AND agents whose config lives in the customer's own repo, database, or prompt registry with the provider agent created at deploy time, or with custom mock servers. Fixed safety invariants (must-fail-first reproduction, attestation, no-prod-in-loop) + a per-project capability manifest declaring where config lives and how to read/render/apply/deploy/verify it.
Generate structured session summaries optimized for future AI agent consumption. Use when (1) ending a coding/debugging session, (2) user says "compact", "summarize session", "save context", or "wrap up", (3) context window is getting long and continuity matters, (4) before switching tasks or taking a break. Produces machine-readable handoff documents that let the next session start fluently without re-explaining.
Complete project setup guide for Mastra AI framework. Covers: CLI installation (create-mastra), manual installation, TypeScript configuration (ES2022 requirements), environment setup, adding to existing projects (Next.js, Express), troubleshooting (module not found, import errors, CommonJS issues), deployment preparation, and monorepo configuration. Includes both quick setup (user runs CLI) and automatic setup (step-by-step file creation). Use this skill for all Mastra installation and setup questions to ensure correct configuration and prevent common errors.
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host, or to continue, resume, or recall recent Cua activity.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
A method for having an unbiased executor run agent-facing text instructions (skill / slash command / task prompt / CLAUDE.md section / code generation prompt) and evaluating them from both sides (the executor's self-report + instruction-side metrics) to improve iteratively. Repeat until improvements plateau. Use right after creating or heavily revising a prompt or skill, or when you want to attribute an agent's unexpected behavior to ambiguity on the instruction side.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
Interactive SKILL.md builder. Use this skill whenever the user asks to "create a skill", "generate a skill", "scaffold a SKILL.md", "write a SKILL.md", or "turn this workflow into a skill" — even if they don't say "skill" and only describe wanting to make a repeatable agent workflow, checklist, or convention. Do NOT use for grading an existing SKILL.md (see rate-skill) or project roadmaps (see track-roadmap).
Author and run a project-TAILORED pre-launch audit as a bounded multi-agent workflow — a real launch verdict, not a checklist skim: fill the bundled workflow template from the repo's real stack and hard rules, then run Gates (typecheck / test / lint / build in parallel) → Find (one read-only finder per applicable audit dimension) → Dedup (merge shared-root-cause findings) → Verify (adversarial agents try to refute every finding; blockers get a code lens plus a spec lens) → Critic (name uncovered areas, spawn follow-up finders) → a GO / NO-GO / GO-WITH-FIXES report, all fanned out under a MAX_PARALLEL cap. Finders and verifiers stay read-only — the skill audits and reports, never fixes; a gate that didn't actually run is treated as a blocker, never counted clean; secret values are redacted to type and location. Confirms scope and warns about the agent count (typically 40-80) before running.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Create, inspect, retrieve, author, revise, enrich, audit, repair, research, analyze change impact, migrate, validate, and maintain knowledge for AI agents as conformant Open Knowledge Format (OKF) bundles. Use for /okf commands; work on an existing OKF bundle; documentation of tables, datasets, views, metrics, runbooks, playbooks, APIs, schemas, or join paths; exports from catalogs, metadata, websites, URLs, or source code; and any knowledge an agent will read later. Apply implicitly when editing an OKF bundle so conformance, provenance and sources, generated and verified trust signals, freshness, log.md, indexes, and cross-links remain current. Tracks OKF v0.2, including attested computations and migration from v0.1.
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
Parse OpenClaw, Claude Code, or Hermes agent session logs and upload structured telemetry via the Cobo Agentic Wallet TelemetryAPI. Zero external dependencies — only requires Python 3 and a valid caw installation (API key auto-detected). Use when: user wants to analyze a session from any supported agent platform, upload session telemetry, view session traces, or debug agent behavior.
Configure OpenSpec project settings and global CLI configuration using `openspec/config.yaml` and `openspec config` commands. Use when the user says "configure OpenSpec", "project config", "add project context", or wants to set per-artifact rules.
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Fast-forward through artifact creation with `/opsx:ff`, generating all planning artifacts (proposal, specs, design, tasks) at once. Use when the user says "fast forward", "create all artifacts", "/opsx:ff", or has a clear picture of what to build.
Guided onboarding through the complete OpenSpec workflow using `/opsx:onboard`, walking the user through a real change in their codebase. Use when the user says "onboard me", "tutorial", "/opsx:onboard", "how does OpenSpec work", or is new to OpenSpec.
Create and manage custom workflow schemas using `openspec schema init/fork/validate/which`. Use when the user says "create a custom workflow", "custom schema", "fork a schema", or wants to define their own artifact types and dependencies.
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper from my experiments", "turn this idea and these results into a paper", "generate a conference submission", "run paper-orchestra on X", or otherwise wants the end-to-end paper-writing pipeline. Coordinates the outline-agent, plotting-agent, literature-review-agent, section-writing-agent, and content-refinement-agent skills.
Use this skill to grade a SKILL.md whenever the user wants to rate, audit, or score one. Triggers include "rate this skill", "grade this skill", "give my skill a letter grade", "audit my SKILL.md", "score this skill against best practices", or "is this SKILL.md up to spec", even if they don't use the word "rate". Returns a letter grade A-F, weighted category scores, and prioritized paste-ready patches. Do NOT use this skill for code review (see code-review) or for authoring a new skill (see generate-skill).
Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.
Create or update role-specific skill packages with deterministic files. Supports output to skills/ (open-source publishing) or .agent-team/teams/ (team use). Triggers: 创建角色, 新建 role, create role, 更新 role scope, edit role, update role, add role skill, 修改角色配置. Use when the user asks to create, update, or edit frontend/backend/product (or custom) role skills with auto-generated role fields, guided brainstorming fallback, and curated skills selection.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
You **MUST** load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
Agent-native armory catalog for eight package types and installer for seven legacy types. Native extensions require the explicit per-host lifecycle CLI. Triggers on: "list available packages", "install skill", "armory install", "armory search", "/library list", "package catalog".
Use this skill when the user needs to create or update Trae IDE rules (.trae/rules/*.md) to constrain AI behavior. Applies to: enforcing code style, naming conventions, commit message formats, or making the AI always follow a specific pattern. Not for skills (use project-skill-writer) or agents (use project-agent-writer). Trigger words: 'create rules,' 'add rule,' 'set code style,' 'enforce conventions,' 'configure AI behavior,' 'AI rules,' 'always do X', or when the user needs consistent AI behavior across sessions.
Initialize, migrate, or refresh a repo's ai-memory wiring: the .ai-memory.toml routing marker (workspace/project), the recall/write routing snippet in CLAUDE.md/AGENTS.md, the ai-memory MCP server entry, and the global capture hooks. Includes the qmd→ai-memory migration for repos still on the old wiki/qmd stack, and a refresh flow that detects CLI↔server version skew and re-stages hooks to parity. Use when the user asks to set up ai-memory in a project (greenfield or brownfield), wire the MCP, enable auto-capture, migrate off qmd, diagnose with doctor, or upgrade/refresh an existing setup (local CLI + hooks) to the server's version.
Guidelines for authoring fullstackrecipes content - setup recipes, exposed skills (in ./skills/), cookbooks, templates, and installable registry utilities. Use when creating or editing any catalog content. For maintainers building the fullstackrecipes project, not developers consuming the stack.
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use when triaging beads tasks, analyzing dependency graphs, finding bottlenecks, detecting circular dependencies, planning parallel execution tracks, or generating sprint burndown data.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.