MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
nonstop
Session-scoped autonomous work mode: runs a strict pre-flight risk assessment, dangerous-ops approval, and a blocker decision framework to let the agent continu
agentscope-java
Reactive Java framework skill for building non-blocking, agent-oriented LLM applications using Project Reactor and AgentScope conventions.
claude-mpm-skills
Canonical demo of the Command → Agent → Skill orchestration pattern: shows preloaded vs dynamic skill invocation, with a code-review example and templates.
code-virtuoso
Interactive guided tool that helps design focused sub-agents (specialist, role, or team-lead) with correct frontmatter, tool permissions, and system prompts.
ash-ai
SDK skill for deploying and managing hosted AI agents with Ash: create clients and sessions, stream SSE responses, handle lifecycle and errors, using TypeScript
anvil
Pick up a paused long-running task, make measurable progress, and save a concise breadcrumb file describing work done and what's left so another agent can conti
dbg
Persistent CLI for debugging, profiling, and JIT disassembly across languages and backends; captures hits for diffing and trend analysis.
evolve
SDK and guides for building and running CLI agents in secure sandboxes (TypeScript & Python).
agentic-kaggle-skill
Assistant skill to run and manage Kaggle competition workflows: submission troubleshooting, score stabilization patterns, kernel workflows, and spec-driven dele
swarma
Framework for running high-velocity growth experiments with agent teams that generate hypotheses, run tests, observe signals, and build a validated playbook.
skills
Run a data-backed audit of AGENTS.md/CLAUDE.md files: surface redundant rules, run A/B evals to prove which instructions are unnecessary, and recommend concise
gsd-skill-creator
Autonomously triage GitHub issues, submit fixes as PRs, and perform adversarial PR reviews to find security and quality problems.
ghfs
Operate GitHub issues and PRs as a local filesystem mirror: sync remote data into `.ghfs/`, author queued operations, validate, preview, and apply batch changes
agents
Opinionated SOLID-guidelines for TypeScript/Bun/Node projects: small files, separated interfaces, mandatory JSDoc, reuse-first workflow and templates to keep co
agent-workflow-protocol
Generate complete Agent Workflow Protocol (AWP) compliant multi-agent workflows from natural language descriptions. Produces workflow.awp.yaml, agent...
repo-atlas
Generate an in-repo persistent context atlas that maps a codebase: directory trees, entrypoints, architecture docs, and onboarding material so agents and engine
skill_everyone
Generate persona skills for characters (fictional or original): collects materials, extracts personality and dialogue style, and produces roleplay and perspecti
openclaw-master-skills
Log learnings, errors, and feature requests to markdown so agents and teams can capture corrections, recurring issues, and actionable improvements.
xagent
Creates and configures custom AI agents: select tools, knowledge bases, and settings so users get an agent tuned for a specific task.
borda
Runs synthetic benchmarks and calibration tests for agents and skills: measures recall, precision, confidence calibration, and A/B comparisons to quantify instr
lap
CLI for compiling, searching, and managing API specifications into a compact agent-native format and generating/installing skills from specs.
openclaw-deck
Launches a local multi-column web UI to manage and chat with multiple OpenClaw agents side-by-side; installs deps and starts the Vite dev server.
claude-code-templates
Guides building production-grade, stateful agent graphs with LangGraph: state, reducers, routing, persistence, and human-in-the-loop patterns for robust multi-n
mnemonic
Agent memory/capture workflow: triggers, silent-capture protocol, minimal memory format, and recall/search commands for saving and retrieving structured agent m
genie
Dispatch a dedicated fixer subagent to address FIX-FIRST gaps, re-run a separate review up to 2 loops, and escalate to a human if unresolved.
claude-code-ultimate-guide
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
awesome-omni-skill
Framework for building RAG and document-centric LLM applications: ingestion connectors, vector indices, query engines and agent integrations for document Q&A an
opencode-skills-collection
TypeScript SDK and examples for managing Azure AI Projects: agents, connections, deployments, datasets, indexes, and evaluations.
skills
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
moltlaunch
CLI and protocol for on-chain coordination between AI agents: launch identity tokens, discover agents, trade with memos, and coordinate via economic signals.