MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
skill-router
A meta-skill that indexes installed skills and routes substantive requests to the most relevant one via suggest or auto mode.
code-abyss
Reference guide for designing single- and multi-agent LLM systems, RAG pipelines, security hardening, and prompt engineering for production agents.
box0
Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.
ppt-agent-skills
Full-workflow AI assistant to generate high-quality HTML slides and PPTX decks: research, outline, style, per-page planning, HTML and visual QA.
ohmyclaw
Orchestrates Plan→Work→Review agent workflows with a bridge for real-time channel notifications and model routing (GLM/GPT/Claude).
the-claude-protocol
Bootstraps a lightweight multi-agent orchestration using Beads CLI and per-task git worktrees; includes orchestrator patterns, supervisors, and hooks to enforce
ai-maestro-orchestrator-agent
Coordinate and delegate tasks to remote AI agents via AI Maestro (AMP), with ACKs, monitoring loops, and verification before approvals.
vibe-skills
Governed runtime entry that orchestrates XL-first planning, execution, verification, and phased cleanup for complex agent workflows.
claude-skill-registry
Drive repo work through a single authoritative YAML todo (.copilot-todo.yaml) using plan → execute → iterate workflows and small, commit-sized tasks.
stellarlinkco
Orchestrates a five-phase, multi-agent feature development workflow (Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper; manages task wor
citadel
Route user intents to the cheapest capable handler (skill, marshal, archon, or fleet) using a multi-tier classifier for scope, complexity, persistence, and para
gran-maestro
Activate Gran Maestro (Maestro) orchestration mode: enables conductor-style orchestration, installs hooks, and configures workspace defaults for coordinated wor
de-anthropocentric-research-engine
Orchestrates a full adversarial assessment: surface enumeration, attack-vector generation, probing, and aggregated findings to score attack resilience.
agent-teams-playbook
A cross-platform playbook for designing and running multi-agent teams: six-stage workflow, fallback chains, scenario decision trees, and quality gates for agent
LunarTech-X Superpowers
Automate Kickbox operations via the Composio Kickbox toolkit on a Rube MCP server — discover tools, manage connections, and execute Kickbox workflows safely.
ai-pair
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
superclaude-plusplus
An always-active orchestration agent that analyzes requests, auto-delegates to sub-agents, and runs PDCA-style project workflows across MCP tools.
orchestrator-supaconductor
A single goal-driven CLI entry that creates or resumes orchestrator tracks: parse a user goal, generate plan/spec, and run an evaluate-loop to execute multi-age
tensorlake-skills
Provides agent-aware guidance and workflows for Tensorlake sandboxes and orchestration — use when the user asks about Tensorlake APIs, sandboxing, or SDK usage.
skills_collection
Coordinate test strategy, automation, and quality gates across unit, integration, E2E and performance tests for a component or service.
fufan-vibecodingcourse
Orchestrates fetching GitHub issues, spawning fix & review sub-agents to open PRs and address review comments, with cron and watch modes for automation.
openclaw-master-skills
IM-first messaging and orchestration layer for OpenClaw: topic & P2P messaging, task and pipeline workflows, delegation, and a WebSocket-first autopoll runtime.
agencycli
CLI to create and manage hierarchical AI agent teams, projects, roles and automated task/playbook workflows (heartbeats, inbox, crons).
agent-skills-library
Automate Skyfire toolkit workflows via Rube MCP: discover tools, verify connections, and execute schema-compliant operations safely.
pos-sprint
Orchestrate natural-language vendor searches: parse requests to structured JSON, rank candidates from Baserow, and summarise feedback with an LLM for hiring or
openteams
Automate Mezmo operations through Composio's Mezmo toolkit via a Rube MCP server; always discover tools first to use current schemas and avoid hardcoding inputs
happycapy-skills
A configurable multi-agent swarm that autonomously finds issues, writes fixes/tests/docs, opens PRs, and iteratively responds to review feedback for open-source
marketplace
Structured 4-hour SOP for comprehensive code review: automated checks, specialized parallel reviews (quality, security, perf, architecture, docs), integration a
deepswarm
Orchestrate large-scale parallel AI workers for batch and multi-turn tasks with auto-calculated worker counts, stagger, and tiered model delegation for cost-eff
manifest-dev
Orchestrates multi-party deliberation in Slack: presses for decisions, surfaces trade-offs and evidence, and posts wrap-up syntheses while the operator retains