MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
deep-recon
Orchestrate parallel multi-agent reconnaissance rounds to explore a topic deeply and produce a structured recon document (vault/Obsidian friendly).
pro-workflow
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
gateflow-plugin
Orchestrates SystemVerilog/RTL development: plan, generate, verify, and iterate using specialist agents to deliver working, lint-clean, tested RTL.
atlas-session-lifecycle
Fast, no-interaction session sync: append session-context files and MEMORY.md, print a concise summary; optional full run builds a capability inventory.
ask_why
A planning skill that turns vague requests into traceable decision rounds, producing PLAN.md, DECISIONS.md and FINAL_PLAN.md to guide complex, iterative work.
claude-superskills
Create, improve, and evaluate Agent Skills with a guided workflow: capture intent, draft SKILL.md, run evals and benchmarks, and optimize triggering description
memstack
Plan and task manager skill: parse, store, and resume project plans; provide next-action, todo, and priorities views for the agent.
lola-opencode
Generate clear, actionable Product Requirements Documents (PRDs) with user stories and acceptance criteria, saved to the repo's tasks/ directory for autonomous
marketplace
Automate Dice.com remote Easy Apply searches and submissions using Puppeteer/Chromium with resume and cover-letter uploads and conservative guardrails.
claude-code-plugins-plus-skills
Build and configure Retell AI voice agents with LLM prompts, function-calling, and call flow settings for phone-based booking and telephony tasks.
claudecode-research-harness-workflow
Unified session management for Claude Code: initialize, resume, persist memory, control state, and broadcast messages across agent sessions.
skills
A job marketplace skill for AI agents to post tasks, apply for work, and manage virtual-credit payments and deliveries.
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
Claude Code Skills
Merges and deduplicates evaluation worker results into a single verified review summary for coordinators, applying an architecture gate and verification checks.
forkprobe
Compares multiple AI skills or pipelines side-by-side on a single task to determine the most effective output.
sage
Create, iterate on, and evaluate Agent Skills: write SKILL.md, design test cases, run benchmarks, and improve triggering and performance.
spectre
Generate a single self-contained HTML prototype to validate features and flows visually before planning or implementation.
nwave
A practical five-phase workflow for designing, building, validating, and refining agent definitions and skills.
claude-elixir-phoenix
Plan Elixir/Phoenix features with domain-aware specialist agents and generate phased, checkbox-style implementation plans with verification steps.
odin-claude-plugin
Automates GitHub issue triage using a configurable label-based state machine to move issues from pending to agent-ready.