MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
ai-factory
Set up agent project context: analyze tech stack, install or generate skills, and configure MCP servers with mandatory security scanning for external skills.
skills
Onboard an agent into the DiagForge repo, run the canonical cold-start smoke test, and start a Visio-based drawing workflow that produces editable .vsdx outputs
hope-agent
Query Hope Agent's local SQLite log and session databases (read-only) to diagnose errors, trace tool failures, and verify fixes without asking users to paste lo
claude-skill-registry
CLI/TUI operation rules and safe automation patterns for PeakyPanes: targeting sessions/panes, using scopes, avoiding prompts, and reliable JSON automation.
Claude Code Settings
Analyze a development or agent session to capture learnings and improve CLAUDE.md instructions; supports quick and deep analysis modes.
claude-matrix
List, inspect, and export Matrix memory contents and statistics; includes modes for stats, failures, warnings, solutions, and JSON export for backups.
agents-in-a-box
SRE patterns for running and protecting autonomous agents: cost caps, circuit breakers, stall detection, observability, and runbooks to recover from incidents.
zylos-core
Report current context/window and token usage across supported runtimes so agents can decide when to rotate or trim conversation history.
claude-skill-registry
Guidance for designing, running, and analyzing test suites for agents: test isolation, execution patterns, and coverage-based enforcement.
agenti
Check ETH and USDC balances for a Base address and get step-by-step funding instructions, including minimum recommended amounts and bridging guidance.
agenti
Send a messages array to the Pinion AI agent and receive contextual responses (with web search), useful for on-chain explanations and protocol guidance; uses x4
skills
Automatically monitor agent wallet balances and top up via MoonPay, with x402 payment handling and safety controls.
soul.md
Defines a digital persona for an agent: reading order, operating principles, modes, and style guidance to embody a consistent identity.
hermes-one-click
Guidelines and workflow for running Codex as an isolated implementation lane while Hermes retains Kanban ownership, verification, and handoff.
boshu2
Mine past agent sessions for working prompts, decisions, rituals and recovery patterns (operational tooling).