MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
third-brain-v5-skills
Transforms repeatable tasks into bounded, evidence-driven agent loops with strict verification and budget controls.
meta_kim
Governance and orchestration dispatcher that routes multi-stage agent workflows using an 8-stage spine for governance, review, and verification.
ask-codex
Routes heavy repo exploration, implementation, and verification work from Claude Code to the Codex CLI with clear review loops and verification requirements.
workflows
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
galyarder-framework
Require and verify concrete evidence (command outputs, test results, build exit codes) before claiming work is complete or creating PRs.
Feature Marker
Orchestrates end-to-end feature development: PRD, tech spec, task breakdown, verification, local commit, and branch handoff using a skill-first workflow.
ystack
Run final verification, check docs and tests, and create a pull request (or delegate to a repo pr-draft skill).
ai-maestro-orchestrator-agent
Coordinate and delegate tasks to remote AI agents via AI Maestro (AMP), with ACKs, monitoring loops, and verification before approvals.
repo-task-proof-loop
A repo-local workflow skill that creates auditable task folders and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
memstack
Run a structured verification protocol (automated checks + manual requirements review) to confirm work meets requirements before committing or shipping.
claw-bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
research-mode
Enforces strict citation-first behavior: require local or external citations, prefer direct quotes, and respond "I don't know" when unsupported — useful for fac
ordinary-claude-skills
Generate context-safe, phase-aligned planning docs for web projects (implementation phases, schemas, API endpoints, UI components and verification criteria).
OrchestKit
Run comprehensive verification: parallel agents for tests, security, coverage, grading and improvement suggestions; produces evidence-backed verification report
marketplace
TDD-driven workflow patterns and phase-checkpoint protocol for Conductor-style task tracks: tests-first, checkpoints, git commit conventions, and verification s
wizards-of-the-ghosts
Activate a high-integrity conversation mode where claims must be sourced, uncertainty is labeled, and speculation is explicitly flagged.
digital-chip-design-agents
Guidance and orchestration rules for logic synthesis: SDC constraint setup, compile strategies, netlist QC and LEC verification for ASIC/FPGA flows.
light0305
Automated reflection and self-review system for high-quality output.
dgk-gpt
A secure local gate that verifies changes, stages specific files, and pushes to the current branch for Codex agents.
zby
Comprehensive quality gate for knowledge notes, combining cold-read prediction, schema validation, and graph health checks.