MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
pikku
Expert guide for writing, running, and optimizing Pikku scenarios for end-to-end testing and production health checks.
awesome-omni-skill
Analyzes QA test case documents against source code to identify coverage gaps and suggest missing test scenarios.
harness9
Performs detailed code reviews of new or modified files, categorizing issues by severity (Critical, Warning, Suggestion).
claude-mpm-skills
Standardizes the process of dispatching code-reviewer subagents to verify implementations against requirements.
inferentialmistakes
A rigorous 10-point statistical audit for movement science and neuroscience research to prevent common inferential mistakes.
meta-skills
An independent reviewer-resolver loop that checks code or artifacts against requirements without sunk-cost bias to ensure high quality before shipping.
claude-toolbox
Compare implementation code against design docs to find missing features, spec deviations, outdated docs, and inconsistencies.
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
claude-skill-registry
Analyze structured review feedback logs to identify recurring false positives, missing checks, and produce evidence-backed recommendations to improve review ski
gascity-packs
A high-rigor, multi-agent code review pipeline using tiered personas and confidence-gated findings for professional software engineering.
light0305
Automated reflection and self-review system for high-quality output.
core
A rigorous, multi-phase loop for reproducing, hypothesizing, and fixing hard bugs and performance regressions.
griddynamics
Expert guidance for writing isolated, idempotent tests with 80%+ coverage and strict external-only mocking.
pr-reviewer-skill
Automates comprehensive GitHub Pull Request reviews using industry-standard quality criteria, gh CLI, and a structured approval workflow.
de-anthropocentric-research-engine
A quality gate that self-reviews research artifacts for completeness and consistency before final delivery.
agentops
Systematically prepares pull requests by validating tests, analyzing commit patterns, and generating high-quality, structured PR bodies.
toolhive-catalog
An expert system for analyzing pull requests, ensuring code correctness, security, and maintainability with structured feedback.
zby
Comprehensive quality gate for knowledge notes, combining cold-read prediction, schema validation, and graph health checks.
zouroboros
A rigorous 3-stage verification system (Mechanical, Semantic, Consensus) to ensure artifacts strictly meet specifications.
video-automator-skills
Code-first auditing for Remotion video projects to ensure overlay readability and safe-area compliance through iterative batch fixes.
skills_collection
Implement a rigorous E2E-first testing philosophy for the AIDB project using the DebugInterface abstraction and MCP health standards.