MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
orchestkit
Run comprehensive verification: parallel agents for tests, security, coverage, grading and improvement suggestions; produces evidence-backed verification report
reviw
Toolkit for backend API testing with proper test frameworks (vitest/jest, go test, pytest, cargo test). Supports verifying API endpoints, database state changes
agent-skills
Extract acceptance criteria from specs, generate BDD scenarios, and perform static compliance checks with evidence-backed verdicts and traceability matrices.
ystack
Run final verification, check docs and tests, and create a pull request (or delegate to a repo pr-draft skill).
vexjoy-agent
Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).
specialist-agent
Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.
orchestrate
Supervisor skill that composes multi-model runs, routes subtasks to the right models and skills, and manages implementation & verification runs.
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.
ask-codex
Routes heavy repo exploration, implementation, and verification work from Claude Code to the Codex CLI with clear review loops and verification requirements.
gateflow-plugin
Orchestrates SystemVerilog/RTL development: plan, generate, verify, and iterate using specialist agents to deliver working, lint-clean, tested RTL.
han
Guidelines for agents to prioritise technical accuracy and direct, evidence-based communication instead of excessive agreeableness.
ordinary-claude-skills
Generate context-safe, phase-aligned planning docs for web projects (implementation phases, schemas, API endpoints, UI components and verification criteria).
memstack
Run a structured verification protocol (automated checks + manual requirements review) to confirm work meets requirements before committing or shipping.
awesome-claude-corporate-skills
Populate and validate LBO Excel templates: fill formulas (no hardcoding), ensure formatting standards, run verification checks, and produce investment-quality o
superclaude-plusplus
Run project-specific verification rules that check business logic, architecture patterns, and naming conventions beyond linters.
cc-design
An agent skill that produces high-fidelity HTML design artifacts and interactive prototypes (slides, landing pages, UI mockups), with routing, templates, and ve
dgk-gpt
Temporarily bias the agent toward a research-heavy workflow: plan sub-questions, retrieve sources, synthesize with explicit citations, and verify before impleme
awesome-skills
Provide senior-level systems engineering guidance for aerospace programs: requirements management, MBSE, integration planning, and verification & validation bes
marketplace
TDD-driven workflow patterns and phase-checkpoint protocol for Conductor-style task tracks: tests-first, checkpoints, git commit conventions, and verification s
RTL Agent Team
Profiles and conventions for clock-domain crossing (CDC) and structural analysis tools (svlens, spyglass, vc_cdc, questa) plus normalized result fields for CI a
aura-frog
A compact TDD-driven bugfix workflow that enforces root-cause investigation, failing-test-first discipline, and stepwise verification to prevent regressions.
RTL Agent Team
Reference policy and checklists defining artifact and quality gates, retry rules, and escalation for the RTL→Verification (Phase 4→5) pipeline in hardware verif
clawsec
Generate deterministic runtime attestations and perform fail-closed drift detection for Hermes-managed infrastructure.
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
Feature Marker
Orchestrates end-to-end feature development: PRD, tech spec, task breakdown, verification, local commit, and branch handoff using a skill-first workflow.
edwinhu
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
atlas-session-lifecycle
Gracefully pause, verify, or finish a work session: harvest promotable content, checkpoint progress, create PRs, and settle optional bounties before archiving.
openspace
Iterative workflow to verify PDF page counts and automatically adjust layout parameters (images, fonts, margins, tables) until page requirements are met.
claude-ai-music-skills
Validate research outputs: check source accessibility, verify quotes, cross-check dates and facts, archive sources, and produce a verification report for human
claude-matrix
A 5-agent, context-aware code review pipeline for comprehensive PR and staged-change reviews, including security detection, blast-radius analysis, triage, remed