SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
orchestkit
Deep pull-request code review using parallel specialized agents (quality, security, tests, architecture, performance) and synthesized review reports for approve
crucible
Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.
agent-skills
Quickly re-read recently changed code to catch obvious bugs, typos, and edge cases before committing.
crouton-kit
Analyze technical designs for requirements coverage, flow correctness, and architectural feasibility to surface implementation risks.
pracht
Audit Pracht layout 'shell' components for composition bugs: document tags in shells, missing children, misplaced ErrorBoundary, missing Loading for SPA routes,
springboot-skills-marketplace
Run focused, evidence-based code reviews for Java 25 and Spring Boot 4 projects — migration risks, architecture boundaries, null-safety (JSpecify), security, an
claude-skill-registry
Automated, structured PR reviewer: gathers metadata, diffs, CI results, dependency changes and provides a concise verdict with testing and documentation recomme
claude-code-harness
Quality guardrail for Claude Code update integrations: detects doc-only Feature Table additions and forces implementation proposals when needed.
specs.md
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
skills
Perform structured, prioritized code reviews that find correctness, security, performance, reliability, and testing issues and provide concrete fix suggestions.
draft
Identify, categorize, and prioritize technical debt across six dimensions, producing evidence-based remediation plans and prioritized quick wins.
chromium
Practical guide to resolving NullAway static analysis issues and migrating code to @NullMarked null-safety in Chromium Java code.
han
Guidelines for agents to prioritise technical accuracy and direct, evidence-based communication instead of excessive agreeableness.
ship
Implements implementation stories from a plan using wave-based parallelism: host implements single-story waves and dispatches subagents for parallel stories, wi
clawg
Delegate coding tasks to the Blackbox multi-model coding CLI; run interactive sessions, one-shot prompts, checkpointing, and background tasks with a judge that
cursor-rules-java
Guidelines and best practices for structuring Micronaut applications: DI scopes, configuration properties, factories, controllers vs services, scheduling, and g
collaborating-with-claude-code
Bridge to delegate code implementation, review, and tests to Claude Code via a JSON bridge script that returns structured output for multi-turn sessions.
cowork-os
Run a consensus-style multi-agent review of a pull request and produce severity-ranked findings and actionable remediation steps.
hivemind-plugin
Research-first architecture review and strategic planning skill: scans codebases, finds architectural issues, and synthesizes evidence-based recommendations for
openfang-cn
Provides senior-level React guidance: hooks, state management, Server Components, performance optimization, and common patterns for building fast, accessible, m
genie
Dispatch a dedicated fixer subagent to address FIX-FIRST gaps, re-run a separate review up to 2 loops, and escalate to a human if unresolved.
claude-code-skills
Coordinate calls to the Codex CLI: collect minimal context, run codex exec/resume, and present the model's independent analysis or review to the user.
codex-skill
Provide independent technical verification and deeper research for Claude Code using the Codex CLI to analyze code, confirm approaches, and surface risks.
alfred-dev
Read and map a repository before making changes: discover structure, config, tests, patterns, and dependencies to avoid breaking conventions when modifying code
owlex
Start a Codex CLI session for deep reasoning, code review, and program analysis; returns a task id and instructions to check results.
ai-pair
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
codex-collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
aiskillstore
Structured 4-hour SOP for comprehensive code review: automated checks, specialized parallel reviews (quality, security, perf, architecture, docs), integration a
vibe-skills
Advisory agent that reviews test architecture, creates quality gates, assesses risk, and suggests test strategies and improvements.
claude-skill-registry
Orchestrates hierarchical, multi-sector Python code reviews (L1–L3) with delegated sub-reviews, scoring, and consolidated final reporting for full-project audit
