SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
ucai
Guidance and templates for designing tests, scaffolding unit/integration/E2E tests, and improving test quality and coverage across languages and frameworks.
plugins
Run a focused code review workflow: gather context, run targeted tests, fix critical issues, commit focused changes, and open or update a PR.
claude-skill-registry
Run multi-language quality gates: linting, formatting, type checking, and tests across major languages to validate code changes before merging.
agentclash
Run lightweight Go-specific checks (detect go.mod, run tests) after commits when Go code is present to catch regressions early.
agentic-dev-team
A four-phase debugging protocol (reproduce, investigate, root-cause, fix) that enforces evidence-driven fixes and prevents guess-and-fix thrashing.
awesome-omni-skills
Run Playwright tests at scale with cloud-hosted browsers and integrated Azure portal reporting. Includes migration notes to @azure/playwright.
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
shipyard
Automated workflow to detect and fix CVEs in Go dependencies across Submariner repositories; creates one commit per package and a single PR per branch.
cowork-wordpress-expert
Guides WordPress PHPUnit testing using WP_UnitTestCase, with test categories, coverage targets, test design principles, and CI integration recommendations.
agentic-tools
Enforce a strict TDD cycle (red→green→refactor) for feature work: require failing tests first, mock bootstrap validation, full-suite runs, and quality gates bef
ordinary-claude-skills
Comprehensive guidance for writing robust unit and integration tests for shell scripts using Bats, including fixtures, setup/teardown, mocking, and CI integrati
ai-workspace-archive
Set up and manage Git hooks (Husky, lint-staged, pre-commit) to enforce linting, formatting, tests, and commit message rules before code reaches CI.
specialist-agent
Run disciplined TDD cycles: write a failing test, implement the minimal fix, then refactor — for features and bugfixes where correctness matters.
specialist-agent
Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.
han
Comprehensive guide to configuring Pylint: pylintrc, message control, plugins, scoring, CI integration, and production-ready best practices for Python projects.
agent-toolkit
Production-quality Bash scripting guide enforcing safe idioms (set -euo pipefail), ShellCheck compliance, and patterns for maintainable scripts.
workflows
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
nexus-agents
Structured bug-fix workflow and triage protocol: reproduce, localize, reduce, fix, add regression test, and verify before resuming development.
hypo-workflow
Manage Hypo-Workflow rule severities, structured rule packs, lifecycle hooks, and rule-based enforcement for agent workflows (severity: off/warn/error).
claude-skill-registry
Assist with Morphir release readiness: run pre-release checks, generate changelogs, manage version bumps, and coordinate release tasks.
skills
Run CLI commands, tests, and debugging reliably inside the project's Linux devcontainer to avoid host-architecture mismatches and preserve isolated test state.
icey-cli
Operator workflow and safe build/packaging/release guidance for the icey-server CLI and media server.
ryanb/dotfiles
Generate a ranked, clickable list of open PRs prioritized by review ease, with grouping for PR dependency chains and optional preference directives.
clawrouter
A strict release checklist for ClawRouter: version bump, changelog, build, tests, tag, GitHub release, and npm publish—used to enforce reliable releases.
skilllearnbench
Run Trivy in offline mode to scan dependency files (package-lock.json, etc.) for HIGH/CRITICAL vulnerabilities and produce machine-readable JSON results.
aura-frog
Validates hierarchical plan trees against 8 invariants (parent/child integrity, no orphans, valid status, monotonic revisions, DAG acyclicity, etc.) and refuses
awesome-omni-skills
Master orchestrator for test-driven development workflows: enforces red-green-refactor discipline, coordinates multi-agent TDD workflows, and preserves provenan
claude-skill-registry
Guidance for designing, running, and analyzing test suites for agents: test isolation, execution patterns, and coverage-based enforcement.
code-abyss
Generates README.md and DESIGN.md scaffolds from a module's code and structure to accelerate project documentation.
ostack-saas
Automated performance benchmarking and regression detection: captures baselines, measures Core Web Vitals, and compares metrics across PRs to flag regressions.
