SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
atelier
Generate and maintain project documentation: READMEs, API docs, changelogs and architecture notes; run generators and keep docs versioned alongside code.
skill
Provides Deno runtime support for executing modern JavaScript/TypeScript tasks and managing Deno permissions and dependencies.
skill
Provides Node.js version management and convenient npm/npx wrappers so agents can install packages, run JS tools, and switch Node versions reliably across envir
skill
Lightweight skill to run and manage Raku (Perl 6) scripts: provides examples and checklist for executing scripts and validating runtime availability.
awesome-omni-skills
Workflow and best practices for restoring and preserving project context during code refactoring, with provenance and selective file restoration.
skill
Run and manage Perl scripts and runtimes from an agent with consistent patterns for execution and environment detection.
ai-toolkit
Guidelines and patterns for implementing prompt caching with Anthropic APIs to reduce input-token costs and latency, including TTLs, breakpoints, and hit-rate m
alef
Generates fully-typed language bindings and scaffolding for Rust libraries across 16 target languages, and provides CLI workflows for generate, build, test, ver
.claude (Claude Code config)
Guides authors on creating robust Claude Code slash commands: naming, frontmatter, argument handling, and best practices for reusable prompts.
awesome-omni-skill
Find, activate, and capture macOS application windows across Spaces with filters for app name, title (regex), process path, PID, and command-line args.
claude-code-blueprint
Run end-to-end Playwright test suites or perform interactive browser walkthroughs to verify UI and user journeys for a project.
nevaberry-plugins
Add knowledge about Drizzle ORM changes (v1.0.0-beta.x) — validator import consolidation, Effect Schema support, node-sqlite driver, and .comment() query taggin
spec-gen
Apply a confirmed refactoring plan safely: reads a refactor plan, applies changes as small, test-gated mini-developments, and stops on failures to avoid lost co
hyperframes
Install and wire reusable HyperFrames blocks and components into compositions using `hyperframes add` and registry manifests.
vexjoy-agent
Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).
cc-skills-golang
Human-coded Go style guidelines for clarity, function design, control flow, and idiomatic practices — use when writing or reviewing Go code, creating linters, o
awesome-omni-skills
"IT Manager Pro (Elite Leadership Advisor) workflow skill. Use this skill when the user needs Elite IT Management Advisor specializing in data-driven...
claude-skill-registry
Drive repo work through a single authoritative YAML todo (.copilot-todo.yaml) using plan → execute → iterate workflows and small, commit-sized tasks.
globalyze
CLI-driven localization toolkit for React/Next.js apps — initialize, sync, audit, analyze, and runtime-wire i18n projects safely.
claude-skill-registry
Manage Trello boards, lists, and cards from the terminal using the uni CLI. Create boards/lists/cards, move or archive cards, and list members; requires TRELLO_
opencode
Create zero-context, executable implementation plans from specs: file-level changes, tests, commands, and step-by-step tasks, avoiding placeholders and ensuring
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
superclaude-plusplus
Run project-specific verification rules that check business logic, architecture patterns, and naming conventions beyond linters.
skill
Run one-off Node.js packages or CLIs directly via npx — useful for scaffolding, testing package versions, and ad-hoc tool execution.
claude-code-blueprint
Run a comprehensive, multi-agent code review that covers quality, security, and database concerns and synthesises a severity-ranked findings table.
capsem
Structured, per-bug review workflow: confirm, validate or push back, get agreement, implement TDD fixes, and commit with changelog — one bug per commit.
claude-build-workflow
Convert product requirement documents (PRDs) or Markdown specs into Ralph's prd.json format, producing small verifiable user stories for autonomous execution.
agentic-dev-team
A four-phase debugging protocol (reproduce, investigate, root-cause, fix) that enforces evidence-driven fixes and prevents guess-and-fix thrashing.
nikoheikkila.fi
A concise guide of project task commands (Taskfile) for common development, build, test, and deployment workflows used in this repository.
mnemonic
Search and synthesize across mnemonic memory files (namespaces, tags, types, full-text) to answer questions and surface sources.
