SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
orchestkit
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
claude-code-minoan
Guidance and tooling for creating, reviewing, and packaging Agent Skills (SKILL.md) — frontmatter quality, triggers, evals, scripts, and packaging best practice
claude-code-templates
Guides creating Hookify rule files (.claude/hookify.*.local.md) to detect patterns (dangerous commands, secrets, debug logs) and show warnings or block actions.
hmem (persistent agent memory)
Interactive installer and setup guide for hmem (persistent memory MCP server); automates .mcp.json config, memory dir, and adds agent hooks for Claude Code, Gem
codex-toolkit-for-claude
Canonical reference for Claude Code plugin schemas, frontmatter, hook events, and naming conventions — used when auditing or authoring Claude Code plugins.
trending-skills
Routes Claude Code tool calls through an OpenAI-compatible shim so Claude Code can use GPT-4o, Gemini, Ollama and other OpenAI-style models while preserving too
caveman
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
skillshub
Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.
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.
oh-my-claudecode
Launch N CLI worker processes (claude/codex/gemini) in tmux panes to run tasks in parallel for multi-agent CLI-first workflows.
ordinary-claude-skills
Author Hookify rule files (.claude/hookify.*.local.md) to detect patterns (bash, file, prompt, stop) and show actionable messages — ideal for enforcing safety,
Claude Code Settings
Analyze a development or agent session to capture learnings and improve CLAUDE.md instructions; supports quick and deep analysis modes.
ClaudeSmalltalk
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
app-plan-skill
Interactive interview flow that turns high-level app ideas into a concrete document structure and initial files—guides product, feature, design and deployment d
Claude Code Clawdbot
Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.
claude-code-voice-skill
Enable voice calls with Claude (Opus) to discuss a project's code and context, supporting inbound and outbound calls and automatic transcript saving.
claude-telegram-supercharged
Manage the Telegram bot daemon lifecycle (start, stop, restart, status, logs) from inside an agent session, with checks and production-safe fallbacks.
claude-skill-registry
Guidelines for creating and running Claude Code CLI agents: agent JSON format, storage conventions, and execution commands.
claude-matrix
Manage file and package warnings (add, remove, list, check) for a Matrix workflow; parse user arguments and call the matrix_warn tool to enforce repository-leve
mnemonic
Installs and configures a filesystem-backed mnemonic memory system for Claude-style agents, creating directory structure, CLAUDE.md hooks, and an initial contex
arra-oracle-skills-cli
Scaffold and create a new oracle repository/session (via maw bud or standalone steps), including CLAUDE.md, ψ/ scaffolding, and optional split/birth workflows.
zylos-core
Schedule and dispatch one-time, recurring and interval tasks to an agent runtime via the C4 comm-bridge for autonomous execution.
buildwithclaude
Get fix intelligence for a vulnerability and propose concrete remediation for the current repository
buildwithclaude
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business,...
prd-debate
Run a multi-agent, cross-model adversarial debate to produce a high-quality product requirements document (PRD) and decision log.
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
.claude (Claude Code config)
Guides authors on creating robust Claude Code slash commands: naming, frontmatter, argument handling, and best practices for reusable prompts.
claude-skill-registry
Bridge Claude Code and the OpenAI Codex CLI: generate AGENTS.md from CLAUDE.md, provide Codex exec helpers, and document skills for cross-tool usage.
the-claude-protocol
Bootstraps a lightweight multi-agent orchestration using Beads CLI and per-task git worktrees; includes orchestrator patterns, supervisors, and hooks to enforce
happycapy-skills
A configurable multi-agent swarm that autonomously finds issues, writes fixes/tests/docs, opens PRs, and iteratively responds to review feedback for open-source
