writing-skills
3049Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
not rated 2 6mo ago A 20 tokens
ODbL-1.0
example-skill
3050Skill Claude CodeCodex
A demonstration Claude skill showing the correct SKILL.md format and structure. Use this as a template when creating new skills or learning about skill packaging.
not rated 2 9mo ago A 33 tokens
eval-skills
3051Skill Claude CodeCodex
Evaluate, benchmark, or test-drive an unfamiliar AI agent skill, tool bundle, prompt workflow, or capability package. Use when the user asks whether a downloaded/shared .skill, SKILL.md, agent workflow, or reusable AI capability actually helps, is worth installing, works as advertised, performs better than asking an…
not rated 2 2mo ago A 114 tokens
original MIT
loop-engineering
3052Skill Claude Code
Loop Engineering — a fully autonomous long-horizon engineering closed loop (degraded version for Gemini CLI / Codebuddy). Propose an idea → rough plan → run the project. Cross-tool orchestration of gstack / OpenSpec / GSD / Superpowers with adversarial quality gates. NOTE: interactive features (AskUserQuestion…
not rated 2 2mo ago A 95 tokens
SkillFather
3053Skill Claude CodeCodex
A command-line reviewer for checking whether an agent skill fits a user's needs, setup, and workflow. It asks diagnostic questions and gives scores across five areas for six agent platforms.
not rated 2 15d ago A 97 tokens
original MIT
swarm-auth-example
3054Skill Claude CodeCodex
Reference implementation showing how to add agent sign-in/sign-up to any software tool. Demonstrates dual authentication (human + agent), SKILL.md creation, and ClawHub publishing.
not rated 2 6mo ago A 41 tokens
kotlarmilos/ai-dotnet-bootstrap
Skill Claude CodeCodex
Turn any .NET repository into an AI-native development environment. Use when someone wants to set up Copilot infrastructure, add AI skills/agents/workflows to a .NET repo, onboard a repo for AI-assisted development, or make a repo "AI-native". Also use when asked about setting up copilot-instructions, CI feedback…
not rated 2 6mo ago A 89 tokens
hasanrafiq-goog/agy-skills-subagents
Skill Claude CodeCodex
Top-level director skill for orchestrating skill-driven sub-agent pipelines, including parallel scatter-gather fan-outs and sequential multi-persona workflows.
not rated 2 1mo ago A 32 tokens
Skill Claude CodeCodex
Use when work is multi-step, context-heavy, research-heavy, or delegated. Contains bulky context, phases work, bounds retries, delegates independent reasoning, and reserves capacity for verification.
not rated 2
changed 2d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Route Agent Skill Factory requests across read-only behavior and explicit Registry mutation modes; enforce mutation authorization, visibility-aware Registry-first planning, Candidate Skill Inspection, Reuse Boundary Check, runtime discovery/composition, and progressive disclosure.
not rated 2
changed 13d ago A 50 tokens
super-mode
3059Skill Claude CodeCodex
A unified super-mode orchestrator inspired by Doubao. It normalizes any user request into a v1/v2-compatible task protocol, determines the execution mode first, decomposes the work into subtasks, and dispatches them to the right capability modules—complex-task-handler, deep-web-search, multi-content-generator, and the…
not rated 2 6mo ago A 114 tokens
autonomous-agent
3060Skill Claude CodeCodex
Enforce a maximally autonomous, self-directed working protocol on the assistant. Apply whenever the user asks the agent to complete a task, build a feature, fix a bug, or "just handle it / do it yourself / figure it out / don't come back until it works / stop asking me". Use ONLY when the user wants the agent to act…
not rated 2 21d ago C 163 tokens
original MIT
claude-md-checker
3061Skill Claude CodeCodex
A checker for CLAUDE.md files, which contain instructions for the Claude coding agent. It reviews whether those instructions follow the official recommended practices.
not rated 2 6mo ago A 36 tokens
butler
3062Skill Claude CodeCodex
What is Butler? Butler is a lightweight, composable orchestration framework for managing autonomous agents and workflows. It enables agents to collaborate, chain operations, and handle complex task decomposition across multiple systems. Think of it as the nervous system that connects your agents together.
not rated 2 7mo ago A 0 tokens
original MIT
skilldo
3063Skill Claude CodeCodex
Generate SKILL.md agent rules files for software libraries. Use when you need to create, review, or lint SKILL.md documentation for Python, Go, JavaScript, Rust, or Java libraries, or when configuring skilldo.toml files.
not rated 2 1mo ago A 52 tokens
package-skill
3064Skill Claude CodeCodex
Create and manage skill packages — bundles of related skills merged into a single top-level skill with internal dispatch. A package skill's own description declares which sub-skills it contains. Trigger when you want to combine multiple skills into one package, reorganize your skill library, or scan a package's…
not rated 2 5mo ago A 100 tokens
original MIT
Skill Factory
3065rollymu25/hermes-skill-factory
Skill Claude CodeCodex
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
not rated 2 4mo ago A 21 tokens
Maxbay1017/harness-engineering-skills
Skill Claude CodeCodex
Harness Engineering skill for initializing or retrofitting a repository with a global AI layer. Use for project AGENTS.md, ARCHITECTURE.md, repo-local docs, execution plans, quality/reliability/security scorecards, nested instructions, repo skills, Codex config, hooks, MCP/LSP strategy, and lint/typecheck/test/review…
not rated 2 3mo ago A 78 tokens
recontextualizer
3067Skill Claude CodeCodex
Forces developers to demonstrate ownership of AI-generated work by gating completion on proven context retention. Uses unpredictable code-level probes, end-to-end trace demands, and anti-gaming detection to prevent shallow engagement. Refuses to mark work as context-owned until answers pass depth checks at the…
not rated 2 1mo ago A 84 tokens
original Apache-2.0
skill-manager
3068dash15686/Claude-skill-manager
Skill Claude Code
A tool for managing Claude Code skills, which are reusable instructions that guide an AI coding assistant. It covers installing, listing, modifying, and removing those skills.
not rated 2 3mo ago B 104 tokens
original MIT
init-rules
3069Skill Claude Code
Interviews the project and generates a complete .claude/rules/ rule set that agents, new teammates, and handover recipients can immediately reference. Extends an existing CLAUDE.md if found; generates from scratch if not.
not rated 2 5mo ago A 51 tokens
Skill Claude CodeCodex
Create, improve, and validate agent skills using a SkillOpt-inspired workflow: scored evidence, bounded add/delete/replace edits, validation gates, rejected-edit memory, and compact deployable SKILL.md artifacts. Trigger when the user says "write a skill", "create a Codex skill", "make a Claude skill", "turn this…
not rated 2 3mo ago A 165 tokens
original MIT
cli-builder
3071Skill Claude CodeCodex
Build a generic-installable CLI tool with its companion SKILL.md so any agent (Vellum, Claude, GPT, etc.) can pick it up and use it. Use when the task is "ship a CLI for service X" or "wrap API Y in a tool agents can call." Out of scope for one-off internal scripts that don't need agent discovery, and for skills that…
not rated 2 3mo ago A 95 tokens
original MIT
skill-creator
3072Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 2 7mo ago A 45 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: