Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,385 indexed, measured the same four ways as everything else here.
Creates a new VR Experience (Level) for Neural Flight. Step-by-step guided workflow — creates folder, adapts 5 files from template, defines parameters, registers in catalog. Supports reference images and descriptions. Use when the user wants to create, scaffold, or add a new experience or level.
Type-safe validated wrappers for browser CustomEvent, BroadcastChannel, and window.postMessage APIs using any standard-schema-compatible validator (zod, valibot, arktype). Use when implementing createEvent, createEventMap, createBroadcastChannel, createBroadcastEvent, or createMessage. For React hooks (useListener…
Comprehensive Ansible automation skills following Red Hat Communities of Practice best practices. Covers playbook creation, role development, shell script conversion, troubleshooting, code review, and collection scaffolding.
★not rated 5 1mo agoA
tokens not measured
originalMIT
A machine-learning guide to causal inference, which estimates whether one factor causes a change in another. It covers DML, causal forests, DoWhy, and AIPW methods.
Iterative sprint workflow with delegated implementation and independent verify-repair loops. Finalize each sprint only after every required gate passes.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Convenes a multi-model "council" to answer a question, then synthesizes a single best answer — inspired by Karpathy's llm-council. Each member runs through its own subscription/sign-in CLI, not an API key: ChatGPT (the desktop app, via chatgpt-ask), Gemini (Antigravity agy), and Claude (claude -p), with Codex (codex…
Run an adversarial debate with a cross-model reviewer (Codex or Antigravity/agy) to stress-test a draft, plan, research claim, or design decision. Use this whenever you need structured critique before finalizing decisions.
Produce higher-quality code by breaking a feature into small, focused tasks the coding agent can nail one at a time. Works like an engineering team: feature → milestones (product deliverables) → 30-min tasks with specific files, acceptance criteria, and dependencies. Each task runs in a fresh context — narrow scope…
A workflow for developing one requirement across multiple Git repositories, which are separate code projects. It creates a shared workspace containing the requirement, implementation plan, and selected project copies.
Talk to humans in HTML — role-aware. /talk-html routes the page to one of 8 audience-specific sub-commands (/talk-ux, /talk-ceo, /talk-data, /talk-reviewer, /talk-cto, /talk-qa, /talk-docs, /talk-legal). Each role hardcodes the audience, the proof modality they must see, the build tools, the programmatic evaluation…
Guide users through creating, reviewing, and improving OpenClaw skills following proven best practices. Use when someone asks to "create a skill", "write a SKILL.md", "make an OpenClaw skill", "publish to ClawHub", "review my skill", "improve my skill", "optimize skill description", "skill frontmatter help", "what…
Write a commit message following the Conventional Commits specification from the staged (or described) changes. Use when asked to write, suggest or reword a commit message. It only writes the message; staging and committing stay with the user.
Fetch content from a source into a directory — YouTube, X, Instagram, LinkedIn, Notion, Scribd, arXiv, blogs — plus Vedic chart digitisation. Output location is a parameter; nothing here knows about vaults.
★not rated 5
changed 1mo agoA
tokens not measured
originalMIT
Skills for autonomous story execution (dex orchestrator), adversarial spec review (Codex or local LMStudio), completeness & wiring review (architect-review-pr), whole-repo three-lens audit (review-codebase), pre-task blind-spot discovery (blind-spot), CLAUDE.md minimizer (claude-md-slim), spec-to-PR conductor…
★not rated 5 1mo agoA
tokens not measured
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: