The Index
Every entry verified live, scored against the public rubric, and timestamped. Sorted by overall score, never by stars.
25 of 46 entries
A process-first skill framework for Claude Code: brainstorming, test-driven development, systematic debugging, and verification skills that…
Anthropic's first-party public skill collection: the de facto reference for SKILL.md structure, frontmatter conventions, and…
An opinionated 23-skill suite that staffs a solo developer's agent with the roles a startup would hire: CEO review, design review,…
Browser automation as agent tools, built on Playwright's accessibility tree rather than screenshots: structured, deterministic web…
The reference implementations of the Model Context Protocol: the official server collection that defines what a well-built agent tool looks…
An MCP server that feeds agents current, version-specific library documentation at generation time, attacking the stale-training-data class…
GitHub's official MCP server: repos, issues, PRs, actions, and code scanning exposed as agent tools with GitHub's own auth and permission…
140 domain skills plus 100+ database connectors that turn a coding agent into a working research assistant for biology, chemistry, medicine,…
An MCP toolkit that gives coding agents semantic code retrieval and editing: language-server-grade symbol operations instead of…
A CLI for configuring Claude Code: install commands, agents, hooks, and settings from a large template catalog, plus usage monitoring.
A multi-harness plugin marketplace of role-specialized subagents (reviewer, architect, security, docs) installable across Claude Code, Codex…
Local-first agent memory over plain Markdown files with an MCP interface: knowledge persists as human-readable notes the agent reads and…
An AI task-management loop that decomposes a spec into ordered, dependency-aware tasks and drives an agent through them one at a time across…
A configuration framework layering specialized commands and cognitive personas onto Claude Code: an opinionated operating mode rather than a…
A defense-tech company's internally-maintained skill set, published. Notable for governance discipline: explicit boundaries, scripts treated…
100+ role-specialized Claude Code subagent definitions, consistently formatted, spanning engineering, review, security, and content roles.
Spec-driven development workflow for Claude Code: requirements, design, tasks, and implementation as gated phases with approval between…
A minimal three-file task loop for AI dev agents: create a PRD, generate a task list, then execute one task at a time with human check-ins.
A Claude-specific aggregator of skills, resources, and tooling. Partially scored: staleness at fetch time left several rubric dimensions…
A single CLAUDE.md distilling Andrej Karpathy's public observations on LLM coding pitfalls into instruction-file rules. An instruction set,…
A hand-picked aggregator of Claude Code resources: skills, commands, CLAUDE.md files, and tooling. More curation voice than most lists, same…
A structured slash-command set for Claude Code covering development workflows: review, test, deploy, and project-management commands with…
A 1000+ entry aggregator of agent skills across Claude Code, Codex, Gemini CLI, and Cursor. Wide coverage, minimal curation signal.
A well-regarded collection of rules and knowledge files for Claude Code and Cursor. Archived by its maintainer in 2026; indexed with a…
An early custom-subagent collection for Claude Code, archived by its maintainer in 2025. Indexed with a deprecation warning as format…