The Index
Every entry verified live, scored against the public rubric, and timestamped. Sorted by overall score, never by stars.
13 of 46 entries
A large library of named, reusable prompt patterns with a CLI for piping content through them. Prompt-layer infrastructure: patterns without…
OpenAI's original eval framework and benchmark registry. Historically foundational; maintenance has visibly slowed as evaluation moved into…
A security toolkit for LLM interactions: scanners for prompt injection, PII, toxicity, and secrets, applied to inputs and outputs.
A configuration framework layering specialized commands and cognitive personas onto Claude Code: an opinionated operating mode rather than a…
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 hand-picked aggregator of Claude Code resources: skills, commands, CLAUDE.md files, and tooling. More curation voice than most lists, same…
The largest MCP server aggregator: thousands of community servers organized by category. A discovery surface for the tool layer, with…
A structured slash-command set for Claude Code covering development workflows: review, test, deploy, and project-management commands with…
The largest collection of Cursor rules files, organized by framework and stack. A discovery source for instruction-file patterns rather than…
A 1000+ entry aggregator of agent skills across Claude Code, Codex, Gemini CLI, and Cursor. Wide coverage, minimal curation signal.
A curated collection of Cursor rules in the modern .mdc format, organized by library and framework. The .mdc counterpart to the older…