Skills & Prompts

agentcanon

One canonical home for all your agent skills and instructions.

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent-facing English.

Better Tropes

A catalogue of 49 AI writing tells, each with a plain rewrite, shared by Fireside. Drop it into a system prompt to stop LLM output reading like LLM output.

A minimal, better version of gstack — two skills that change what you build, and nothing else.

Caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

A Claude Code plugin that shows a plain-English rewrite of each assistant message, produced by a local LLM via ollama (default), the Anthropic API, or any OpenAI-compatible API. It is display-only: Claude's own reasoning and the saved transcript keep the original text — only what you read on screen changes.

Compound Engineering

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

error-discovery-skill

Interactive error analysis skill for AI agents. Studies LLM trace datasets, builds a review UI, monitors annotations, categorizes failure modes, proposes new samples.

GEPA

Optimize any text — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. If you can measure it, you can optimize it.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

guides.show

Agent skill: write a Guided Review of a diff and export it as a portable HTML file (plannotator guide export)

Hallmark

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

Claude Code skill to stop it from burying the answer. ADHD-friendly output.

Impeccable

1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, GitHub Copilot, Gemini CLI, and Codex CLI.

Instructa Agent Skills

A curated collection of agent-skills

Claude Code skill: an unattended nightly loop that turns Linear tickets into reviewed PRs

MagicPath Agent Skills

Agent Skills for MagicPath, packaged for the open Agent Skills ecosystem and installable with Vercel's skills CLI or as a Claude Code, Codex, or Cursor plugin. In Cursor, install the plugin from the Cursor marketplace, or run the following from inside a Cursor session: In Claude Code, add this repo as a marketplace and install the plugin: In Codex (CLI, app, or VS Code extension), add this repo as

OpenMausBot Teams

Community team templates and skill playbooks for OpenMausBot

Pilcrow

Turn the LLM in your harness into the editor it should be.

Ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

pstack

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

Claude Code port of poteto's pstack (cursor/plugins/pstack). Rigorous agent workflows with Cursor primitives translated to their Claude Code equivalents.

Quiver (qvr)

quiver (qvr): open-source git-native package manager for agent skills — lockfile-first, registry-agnostic, and built for reproducible AI agent workflows.

Recursive workflow for agentic engineering. Like Factory Missions but properly recursive, free and open source.

SEO Skill

The only SEO skill your agent needs. 70+ SEO audit tools through a local CLI and MCP server, using your own crawl, Search Console, and GA4 data.

Skill Cabinet

A local catalog for agent skills installed on your machine.

skill-issue

Reusable AI skills and prompts powering Crown Dev Studios' agent workflows

skilld

Generate AI agent skills from your NPM / create dependencies. npx skilld

SkillDeck

Native macOS SwiftUI app for managing multiple AI code agent skills

Skills for Real Engineers. Straight from my .claude directory.

Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Cursor, or Gemini from any compatible tool.

Agent skills for Claude Code and other AI agents

ui.sh

A collection of expertly crafted, task-oriented prompts and workflows for building UIs that don't suck.

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

variate

A compact design skill that generates four design variations of a component to iterate better on your UIs. A skill for Claude Code, Codex CLI, and opencode.

watchmen

Watchmen turns every coding session into the skill bundles you’d never sit down and write yourself.