A set of workflow skills where you state the goal and it picks the routine: for a bug it reproduces the failure, finds the cause, has the fix made, then reruns the failing case to show it now passes.
In short: A set of workflow skills where you state the goal and it picks the routine: for a bug it reproduces the failure, finds the cause, has the fix made, then reruns the failing case to show it now passes. It is a free skill for people who use Claude Code, Codex or Gemini and want help with coding agent skills.
Checked on · Added
| Agent / tool | Access / cost | Link |
|---|---|---|
| Claude Code | Paid Claude plan or API | claude.com/claude-code |
| Codex | ChatGPT plan or API | openai.com/codex |
| Gemini | Free tier + paid | gemini.google.com |
| GitHub repo | Open source · ★ 3.3k | michael-denyer/pstack-claude |
Image: from the GitHub README, shown with credit.
/plugin marketplace add michael-denyer/pstack-claude /plugin install pstack@pstack-claude codex plugin marketplace add michael-denyer/pstack-claude
Install command copied from the project README. Check the README for the latest version.
A set of workflow skills where you state the goal and it picks the routine: for a bug it reproduces the failure, finds the cause, has the fix made, then reruns the failing case to show it now passes.
Lauren Tan's pstack is an opinionated Cursor skill stack that improves agent outcomes. This is a port for Claude Code, Codex, Pi, GitHub Copilot, Muse, and other agent harnesses. It tracks upstream and also carries…
Short excerpt from the README of michael-denyer/pstack-claude. Read the full README on GitHub.
A community port of the pstack skills that Cursor published for its own editor; it tracks the original but is kept by a different maintainer. A start-up hook points every session at it; switch that off with setup-pstack if you only want it on request. Some routines hand work to extra sub-agents, so expect more token use. Narrower than gstack or ECC: its focus is proving each change works.
A set of workflow skills where you state the goal and it picks the routine: for a bug it reproduces the failure, finds the cause, has the fix made, then reruns the failing case to show it now passes.
It works with Claude Code, Codex and Gemini. The code is on GitHub at michael-denyer/pstack-claude.
Free & open source (MIT). Runs on your agent's own model; no server or telemetry, per the README.
Run the install command from the README: “/plugin marketplace add michael-denyer/pstack-claude”. Check the README on GitHub for the latest version, then follow the steps on this page.
We read 268 instruction and code files in the repo and found no red flags. That is not a guarantee, so review anything that runs commands on your machine.
All credit to the original authors. We rewrite in our own words and link back. Something wrong? Report it.
SKILLYour coding agent connects to an Android or Google TV over Wi-Fi, switches off the ad and tracking apps, and puts in a clean, Apple TV-style home screen. Nothing is uninstalled.
Claude Code +2★ 14.8k
SKILLOne install gives your agent a plan, test, build, review and remember routine, with 71 helper agents, about 300 skills, memory between sessions and a built-in scanner for risky agent settings.
Claude Code +3★ 285.3k
SKILLA skills framework that makes agents brainstorm, plan, test and debug systematically.
Claude Code +1★ 299.2k
SKILLReal engineering skills from a well-known TypeScript educator's own .agents folder.
Claude Code +1★ 291.4k
SKILLA skill that pushes coding agents to act like a lazy senior: fewer lines, more tests, lower cost — without skipping the hard checks.
Claude Code +2★ 164.8k
SKILLSpecialist agent personas for engineering, design, marketing, sales and support you can drop into Claude Code, Codex or Cursor.
Claude Code +2★ 160.4kFree newsletter
New AI tools you can use right away, in plain words. Every Friday.