Prompt-driven capabilities that teach an agent new workflows. Every skill here is evaluated before it is listed.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Evidence before assertions, always
Turn specs into phased implementation plans
Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.
Red → green → refactor discipline for any feature or bugfix
Reproduce, isolate, diagnose — don't guess
Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Clear the freeze boundary set by /freeze, allowing edits to all directories again. (gstack)
Scrape the Hacker News front page (titles, points, comment counts).
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Import cookies from your real Chromium browser into the headless browse session. (gstack)
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)
Triage a Playwright bug report by reproducing it from the information in the issue. Use when asked to triage, reproduce, or verify a GitHub issue (a new bug report, or an existing report with a new comment).
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)
Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack)
Query Playwright CI test results from the aggregated DuckDB database. Answers questions about flaky tests, failure rates, slow tests, and per-run/SHA/PR results without hunting through GitHub artifacts.
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
Turn vague intent into a precise, executable spec in five phases. (gstack)
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware with per-person contributions, praise, and growth areas. Use when asked for weekly retro, what shipped this week, or engineering retrospective.
Pair a remote AI agent with your browser. (gstack)
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Systematically QA test a web application and fix bugs found. (gstack)
Designer's eye plan review — interactive, like CEO and Eng review. (gstack)
🎨 Local-first, open-source Claude Design alternative.
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
🎨 Local-first, open-source Claude Design alternative.
Turn any markdown file into a publication-quality PDF. (gstack)
Visual design audit for iOS apps on real hardware. (gstack)
🎨 Local-first, open-source Claude Design alternative.
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)
Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. (gstack)
Generate missing documentation from scratch for a feature, module, or entire project. (gstack)
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
Live developer experience audit. (gstack)
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)
Restrict file edits to a specific directory for the session. (gstack)
Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)
Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open (gstack)
Fast headless browser for QA testing and site dogfooding. (gstack)
Performance regression detection using the browse daemon. (gstack)
OpenAI Codex CLI wrapper — three modes. (gstack)
Safety guardrails for destructive commands. (gstack)
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)
Fast headless browser for QA testing and site dogfooding. (gstack)