agent-skills
claudecodexJoe Black's custom skills for Claude Code — agentic development, multi-provider plugin architecture, Claude Code plugin development, and best practices for working with Claude Code.
42 skills
Garry Tan's gstack AI workflow skills, packaged as a Claude Code plugin with gstack: namespace. 47 skills including ship, review, qa, browse, investigate, office-hours, and more. Fork of garrytan/gstack.
Plugin gstack from marketplace agent-marketplace in joeblackwaslike/agent-marketplace. Commands read from the repo's manifest — 9 days ago.
gstackRouter for the gstack skill suite. (gstack)
autoplanAuto-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)
benchmark-modelsCross-model benchmark for gstack skills. (gstack)
benchmarkPerformance regression detection using the browse daemon. (gstack)
browseFast headless browser for QA testing and site dogfooding. (gstack)
hackernews-frontpageScrape the Hacker News front page (titles, points, comment counts).
canaryPost-deploy canary monitoring. (gstack)
carefulSafety guardrails for destructive commands. (gstack)
codexOpenAI Codex CLI wrapper — three modes. (gstack)
context-restoreRestore working context saved earlier by /context-save. (gstack)
context-saveSave working context. (gstack)
csoChief Security Officer mode. (gstack)
design-consultationDesign consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)
design-htmlDesign finalization: generates production-quality Pretext-native HTML/CSS. (gstack)
design-reviewDesigner's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)
design-shotgunDesign shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. (gstack)
devex-reviewLive developer experience audit. (gstack)
diagramTurn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG. (gstack)
document-generateGenerate missing documentation from scratch for a feature, module, or entire project. (gstack)
document-releasePost-ship documentation update. (gstack)
freezeRestrict file edits to a specific directory for the session. (gstack)
gstack-upgradeUpgrade gstack to the latest version.
guardFull safety mode: destructive command warnings + directory-scoped edits. (gstack)
healthCode quality dashboard. (gstack)
investigateSystematic debugging with root cause investigation. (gstack)
ios-cleanRemove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
ios-design-reviewVisual design audit for iOS apps on real hardware. (gstack)
ios-fixAutonomous iOS bug fixer. (gstack)
ios-qaLive-device iOS QA for SwiftUI apps. (gstack)
ios-syncRegenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
land-and-deployLand and deploy workflow. (gstack)
landing-reportRead-only queue dashboard for workspace-aware ship. (gstack)
learnManage project learnings.
make-pdfTurn any markdown file into a publication-quality PDF. (gstack)
office-hoursYC Office Hours — two modes. (gstack)
open-gstack-browserLaunch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
gstack-openclaw-ceo-reviewUse 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.
gstack-openclaw-investigateUse 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.
gstack-openclaw-office-hoursUse 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.
gstack-openclaw-retroWeekly 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-agentPair a remote AI agent with your browser. (gstack)
plan-ceo-reviewCEO/founder-mode plan review. (gstack)
plan-design-reviewDesigner's eye plan review — interactive, like CEO and Eng review. (gstack)
plan-devex-reviewInteractive developer experience plan review. (gstack)
plan-eng-reviewEng manager-mode plan review. (gstack)
plan-tuneSelf-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)
qa-onlyReport-only QA testing. (gstack)
qaSystematically QA test a web application and fix bugs found. (gstack)
retroWeekly engineering retrospective. (gstack)
reviewPre-landing PR review. (gstack)
scrapePull data from a web page. (gstack)
setup-browser-cookiesImport cookies from your real Chromium browser into the headless browse session. (gstack)
setup-deployConfigure deployment settings for /land-and-deploy.
setup-gbrainSet up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)
shipShip workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack)
skillifyCodify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)
specTurn vague intent into a precise, executable spec in five phases. (gstack)
sync-gbrainKeep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. (gstack)
unfreezeClear the freeze boundary set by /freeze, allowing edits to all directories again. (gstack)
Joe Black's custom skills for Claude Code — agentic development, multi-provider plugin architecture, Claude Code plugin development, and best practices for working with Claude Code.
42 skills
Automatic mistake capture and proactive lesson injection for AI coding agents. Mines conversation logs for mistake patterns, structures them as indexed lessons, and injects relevant warnings before the agent repeats the mistake.
3 skills · 12 commands · 1 MCP server · hooks
Make every Claude Code session discoverable by what was done, asked, and questioned. Indexes transcripts into a sidecar SQLite store with heuristic and LLM-powered synthesis. Includes SessionEnd hook for forward capture and UserPromptSubmit hook for search reminders.
1 skill · 6 commands · hooks
Persistent context graph for codebase and web navigation. Symbol-chunks files, stores nodes in a SQLite graph, and returns compact references — enabling recall across sessions without re-reading files.
3 skills · 1 MCP server · hooks
Scaffold and maintain production-ready TypeScript projects — the cookiecutter-uv equivalent for the TypeScript ecosystem. Includes /new and /update commands plus a skill covering interactive and agent-driven scaffold flows.
1 skill · 2 commands · hooks
Scaffold and maintain production-ready Python projects — uv for dependency management, ruff + mypy for quality, pytest + tox-uv for testing, GitHub Actions CI, and Docusaurus docs. The cookiecutter for modern Python.
2 commands · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.