Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gstack
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
elements, verify page state, diff before/after actions, take annotated screenshots, check
responsive layouts, test forms and uploads, handle dialogs, and assert element states.
~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
user flow, or file a bug with evidence.
gstack also includes development workflow skills. When you notice the user is at
these stages, suggest the appropriate skill:
- Brainstorming a new idea → suggest /office-hours
- Reviewing a plan (strategy) → suggest /plan-ceo-review
- Reviewing a plan (architecture) → suggest /plan-eng-review
- Reviewing a plan (design) → suggest /plan-design-review
- Creating a design system → suggest /design-consultation
- Debugging errors → suggest /investigate
- Testing the app → suggest /qa
- Code review before merge → suggest /review
- Visual design audit → suggest /design-review
- Ready to deploy / create PR → suggest /ship
- Post-ship doc updates → suggest /document-release
- Weekly retrospective → suggest /retro
- Wanting a second opinion or adversarial code review → suggest /codex
- Working with production or live systems → suggest /careful
- Want to scope edits to one module/directory → suggest /freeze
- Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard
- Removing edit restrictions → suggest /unfreeze
- Upgrading gstack to latest version → suggest /gstack-upgrade
If the user pushes back on skill suggestions ("stop suggesting things",
"I don't need suggestions", "too aggressive"):
1. Stop suggesting for the rest of this session
2. Run: gstack-config set proactive false
3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive
again if you change your mind."
If the user says "be proactive again" or "turn on suggestions":
1. Run: gstack-config set proactive true
2. Say: "Proactive suggestions are back on."
majiayu000/claude-skill-registry 163
-
Appropriate Reliance Skill (v2.0)
Calibrated human-AI collaboration with creative latitude — trust calibrated to reliability, creativity preserved with validation.
majiayu000/claude-skill-registry 163
-
af-canvas-expertise
Use when presenting content to the user visually via the Agentview canvas.
Covers writing markdown, mermaid diagrams, HTML, and Excalidraw drawings to
task-scoped canvases. Use this when the user asks to "show me" something,
explain with a diagram, or display a file in the canvas.
majiayu000/claude-skill-registry 163
-
tailwind-4
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind - cn(), theme variables, no var() in className.
majiayu000/claude-skill-registry 163
-
container-ops
Docker 容器操作与管理
majiayu000/claude-skill-registry 163
-
mcp-management
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.
majiayu000/claude-skill-registry 163
-
riverpod-select
Reduce rebuilds with ref.watch(provider.select(...)); select a subset of state so widgets rebuild only when that part changes. Use when optimizing performance or when a widget uses only one field of a large object. Use this skill when the user asks about select, reducing rebuilds, or optimizing Riverpod watch.
majiayu000/claude-skill-registry 163
-
regression-analysis-helper
Regression Analysis Helper - Auto-activating skill for Data Analytics.
Triggers on: regression analysis helper, regression analysis helper
Part of the Data Analytics skill category.
majiayu000/claude-skill-registry 163
-
build-fix
Run the build and intelligently fix errors with guardrails. Stops if fixes introduce more errors or the same error persists after 3 attempts.
majiayu000/claude-skill-registry 163
-
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
majiayu000/claude-skill-registry 163
-
marketing-ideas
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category.
majiayu000/claude-skill-registry 163
-
text_based_beat_em_up_rpg
Simulates a side-scrolling beat 'em up RPG where the user navigates levels and fights enemies using stats (HP, Power, Defense, Speed). Tracks health, calculates combat outcomes based on move success chances, and presents choices with hidden outcomes and varying favorability.
majiayu000/claude-skill-registry 163
-
deploying-applications
Deployment patterns from Kubernetes to serverless and edge functions. Use when deploying applications, setting up CI/CD, or managing infrastructure. Covers Kubernetes (Helm, ArgoCD), serverless (Vercel, Lambda), edge (Cloudflare Workers, Deno), IaC (Pulumi, OpenTofu, SST), and GitOps patterns.
majiayu000/claude-skill-registry 163
-
gtm-motions
Identify the best GTM motions and tools across 7 motion types: Inbound, Outbound, Paid Digital, Community, Partners, ABM, and PLG. Use when selecting marketing channels, choosing between inbound and outbound strategy, or planning cross-channel campaigns.
majiayu000/claude-skill-registry 163
-
reactive-dashboard-performance
Expert in building blazing-fast reactive dashboards with comprehensive testing. Masters React performance patterns, testing strategies for async components, and real-world patterns from Linear, Vercel, Notion.
majiayu000/claude-skill-registry 163
-
deep-interview
Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One question per message, weighted ambiguity scoring, brownfield-aware, outputs a complete PRD. Replaces discovery-interview with a stricter protocol.
majiayu000/claude-skill-registry 163
-
add-playlist-tracks
Add and remove tracks from playlists with position management and validation (project)
majiayu000/claude-skill-registry 163
-
sokosumi
Hire AI agents from the Sokosumi marketplace to perform tasks.
majiayu000/claude-skill-registry 163
-
context-engineering
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
majiayu000/claude-skill-registry 163
-
context-engineering
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
majiayu000/claude-skill-registry 163
-
fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
majiayu000/claude-skill-registry 163
-
ln-403-task-rework
Fixes tasks in To Rework by applying reviewer feedback, then returns to To Review. Use when task was rejected during review.
majiayu000/claude-skill-registry 163
-
process-issues
Execute recipe sessions batch-by-batch for triaged GitHub issues. Reads the triage-issues output manifest, processes each batch sequentially, and launches the appropriate recipe for each issue. Use when user says "process issues", "run issues", or "execute pipeline for issues".
majiayu000/claude-skill-registry 163
-
card-news-generator-v2
Create 600x600 Instagram-style card news series automatically with optional background images. User provides topic, colors, and optional images - Claude generates content and creates multiple cards with proper text wrapping.
majiayu000/claude-skill-registry 163