Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
context-fundamentals
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
guanyang/antigravity-skills 617
-
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
guanyang/antigravity-skills 617
-
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
guanyang/antigravity-skills 617
-
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
guanyang/antigravity-skills 617
-
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
guanyang/antigravity-skills 617
-
debug
Structured bug diagnosis and fixing workflow — reproduce, diagnose root cause, apply minimal fix, write regression test, and scan for similar patterns
first-fluke/fullstack-starter 208
-
design
Design workflow — create design systems, DESIGN.md, and design tokens with anti-pattern enforcement and accessibility checks
first-fluke/fullstack-starter 208
-
tools
Manage MCP tools with natural language commands — list, enable, disable tools and tool groups
first-fluke/fullstack-starter 208
-
deepinit
Initialize project harness — AGENTS.md as table of contents, ARCHITECTURE.md as domain map, structured docs/ knowledge base
first-fluke/fullstack-starter 208
-
review
Full QA review pipeline — security audit (OWASP Top 10), performance analysis, accessibility check (WCAG 2.1 AA), and code quality review
first-fluke/fullstack-starter 208
-
coordinate
Coordinate multiple agents for a complex multi-domain project using PM planning, parallel agent spawning, and QA review
first-fluke/fullstack-starter 208
-
pdf
Convert PDF to Markdown using opendataloader-pdf — extracts text, tables, headings, and images with correct reading order
first-fluke/fullstack-starter 208
-
ralph
Ralph - persistent self-referential execution loop wrapping ultrawork with independent verifier verification
first-fluke/fullstack-starter 208
-
setup
oh-my-agent project setup verification and configuration
first-fluke/fullstack-starter 208
-
orchestrate
Automated CLI-based parallel agent execution — spawn subagents via Gemini CLI, coordinate through MCP Memory, monitor progress, and run verification
first-fluke/fullstack-starter 208
-
ultrawork
Ultrawork - high-quality 5-phase development workflow with 11 review steps out of 17
first-fluke/fullstack-starter 208
-
stack-set
Auto-detect project tech stack and generate stack-specific references for domain skills
first-fluke/fullstack-starter 208
-
brainstorm
Design-first ideation workflow — explore user intent, clarify constraints, propose approaches, and produce an approved design document before planning
first-fluke/fullstack-starter 208
-
plan
PM planning workflow — analyze requirements, select tech stack, decompose into prioritized tasks with dependencies, and define API contracts
first-fluke/fullstack-starter 208
-
exec-plan
Create, manage, and track execution plans as first-class repository artifacts in docs/exec-plans/
first-fluke/fullstack-starter 208
-
ccs-delegation
Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.
kaitranntt/ccs 1,941
-
oma-mobile
Mobile specialist for Flutter, React Native, and cross-platform mobile development. Use for mobile app, Flutter, Dart, iOS, Android, Riverpod, and widget work.
first-fluke/fullstack-starter 208
-
oma-frontend
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.
first-fluke/fullstack-starter 208
-
oma-backend
Backend specialist for APIs, databases, authentication with clean architecture (Repository/Service/Router pattern). Use for API, endpoint, REST, database, server, migration, and auth work.
first-fluke/fullstack-starter 208