Agent skills

Skills you can use with AI coding agents, indexed from public GitHub repositories.

Latest Most Popular

method:janitor Artifact-centric method for systematic codebase cleanup — dead code, stale docs, orphaned artifacts, vestigial comments, and redundant abstractions. 8 steps across 5 phases: Survey -> Triage -> Prove -> Clean -> Verify. Dual-mode: interactive (user checkpoints) or autonomous (evidence-gated with deferred review). Use when asked to clean up dead code, do a janitor sweep, improve context hygiene for agents, remove stale docs, or find and remove unused code. Do not use for refactoring with behavior changes, architecture decisions, feature work, one-off deletions, dependency upgrades, or formatting cleanup.
petekp/claude-code-setup 20
research-prompt Craft a high-quality prompt for a deep research agent (like ChatGPT Deep Research) through adaptive interviewing. Use when the user wants to research something but needs help formulating what to ask — when they say "I need to research X", "help me figure out what to ask about Y", "write a research prompt for Z", "I want to use deep research on...", or when they have a vague research need and want a precise, comprehensive prompt that will get excellent results from a research agent. Also use when the user mentions deep research, ChatGPT research, or preparing a query for an AI research tool.
petekp/claude-code-setup 20
seam-ripper Ruthlessly analyze architectural seams—the interfaces, boundaries, and contracts between system components—to expose coupling problems, abstraction leaks, and design failures. Use when asked to review architecture, analyze coupling, find interface problems, improve module boundaries, audit dependencies, or redesign system structure. Produces uncompromising redesign proposals that prioritize correctness over backwards compatibility.
petekp/claude-code-setup 20
deep-research Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, documentation APIs, and codebase exploration. Use when asked to "research X", "find out about Y", "investigate Z", "deep dive into...", "what's the current state of...", "compare options for...", "fact-check this...", or any request requiring comprehensive, accurate information from multiple sources. Prioritizes accuracy over speed, cross-references claims across sources, identifies conflicts, and provides full citations. Outputs structured findings with confidence levels and source quality assessments.
petekp/claude-code-setup 20
pipeline Modular development pipeline orchestrator. Use for "/pipeline", "pipeline init", "pipeline resume", "pipeline status", or phased triage → align → execute workflows.
petekp/claude-code-setup 20
vercel-react-best-practices React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
petekp/claude-code-setup 20
dead-code-sweep This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up unused code", "remove redundant code", "prune this codebase", "dead code sweep", "code cleanup", or when a codebase has gone through multiple agent-driven refactors and likely contains overlooked remnants. Systematically identifies cruft, categorizes findings, and removes confirmed dead code with user approval.
petekp/claude-code-setup 20
improve-codebase-architecture Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
petekp/claude-code-setup 20
method:create Codex-powered compiler for turning a natural-language workflow description into a method skill that matches the live corpus. 5 phases: Intake -> Analysis -> Authoring -> Validation -> Refinement. Codex workers handle analysis, file generation, and quality gate; Claude does intake and a final refinement pass optimized for Claude Code. Use when you want to create a method, compile a method, author a method skill, or turn this workflow into a method. Not for editing existing methods, not a runtime engine, and not for one-off prompts.
petekp/claude-code-setup 20
method:router Routes `/method:router` requests to the best-fit method skill among the 7 methods. Not a method itself. Use for `/method:router` or `/method:router <args>` when choosing which method to start.
petekp/claude-code-setup 20
deepwiki Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.
petekp/claude-code-setup 20
prd-to-issues Break a PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.
petekp/claude-code-setup 20
architecture-scaffold Build a compilable type-level skeleton from a high-level architecture spec before writing any implementation logic. Use when you have an architectural assessment, design doc, or restructuring plan and need to prove the new architecture is sound before migrating code. Also use when asked to "scaffold the new architecture", "create type stubs", "build the shell", "flesh out this spec", "skeleton the modules", or any request to turn architectural intent into verified structure. This skill follows the "Human Builds the Shell" paradigm: types are hard constraints that the compiler enforces, so if the skeleton compiles, the architecture is structurally sound. Especially valuable for large refactors where you don't trust agents to maintain coherence.
petekp/claude-code-setup 20
formal-verify Continuous formal verification of architectural constraints and code quality. Use when asked to verify, audit, or validate codebase integrity. Runs automatically via hooks on every edit (structural) and pre-commit (full). Catches ownership violations, boundary crossings, state machine bugs, and code smells that grep ratchets miss. Triggers: "verify", "formal verify", "check architecture", "audit code quality", "run verification", "/verify", "/verify --bootstrap", "/verify --grade".
petekp/claude-code-setup 20
write-a-prd Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
petekp/claude-code-setup 20
agentation Add Agentation visual feedback toolbar to a Next.js project
petekp/claude-code-setup 20
skill-manager Manage, audit, and maintain your skill ecosystem. Use when the user asks to "check my skills", "audit skills", "find duplicate skills", "which skills am I using", "prune unused skills", "are my skills synced", "check for skill updates", "skill report", "skill health", or mentions skill maintenance, cleanup, or organization.
petekp/claude-code-setup 20
grill-me Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
petekp/claude-code-setup 20
claude-md-author This skill should be used when the user asks to "create a CLAUDE.md", "write a CLAUDE.md", "set up CLAUDE.md", "configure Claude for this project", "add project instructions for Claude", "initialize Claude context", or mentions needing project-specific Claude instructions.
petekp/claude-code-setup 20
agent-native-architecture Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
petekp/claude-code-setup 20
typography Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure, typographic hierarchy, variable fonts, font loading, or OpenType features.
petekp/claude-code-setup 20
ai-sdk Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
petekp/claude-code-setup 20
method:spec-hardening Artifact-driven method for turning a rough RFC, design spec, PRD, or method schema into a canonical amended spec, a build-ready execution packet, and a reviewed implementation plan without crossing into code. 10 steps across 6 phases: Intake -> Multi-Angle Review -> Amendment -> Contracting -> Planning -> Validation. Use when an existing draft exists but is not yet safe to build from.
petekp/claude-code-setup 20
manual-testing Guide users through targeted manual verification after code changes. Use when asked to "test this", "verify it works", "QA this", "walk me through testing", "smoke test", "sanity check", "regression test", "acceptance test", or after implementing a feature or bug fix that still needs human validation. Favor this skill for focused verification of the current change; use a broader exploratory-testing skill for open-ended bug hunting across an entire app.
petekp/claude-code-setup 20