Agent skills

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

Latest Most Popular

review-package Create a self-contained review package of current work for external review by another AI model or human reviewer. Bundles relevant files with a contextual README and instructional prompt. Triggers: "review package", "create review package", "hand off for review", "get a second opinion", "external code review", "cross-model review", "package for review", "prepare code review". Accepts an optional focus area argument to scope the analysis.
petekp/claude-code-setup 20
explanatory-playground Build interactive, source-linked explanatory artifacts that help someone understand a real codebase or subsystem through narrative, runtime evidence, and focused visualizations. Use when the user wants to understand how a system works, create an interactive codebase guide, build a literate walkthrough, reveal hidden state or data flow, or turn opaque code into a grounded explorable artifact. Best for request lifecycles, state machines, data pipelines, render/update behavior, event systems, algorithms, and async workflows where static code reading alone is not enough.
petekp/claude-code-setup 20
agent-telemetry Make application behavior visible to coding agents by exposing structured logs and telemetry. Use when asked to "add telemetry", "make logs accessible to agents", "add observability", "debug with logs", or when an agent needs to understand runtime behavior but has no way to query logs. Also use when debugging is difficult because there are no structured logs, when agent docs (CLAUDE.md, AGENTS.md) lack instructions for querying application logs, or when setting up logging infrastructure for a new or existing web application.
petekp/claude-code-setup 20
browser-use Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
petekp/claude-code-setup 20
frontend-design Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
petekp/claude-code-setup 20
unix-macos-engineer Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
petekp/claude-code-setup 20
method:autonomous-ratchet Autonomous-only artifact-centric method for overnight quality improvement runs on an existing codebase. 17 steps across 6 phases: Triage -> Stabilize -> Envision -> Plan -> Execute -> Finalize. Use when asked to run this overnight, improve while I sleep, ratchet quality autonomously, or do an autonomous quality pass. Do not use for interactive steering, greenfield feature work, architecture decisions, cleanup-only sweeps, one-off fixes, or repos without explicit build/test/verify commands.
petekp/claude-code-setup 20
audit-and-migrate Slice-based, evidence-driven framework for auditing and migrating debt-heavy codebases. Use for large refactors, codebase consolidation, tech debt paydown, dependency standardization, architecture cleanup, or any multi-session migration. Also use when asked to audit the codebase, migrate from X to Y, standardize on one approach, consolidate duplicated code, or run a systematic refactor with built-in cleanup, residue sweeps, and a final ship-readiness gate. Make sure to use this skill whenever the user wants a controlled migration with slices, guardrails, handoffs, cleanup, or release closeout, even if they do not explicitly say "migration". Mentions of ratchets, slices, migration playbooks, anti-vestigial discipline, convergence, or release cleanup should strongly trigger it.
petekp/claude-code-setup 20
architecture-exploration Explore and compare architectural options before committing to a large technical direction. Use when the user wants to evaluate different architectures, compare approaches, choose between competing designs, rethink a subsystem, or understand tradeoffs before a major refactor or migration. Also use for prompts like "explore the architecture", "what are our options", "compare approaches", "what design should we choose", "audit and recommend an improved architecture", or "help me think through a large architectural change" even if the user does not mention a formal architecture review.
petekp/claude-code-setup 20
handoff Generate a resume-ready handoff prompt that lets another session or agent continue work without rediscovering context. Use when the user asks for a handoff, bootstrap prompt, session summary, save-state prompt, or wants to continue later in a fresh session, another model, or a different environment. Also use when context is getting full and the current goal, repo state, decisions, verification status, blockers, and exact next actions must be preserved in a compact prompt.
petekp/claude-code-setup 20
swiftui-expert-skill Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
petekp/claude-code-setup 20
find-skills Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
petekp/claude-code-setup 20
solution-explorer Exhaustively explore a problem and solution space before implementing a feature or making an architectural decision. Use when asked to implement a feature, design a system, choose between approaches, or any time there are multiple valid ways to solve a problem. Forces systematic exploration of alternatives to find the global optimum instead of settling on the first reasonable idea. Use this skill whenever the user says things like "implement X", "how should we build", "best way to", "design", "architect", "add a feature for", or describes a non-trivial feature they want built. Even if the user doesn't explicitly ask for exploration, use this skill when you recognize that the implementation has multiple viable paradigms worth comparing.
petekp/claude-code-setup 20
proposal-review Facilitate methodical review of proposals (technical designs, product specs, feature requests). Use when asked to "review this proposal", "give feedback on this doc", "help me review this RFC", or when presented with a document that needs structured feedback. Handles markdown files, GitHub gists/issues/PRs, and other text formats. Chunks proposals intelligently, predicts reviewer reactions, and produces feedback adapted to the proposal's format.
petekp/claude-code-setup 20
agent-browser Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
petekp/claude-code-setup 20
method:flow-audit-and-repair Forensic debugging workflow for broken end-to-end flows. 8 steps across 5 phases: Failure Framing → Forensics → Repair Design → Layered Repair → Reaudit. Use when an existing flow is broken, flaky, or operationally unsafe and the team needs a path from observed failure to verified repair — not for greenfield features or speculative design work.
petekp/claude-code-setup 20
product-design Expert product design knowledge for software interfaces — 451 practices across 25 categories, each with tags, priority (core/situational/niche), and applies_when metadata for precise retrieval. Use this skill whenever the user is designing, reviewing, building, or discussing any part of a software interface. This includes: building forms or input flows, designing dashboards or data tables, choosing UI components (modals vs. sidebars, tabs vs. accordions, toggles vs. checkboxes), planning navigation or information architecture, handling errors and feedback, designing onboarding or empty states, building enterprise/B2B admin panels, creating design systems, implementing accessibility, optimizing perceived performance, designing search/filter/sort, building multi-step workflows or wizards, or reviewing existing designs for usability issues. Also trigger when the user asks about design best practices, UX heuristics, cognitive load, Gestalt principles, Fitts's Law, Hick's Law, or any named design principle. Even if the user doesn't explicitly say "design" — if they're building UI and making layout, component, or interaction decisions, this skill applies.
petekp/claude-code-setup 20
clean-architecture Clean Architecture principles and best practices from Robert C. Martin's book. This skill should be used when designing software systems, reviewing code structure, or refactoring applications to achieve better separation of concerns. Triggers on tasks involving layers, boundaries, dependency direction, entities, use cases, or system architecture.
petekp/claude-code-setup 20
pi-delegate Delegate tasks to Pi subagents with preset roles (oracle, worker, reviewer, ui-engineer, librarian) or ad-hoc prompts. Use for fresh context, model specialization, second opinions, code review, isolated execution, or parallel task delegation.
vaayne/agent-kit 33
mcp-jetbrains-ide Control JetBrains IDE (IntelliJ, WebStorm, PyCharm) via MCP. Use when manipulating IDE files, running configurations, searching code, or performing refactoring. Triggers on "open in IDE", "run configuration", "refactor code", "IDE search", "JetBrains".
vaayne/agent-kit 33
mcp-context7-docs Query up-to-date documentation and code examples for any programming library or framework. Use when looking up API docs, finding code examples, or checking library usage. Triggers on "how to use [library]", "docs for [package]", "show me examples of [framework]", "Context7 lookup".
vaayne/agent-kit 33
web-fetch Fetch and extract clean content from URLs using Jina Reader API. Use when users need to read webpage content, extract article text, or fetch URL content for analysis. Triggers on "fetch this page", "read this URL", "extract content from", "get the content of", "what does this page say".
vaayne/agent-kit 33
tmux Control interactive terminal sessions via tmux. Use when tasks need persistent REPLs, parallel CLI agents, or any process requiring a TTY that simple shell execution cannot handle.
vaayne/agent-kit 33
specs-dev Plan-first development workflow with review gates. Use when implementing features, refactoring, or any task requiring structured planning, iterative implementation with reviews, and clean commits. Triggers on requests like "implement feature X", "plan and build", "spec-driven development", or when user wants disciplined, reviewed code changes.
vaayne/agent-kit 33