🎯Skills60
A UX/UI design specification skill that produces implementation-ready specs including user flows, component briefs, design tokens, accessibility constraints, and handoff guidance for frontend engineering agents.
An AI agent skill that estimates the development cost of a codebase, branch diff, or single commit by combining repo metrics, category-based productivity rates, organizational overhead, and optional Claude ROI analysis using helper scripts for LOC counting, git session analysis, and cost calculation.
A fast browser and native app automation skill for AI coding agents, providing persistent headless Chromium for web tasks and accessibility-API-based automation for Android, iOS, and macOS apps — supporting URL navigation, element interaction, form filling, JavaScript execution, and screenshots at ~100ms per command.
Filament v5 admin panel reference skill covering resources, forms, tables, actions, filters, relation managers, widgets, panels, and testing patterns with v5 namespace and API conventions.
A safe git merge workflow skill that handles branch merges, PR merges, conflict resolution, validation, rollback, and branch cleanup, with built-in readiness checks and worktree isolation for risky merges.
Scans the codebase and updates project memory files such as CLAUDE.md and imported reference docs with real project-specific routes, exports, flows, and implementation guidance.
A bug-finding skill that reviews branch diffs for real bugs and security issues, verifies each finding against surrounding code context, and produces a prioritized report of confirmed defects and vulnerabilities.
A skill that reviews implementation plans before execution, verifying markdown/JSON consistency, challenging scope and architecture, checking file paths against the codebase, auditing risk and test gaps, and delivering APPROVE/REVISE/REJECT verdicts. Runs as a forked review workflow with separate reasoning budget.
A skill that simplifies existing code without changing behavior by flattening nesting, extracting readable helpers, removing dead code, consolidating duplication, and improving naming, with built-in baseline verification to ensure correctness.
A structured bugfix skill that enforces a reproduce-diagnose-fix-verify loop with framework-specific references and category-based playbooks, supporting 15+ frameworks (React, Next.js, Express, Go, Rust, Laravel, etc.) to fix confirmed defects with minimal, root-cause-targeted changes.
Creates safe implementation plans as both Markdown and JSON DAG artifacts. Challenges scope with the user, explores real code before decomposing, then emits atomic TASK entries with explicit dependencies, write scope, validation, and assigned agents.
A maintenance skill that extracts validated learnings about Claude Code behavior from the current session and persists them to the project's CLAUDE.md memory file for future reference.
Extracts validated learnings from the current session, stores them in a central agent learnings file, and syncs the resulting Learnings section into agent definitions used by supported CLIs.
Provides architecture-aware code analysis using the codemap CLI, including semantic search, symbol lookup, dependency tracing, file summaries, importance ranking, coupling metrics, and circular dependency detection.
A git workflow skill that creates commits from the current working tree by reading diffs, scanning for obvious blockers, running relevant checks, staging explicit files, and verifying the result.
A maintenance skill that extracts validated learnings about skill design patterns and quality from the current session, persisting them to a central skill learnings file for ongoing improvement.
Pre-landing diff review against the default branch that catches structural defects tests often miss: unsafe queries, race conditions, trust-boundary mistakes, conditional side effects, and similar branch risks.
Performs git merge operations in isolated worktrees for safe conflict resolution and validation, with proper worktree lifecycle management including creation, merge execution, result validation, and cleanup.
Maintenance skill that scans a Cargo workspace or package monorepo and refreshes per-member CLAUDE.md files plus a root CLAUDE.md. Keeps workspace-local AI context accurate after refactors, member additions, or architectural changes.
A GitHub pull request creation skill that validates branch readiness, reads the real diff, drafts a precise title and body, pushes the branch, and verifies the created PR with built-in guardrails against protected branches and conflict markers.
An internal conversation-entry router skill for Claude Code that performs lightweight intake at the start of tasks, deciding whether a more specific skill should be invoked, whether agent delegation is needed, and how much context is required.
Analyzes the current feature branch against its base branch, computes branch-health metrics, scans for common pre-PR issues, and delivers a merge-readiness verdict with an optional JSON snapshot.
A skill that runs the Kiro CLI as an independent code reviewer over a branch, specific commit, or uncommitted changes. It builds a focused prompt from the actual diff and returns a structured review summary with targeted findings.
A Claude Code skill that orchestrates multiple debugging agents in parallel when there are 3 or more independent failures with disjoint root causes, using isolated worktrees and background execution.
Performs structural code search using AST patterns via the ast-grep CLI, useful when grep or ripgrep cannot reliably express syntax-based queries like finding async functions without try/catch.
A skill for discovering, installing, listing, removing, updating, and scaffolding AI agents using the agentshq CLI, supporting multiple coding CLIs and IDEs with both project-level and global scope management.
A skill that manages encrypted local credentials for agent tooling through a secrets CLI, supporting operations like adding, rotating, listing, enabling, and disabling service integrations without exposing secret values in agent output.
A skill that launches an isolated Claude reviewer for the current branch, a specific commit, or uncommitted changes. Uses worktree isolation to provide a read-only view of the code and returns actionable findings without modifying any files.
A skill that orchestrates multiple code-writing agents in parallel when the work contains three or more independent build tasks, verifying independence before launching and using isolated worktrees to prevent file conflicts.
A Node.js and Bun backend reference skill that enforces TypeScript-first conventions including structured error handling with pino logging, Zod validation, async patterns, HTTP server setup, database access, auth, queues, caching, testing, and observability.
A skill that runs OpenAI Codex CLI as an independent code reviewer over the current branch, a specific commit, or uncommitted changes, building focused review instructions from the real diff and returning a compact, structured review summary.
A comprehensive skill collection for AI coding agents featuring headless browser automation, stealth browsing, SEO/AEO/GEO audits, code search with architecture analysis, task DAG planning, and bug-fixing workflows.
A Laravel backend reference skill that enforces thin controllers, Form Request validation, Action-driven business logic, API Resources, strict Eloquent mode, and proper queue and caching patterns.
A QA skill that tests web or app features from tickets, URLs, or acceptance criteria, executing scenarios through browser interaction, capturing evidence, and generating reusable regression flows with structured QA reports.
A skill that automates building distributable DMG files for macOS Xcode projects, handling code signing, provisioning, and export options through a helper script.
A skill for running local web and app development behind named HTTPS .test domains using lokei, with support for tunnel sharing, framework-aware dev-server startup, and Docker Compose HTTPS orchestration.
A Rust systems-programming reference skill that provides conventions for storage engines, binary formats, Arrow/DataFusion, vector search, async concurrency with tokio, and strict unsafe discipline with per-crate error types.
A Next.js App Router reference skill that routes tasks through project-specific conventions for pages, layouts, server actions, metadata, i18n, caching, accessibility, analytics, and testing, using progressive reference loading from a stack contract.
A NestJS reference skill providing comprehensive guidance on modules, controllers, providers, DTOs with class-validator, TypeORM/Prisma integration, guards, interceptors, pipes, BullMQ queues, WebSockets, microservices, testing, and OpenAPI documentation.
Converts local agent skills into a Claude Code optimized shape. Audits a SKILL.md against Claude Code runtime behavior, creates a DAG rewrite plan with source-backed guardrails, and optionally rewrites frontmatter and body for better routing and smaller prompt footprint.
Converts local AGENT.md files into Claude Code optimized agents by auditing them against Claude Code runtime behavior and creating a per-agent DAG rewrite plan. Optionally rewrites frontmatter and system-prompt body so the agent is thinner, more role-specific, and better aligned with Claude's agent runtime.
Stealth web browsing skill for AI agents using the camoufox anti-detection Firefox runtime to bypass bot protections like Cloudflare Turnstile, DataDome, and PerimeterX. Supports named profiles, authenticated sessions, and proxy rotation.
A Claude Code skill for disciplined Rust crate bug fixing that enforces a red-green-refactor loop: write a failing test first, apply the minimal fix, then verify with cargo test and clippy after each change.
A deep-review skill for Rust crates that reads every file in a target crate, runs its test suite, and writes verified findings with exact file:line evidence to a canonical issue file. It runs as a forked analysis workflow with separate reasoning budget to ensure thorough, grounded auditing.
A Docker and container infrastructure skill covering Dockerfiles, multi-stage builds, Compose, networking, volumes, health checks, registries, BuildKit, security hardening, and CI/CD integration.
A skill that extracts large inline test modules into adjacent test files while preserving visibility, helper access, and coverage shape, keeping production files clean without weakening tests.
A Generative Engine Optimization (GEO) monitoring skill that tracks brand and domain visibility across AI-powered search engines including Google AI Overviews, Perplexity, and ChatGPT Search, generating cross-engine visibility reports.
A Claude Code skill for Answer Engine Optimization (AEO) auditing and SERP analysis. Evaluates pages for AEO readiness by checking structured data, FAQ patterns, heading hierarchy, and meta quality, and analyzes how queries appear in AI-powered search results from Google AI Overviews, Perplexity, and ChatGPT Search.
An SEO auditing skill for AI agents that uses the browse CLI to extract meta tags, headings, structured data, performance metrics, and link structure, generating actionable audit reports with recommendations.
A guided configuration generator for the browse CLI's camoufox integration, offering preset profiles for stealth browsing, fast scraping, Google-safe searches, and custom setups. Walks users through anti-detection settings including GeoIP, fingerprinting, and WebRTC/WebGL blocking.
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill