Best skills for AI agents
AI coding agents — Claude Code, Cursor, Windsurf, Copilot, Codex and the rest — all share one idea: give the model a clear, reusable instruction set and it stops improvising. That instruction set is a skill: a self-contained SKILL.md that teaches an agent how to handle one specific job, from automating a browser to reviewing a spec or generating a full test suite. This page ranks the skills that work across agents, not just one tool.
The ranking is recomputed continuously from three signals: an automated quality score of each skill's content, its GitHub star count, and a security review that flags skills requesting risky permissions and keeps them out of the top. Safe, well-documented, widely-starred skills rise to the front. The three signals are weighed together, so popularity alone never carries a skill — a well-documented, verified SKILL.md outranks a starrier but riskier one.
The picks span every category we track — development and productivity lead, followed by data & AI, with DevOps, documentation, testing, content and security represented. Each skill page below spells out what the skill does, its difficulty level, and step-by-step install instructions for the major agents.
Because these skills are tool-agnostic, the same SKILL.md usually drops straight into Claude Code, Cursor, Windsurf, Copilot or Codex — check the platform badges on each card. This ranking is never final — new agent skills are scraped, scored and security-reviewed continuously, and the leaderboard reshuffles as they arrive. Return whenever you are choosing a skill and you will see the current best, not last month's.
24 skills ranked
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.
Firecrawl Build Search
Development
Integrate Firecrawl /search into product code and agent workflows for web discovery before extraction. Use when features start with a query instead of a URL.
Frontend i18n
Development
Add or change user-facing text in the Langflow frontend via the i18n system (i18next/react-i18next). Every visible string must use t() and exist in all locale files.
PR Quiz
Development
Interactive quiz that tests whether a PR author genuinely understands their own branch before requesting review, covering changes, rationale, edge cases, and risks. Grounded in real code with honest grading.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
CCXT for TypeScript and JavaScript
Development
Comprehensive guide to using CCXT in TypeScript/JavaScript for crypto exchange integration, covering REST and WebSocket APIs, authentication, and examples.
MR Split Analysis
Development
Analyzes all changes on the current branch (uncommitted and committed) and recommends whether to split them into smaller, focused MRs. Uses heuristics like backend/frontend separation, migration-first, and cohesion.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
DeFi AMM Security
Security
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, donation attacks, oracle manipulation, slippage, and integer math.
Set up pre-commit hooks with Husky, lint-staged, Prettier
Development
Set up Husky, lint-staged, and Prettier to add a pre-commit hook that formats files, type-checks, and runs tests.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Pyrefly Type Coverage
Development
Migrate a file to use stricter Pyrefly type checking by adding annotations to all functions, classes, and attributes.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Semgrep Rule Creator
Security
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Includes test-first methodology, taint mode support, and validation steps. Helps when building targeted static analysis detections.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.
Playwright E2E Testing Patterns
Testing
Playwright E2E testing patterns covering Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Team Agent Orchestration
Development
Run team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.
How to choose
- How are these skills selected?
- An algorithm picks them among the published skills that match this page's criteria, such as category, tags or compatible tools. It ranks them by the quality score a language model gave them. On ranking pages, it also weighs GitHub stars and the security rating. Nobody reviews them one by one.
- What do the security ratings mean?
- A language model reads the SKILL.md file, without running it, and gives it a rating. Safe means it sees no meaningful execution risk. Caution means the skill uses powerful tools such as bash, docker or the network for a legitimate purpose. Risky means it asks for destructive actions, for secrets to be sent out, or for obfuscated code to run; a skill rated Risky is never published. The rating does not replace your own reading of the file.
- How do I install a skill?
- Open any skill page and follow its install instructions for your tool — Claude Code, Cursor or Copilot. Each skill lists the exact steps so you can get it running in a couple of minutes.