Agent Skills

greeter

✓★ 105,700

by google-gemini

A friendly greeter skill

🧰 Not standalone — use together with google-gemini/gemini-cli

pirate-skill

✓★ 105,700

by google-gemini

Speak like a pirate.

🧰 Not standalone — use together with google-gemini/gemini-cli

code-reviewer

✓★ 105,700

by google-gemini

Automated code review for local changes and remote pull requests with structured analysis across correctness, maintainability, and security. Supports both local file system changes (staged and unstaged) and remote PRs (by number or URL) with automatic GitHub CLI checkout Analyzes code across seven dimensions: correctness, maintainability, readability, efficiency, security, edge case handling, and test coverage Runs optional preflight verification suites (e.g., npm run preflight ) to catch...

🧰 Not standalone — use together with google-gemini/gemini-cli

pr-creator

✓★ 105,700

by google-gemini

Guided pull request creation that enforces repository templates and safety standards. Enforces branch safety with critical checks to prevent commits and pushes to main Locates and applies repository-specific PR templates from .github/ directories, supporting multiple template variants Guides description drafting with template structure preservation, checklist completion, and issue linking Includes preflight validation via npm run preflight to catch build, lint, and test failures before PR...

🧰 Not standalone — use together with google-gemini/gemini-cli

review-duplication

✓★ 105,700

by google-gemini

Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing…

🧰 Not standalone — use together with google-gemini/gemini-cli

skill-creator

✓★ 105,700

by google-gemini

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's…

🧰 Not standalone — use together with google-gemini/gemini-cli

behavioral-evals

✓★ 105,700

by google-gemini

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt…

🧰 Not standalone — use together with google-gemini/gemini-cli

async-pr-review

✓★ 105,700

by google-gemini

Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR…

🧰 Not standalone — use together with google-gemini/gemini-cli

cloud

★ 102,600

by browser-use

Reference docs for the Cloud REST API, SDKs, and integration patterns. Read the relevant file based on what the user needs.

🧰 Not standalone — use together with browser-use/browser-use

browser-use

★ 102,600

by 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.

🧰 Not standalone — use together with browser-use/browser-use

open-source

★ 102,600

by browser-use

Reference docs for writing Python code against the browser-use library. Read the relevant file based on what the user needs.

🧰 Not standalone — use together with browser-use/browser-use

remote-browser

★ 102,600

by browser-use

Cloud browser automation for sandboxed agents without local GUI access. Supports navigation, page inspection, interactions, JavaScript execution, and cookie management via 30+ CLI commands Includes cloud session management for running autonomous browser agents in parallel, with task monitoring and structured output options Provides local dev server tunneling via Cloudflare to expose ports from the remote machine to the cloud browser Maintains session state across commands, enabling...

🧰 Not standalone — use together with browser-use/browser-use

add-uint-support

★ 101,500

by pytorch

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to…

🧰 Not standalone — use together with pytorch/pytorch

skill-writer

★ 101,500

by pytorch

Guide for creating well-structured Agent Skills for Claude Code with best practices and validation. Covers full Skill lifecycle: scoping, file structure, YAML frontmatter validation, content organization, and testing procedures Enforces strict naming rules (lowercase, hyphens, max 64 chars) and description requirements (specific triggers, file types, "what" and "when" clauses) Provides templates for common patterns including read-only Skills, script-based Skills, and multi-file Skills with...

🧰 Not standalone — use together with pytorch/pytorch

babysit-pr

✓★ 95,500

by openai

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is…

🧰 Not standalone — use together with openai/codex

code-review

✓★ 95,500

by openai

Run a final code review on a pull request

🧰 Not standalone — use together with openai/codex

codex-pr-body

✓★ 95,500

by openai

Update the title and body of one or more pull requests.

🧰 Not standalone — use together with openai/codex

plugin-creator

✓★ 95,500

by openai

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

🧰 Not standalone — use together with openai/codex

skill-creator

✓★ 95,500

by openai

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's…

🧰 Not standalone — use together with openai/codex

performance-investigation

★ 87,500

by sveltejs

Investigate performance regressions and find opportunities for optimization

🧰 Not standalone — use together with sveltejs/svelte

ponytail

★ 73,500

by dietrichgebert

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or...

🧰 Not standalone — use together with dietrichgebert/ponytail

context7-cli

✓★ 58,600

by upstash

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7",…

🧰 Not standalone — use together with upstash/context7

find-docs

✓★ 58,600

by upstash

Retrieve current documentation and code examples for any library using the Context7 CLI.

🧰 Not standalone — use together with upstash/context7

context7-mcp

✓★ 58,600

by upstash

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code…

🧰 Not standalone — use together with upstash/context7

docs

✓★ 58,600

by upstash

Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework. Use when writing code that depends on…

🧰 Not standalone — use together with upstash/context7

context7-cli

✓★ 58,600

by upstash

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7",…

🧰 Not standalone — use together with upstash/context7

find-docs

✓★ 58,600

by upstash

Retrieve current documentation and code examples for any library using the Context7 CLI.

🧰 Not standalone — use together with upstash/context7

context7-mcp

✓★ 58,600

by upstash

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code…

🧰 Not standalone — use together with upstash/context7

add-expert

★ 52,100

by remotion-dev

Add a new expert to the Remotion experts page

🧰 Not standalone — use together with remotion-dev/remotion

android-e2e-testing

✓★ 50,400

by expo

Test Expo Router features on Android emulators using ADB. Use after implementing native Android features or when verifying UI behavior on Android.

🧰 Not standalone — use together with expo/expo