AI Agent Skills — what each costs to run

58 skills

• pytest-coverage

  coding

  github/awesome-copilot

  Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.

  SKILL.md tokens

  281

  Sonnet 5 / 1k loads

  $0.56

  No flags detected
• gh-address-comments

  coding

  openai/skills

  Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

  SKILL.md tokens

  319

  Sonnet 5 / 1k loads

  $0.64

  Runs scripts
• multi-stage-dockerfile

  coding

  github/awesome-copilot

  Create optimized multi-stage Dockerfiles for any language or framework

  SKILL.md tokens

  577

  Sonnet 5 / 1k loads

  $1.15

  No flags detected
• conventional-commit

  coding

  github/awesome-copilot

  Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, exa

  SKILL.md tokens

  662

  Sonnet 5 / 1k loads

  $1.32

  Network access

  Shell commands
• vercel-deploy

  coding

  openai/skills

  Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

  SKILL.md tokens

  662

  Sonnet 5 / 1k loads

  $1.32

  Runs scripts

  Network access

  Shell commands
• nextjs-on-cloudflare

  coding

  cloudflare/skills

  Build, migrate, and deploy Next.js apps on Cloudflare Workers with vinext. Use when starting a Next.js project on Cloudflare, moving an existing app to Workers, choosing between vinext and OpenNext, or setting up vinext for Workers. For set

  SKILL.md tokens

  677

  Sonnet 5 / 1k loads

  $1.35

  Network access

  Shell commands
• swarm

  coding

  cursor/plugins

  Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

  SKILL.md tokens

  684

  Sonnet 5 / 1k loads

  $1.37

  No flags detected
• requesting-code-review

  coding

  obra/superpowers

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements

  SKILL.md tokens

  742

  Sonnet 5 / 1k loads

  $1.48

  Shell commands
• verification-before-completion

  coding

  obra/superpowers

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

  SKILL.md tokens

  899

  Sonnet 5 / 1k loads

  $1.80

  No flags detected
• gh-fix-ci

  coding

  openai/skills

  Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers

  SKILL.md tokens

  912

  Sonnet 5 / 1k loads

  $1.82

  Runs scripts

  Network access
• playwright

  coding

  openai/skills

  Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

  SKILL.md tokens

  942

  Sonnet 5 / 1k loads

  $1.88

  Runs scripts

  Network access

  Shell commands
• huggingface-local-models

  coding

  huggingface/skills

  Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

  SKILL.md tokens

  945

  Sonnet 5 / 1k loads

  $1.89

  Runs scripts

  Network access

  Shell commands
• sentry

  coding

  openai/skills

  Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

  SKILL.md tokens

  952

  Sonnet 5 / 1k loads

  $1.90

  Network access

  Shell commands
• webapp-testing

  coding

  anthropics/skills

  Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

  SKILL.md tokens

  965

  Sonnet 5 / 1k loads

  $1.93

  Runs scripts

  Network access

  Shell commands
• figure-it-out

  coding

  cursor/plugins

  Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it

  SKILL.md tokens

  1,027

  Sonnet 5 / 1k loads

  $2.05

  No flags detected
• chrome-devtools

  coding

  github/awesome-copilot

  Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.

  SKILL.md tokens

  1,036

  Sonnet 5 / 1k loads

  $2.07

  Network access
• jupyter-notebook

  coding

  openai/skills

  Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

  SKILL.md tokens

  1,038

  Sonnet 5 / 1k loads

  $2.08

  Runs scripts

  Shell commands
• make-bot-ui

  coding

  cursor/plugins

  Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

  SKILL.md tokens

  1,162

  Sonnet 5 / 1k loads

  $2.32

  Network access
• reflect

  coding

  cursor/plugins

  Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

  SKILL.md tokens

  1,248

  Sonnet 5 / 1k loads

  $2.50

  Shell commands
• arena

  coding

  cursor/plugins

  Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

  SKILL.md tokens

  1,399

  Sonnet 5 / 1k loads

  $2.80

  Shell commands
• workers-best-practices

  coding

  cloudflare/skills

  Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.

  SKILL.md tokens

  1,402

  Sonnet 5 / 1k loads

  $2.80

  Network access
• durable-objects

  coding

  cloudflare/skills

  Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

  SKILL.md tokens

  1,509

  Sonnet 5 / 1k loads

  $3.02

  Network access
• dispatching-parallel-agents

  coding

  obra/superpowers

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

  SKILL.md tokens

  1,513

  Sonnet 5 / 1k loads

  $3.03

  No flags detected
• receiving-code-review

  coding

  obra/superpowers

  Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

  SKILL.md tokens

  1,541

  Sonnet 5 / 1k loads

  $3.08

  No flags detected
• show-me-your-work

  coding

  cursor/plugins

  Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-

  SKILL.md tokens

  1,637

  Sonnet 5 / 1k loads

  $3.27

  Runs scripts
• cloudflare-email-service

  coding

  cloudflare/skills

  Implement or troubleshoot Cloudflare Email Sending and Email Routing integrations and their delivery configuration.

  SKILL.md tokens

  1,650

  Sonnet 5 / 1k loads

  $3.30

  Network access

  Shell commands
• using-git-worktrees

  coding

  obra/superpowers

  Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

  SKILL.md tokens

  1,700

  Sonnet 5 / 1k loads

  $3.40

  Shell commands
• netlify-deploy

  coding

  openai/skills

  Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

  SKILL.md tokens

  1,746

  Sonnet 5 / 1k loads

  $3.49

  Network access

  Shell commands
• create-github-action-workflow-specification

  coding

  github/awesome-copilot

  Create a formal specification for an existing GitHub Actions CI/CD workflow, optimized for AI consumption and workflow maintenance.

  SKILL.md tokens

  1,915

  Sonnet 5 / 1k loads

  $3.83

  No flags detected
• finishing-a-development-branch

  coding

  obra/superpowers

  Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

  SKILL.md tokens

  1,932

  Sonnet 5 / 1k loads

  $3.86

  Shell commands
• web-perf

  coding

  cloudflare/skills

  Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.

  SKILL.md tokens

  2,063

  Sonnet 5 / 1k loads

  $4.13

  Network access
• mcp-builder

  coding

  anthropics/skills

  Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (F

  SKILL.md tokens

  2,264

  Sonnet 5 / 1k loads

  $4.53

  Runs scripts

  Network access

  Shell commands
• systematic-debugging

  coding

  obra/superpowers

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

  SKILL.md tokens

  2,376

  Sonnet 5 / 1k loads

  $4.75

  Runs scripts

  Shell commands
• test-driven-development

  coding

  obra/superpowers

  Use when implementing any feature or bugfix, before writing implementation code

  SKILL.md tokens

  2,389

  Sonnet 5 / 1k loads

  $4.78

  Shell commands
• writing-plans

  coding

  obra/superpowers

  Use when you have a spec or requirements for a multi-step task, before touching code

  SKILL.md tokens

  2,579

  Sonnet 5 / 1k loads

  $5.16

  Shell commands
• cli-creator

  coding

  openai/skills

  Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose com

  SKILL.md tokens

  2,625

  Sonnet 5 / 1k loads

  $5.25

  Network access

  Shell commands
• debugging-and-error-recovery

  coding

  addyosmani/agent-skills

  Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why

  SKILL.md tokens

  2,636

  Sonnet 5 / 1k loads

  $5.27

  Shell commands
• ci-cd-and-automation

  coding

  addyosmani/agent-skills

  Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

  SKILL.md tokens

  2,752

  Sonnet 5 / 1k loads

  $5.50

  Shell commands
• wrangler

  coding

  cloudflare/skills

  Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wran

  SKILL.md tokens

  2,906

  Sonnet 5 / 1k loads

  $5.81

  Network access
• agents-sdk

  coding

  cloudflare/skills

  Build, debug, or review Cloudflare Agents SDK applications using the agents package.

  SKILL.md tokens

  3,003

  Sonnet 5 / 1k loads

  $6.01

  Network access

  Shell commands
• spec-driven-development

  coding

  addyosmani/agent-skills

  Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambi

  SKILL.md tokens

  3,249

  Sonnet 5 / 1k loads

  $6.50

  Shell commands
• git-workflow-and-versioning

  coding

  addyosmani/agent-skills

  Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR),

  SKILL.md tokens

  3,465

  Sonnet 5 / 1k loads

  $6.93

  Shell commands
• browser-testing-with-devtools

  coding

  addyosmani/agent-skills

  Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual ou

  SKILL.md tokens

  3,483

  Sonnet 5 / 1k loads

  $6.97

  Network access
• api-and-interface-design

  coding

  addyosmani/agent-skills

  Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend a

  SKILL.md tokens

  3,702

  Sonnet 5 / 1k loads

  $7.40

  No flags detected
• playwright-cli

  coding

  microsoft/playwright-cli

  Automate browser interactions, test web pages and work with Playwright tests.

  SKILL.md tokens

  3,855

  Sonnet 5 / 1k loads

  $7.71

  Network access

  Shell commands
• performance-optimization

  coding

  addyosmani/agent-skills

  Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patte

  SKILL.md tokens

  4,129

  Sonnet 5 / 1k loads

  $8.26

  Shell commands
• refactor

  coding

  github/awesome-copilot

  Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less

  SKILL.md tokens

  4,210

  Sonnet 5 / 1k loads

  $8.42

  Shell commands
• render-deploy

  coding

  openai/skills

  Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.

  SKILL.md tokens

  4,395

  Sonnet 5 / 1k loads

  $8.79

  Network access

  Shell commands
• huggingface-spaces

  coding

  huggingface/skills

  Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create

  SKILL.md tokens

  4,446

  Sonnet 5 / 1k loads

  $8.89

  Network access

  Shell commands
• executing-plans

  coding

  obra/superpowers

  Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

  SKILL.md tokens

  4,499

  Sonnet 5 / 1k loads

  $9.00

  Shell commands
• openai-docs

  coding

  openai/skills

  Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade an

  SKILL.md tokens

  4,575

  Sonnet 5 / 1k loads

  $9.15

  Runs scripts

  Network access

  Shell commands
• subagent-driven-development

  coding

  obra/superpowers

  Use when executing implementation plans with independent tasks in the current session

  SKILL.md tokens

  4,847

  Sonnet 5 / 1k loads

  $9.69

  Shell commands
• chatgpt-apps

  coding

  openai/skills

  Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply A

  SKILL.md tokens

  4,903

  Sonnet 5 / 1k loads

  $9.81

  Runs scripts

  Network access
• code-review-and-quality

  coding

  addyosmani/agent-skills

  Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Us

  SKILL.md tokens

  5,224

  Sonnet 5 / 1k loads

  $10.45

  Shell commands
• poteto-mode

  coding

  cursor/plugins

  poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

  SKILL.md tokens

  5,407

  Sonnet 5 / 1k loads

  $10.81

  Runs scripts

  Network access

  Shell commands
• huggingface-gradio

  coding

  huggingface/skills

  Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

  SKILL.md tokens

  6,182

  Sonnet 5 / 1k loads

  $12.36

  Network access

  Shell commands
• transformers-js

  coding

  huggingface/skills

  Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech r

  SKILL.md tokens

  6,224

  Sonnet 5 / 1k loads

  $12.45

  Network access

  Shell commands
• claude-api

  coding

  anthropics/skills

  Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-li

  SKILL.md tokens

  26,279

  Sonnet 5 / 1k loads

  $52.56

  Runs scripts

  Network access