Skip to content
Skill category

Developer Tools skills

Agent skills for developers: build on the Claude API, write and evaluate MCP servers, create skills, test local web apps with Playwright, ship React artifacts.

46 skills

About Developer Tools

These skills give a coding agent the knowledge and scripts for jobs it would otherwise improvise: calling an API whose details change faster than training data, wiring up a protocol server, testing a page in a real browser, or packaging an app into one file.

What is here

Building on Claude

  • claude-api is a large reference skill: current model IDs and pricing, SDK patterns in seven languages plus cURL, Managed Agents, model migrations and evals. It loads only the reference files a task needs.
  • mcp-builder walks Claude through building an MCP server: researching the target API, implementing tools in TypeScript or Python, testing with the MCP Inspector, then measuring the server with an LLM evaluation harness.
  • skill-creator is the skill for making skills. Claude drafts a SKILL.md, runs test prompts with and without it, shows the results in a review viewer and tunes the description that decides when it triggers.

Building and testing web apps

  • webapp-testing has Claude write native Python Playwright scripts against a local app, start the dev servers with a lifecycle helper, then inspect screenshots, the DOM and console logs.
  • web-artifacts-builder scaffolds a React, TypeScript, Tailwind and shadcn/ui project with one script and bundles it into a single HTML file with another, for artifacts too complex to hand-write.
  • frontend-design pushes generated interfaces away from templated defaults toward a deliberate palette, type, layout and copy. It also sits under design and visual art.

How to choose

Start from what you are shipping. If it calls the Claude API, claude-api keeps model names and SDK usage current. If it is a tool for agents, mcp-builder covers servers and skill-creator covers skills, and both put real weight on evaluation rather than stopping at “it runs”. For web work, webapp-testing checks behaviour, web-artifacts-builder handles packaging and frontend-design handles the look.

Several of these run commands, use the network or write files, and claude-api includes scripts that read credentials; each record’s security notes list what it touches, which matters if you run agents with broad permissions.

Showing 34 of 46 skillsScript-led Model-led Mixed Network Git Clear all
Model-led1,426 tokens in use

Code Review

329,112

Code Review And Quality · Developer Tools

Reviews the changes since a fixed point along two axes, repo standards and spec match, with parallel sub-agents and a Fowler smell baseline.

Skill
94idle
1,426in use
1,426up to
Tokens, counted offlineView skill
Model-led1,295 tokens in use

Codebase Design

329,112

Developer Tools · Software Architecture And Planning

Shared vocabulary for deep modules: a lot of behaviour behind a small interface, placed at a clean seam and testable through that interface.

Skill
57idle
1,295in use
2,451up to
Tokens, counted offlineView skill
Model-led1,994 tokens in use

Diagnosing Bugs

329,112

Code Review And Quality · Developer Tools

A six-phase debugging discipline that starts by building a tight, red-capable feedback loop for the bug before any theorising.

Skill
43idle
1,994in use
1,994up to
Tokens, counted offlineView skill
Model-led106 tokens in use

Implement

329,112

Agent Workflows · Developer Tools

Builds the work in a spec or ticket by driving TDD at pre-agreed seams, then runs code-review and commits to the current branch.

Skill
16idle
106in use
106up to
Tokens, counted offlineView skill
Model-led572 tokens in use

Implement Spec

329,112

Agent Workflows · Developer Tools

Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.

Skill
18idle
572in use
572up to
Tokens, counted offlineView skill
Model-led1,320 tokens in use

Improve Codebase Architecture

329,112

Developer Tools · Software Architecture And Planning

Scans a codebase for deepening opportunities, shows them in a visual HTML report, then interviews you through the candidate you choose.

Skill
32idle
1,320in use
2,930up to
Tokens, counted offlineView skill
Model-led914 tokens in use

PR

329,112

Developer Tools

A pull request body template with a summary as the smallest useful visual, before and after evidence, and a merge-danger call.

Skill
9idle
914in use
914up to
Tokens, counted offlineView skill
Model-led604 tokens in use

Prototype

329,112

Developer Tools · Software Architecture And Planning

Builds throwaway code that answers one design question, either as a shareable HTML logic demo or as several UI variants on one route.

Skill
39idle
604in use
3,531up to
Tokens, counted offlineView skill
Model-led588 tokens in use

Setup Pre-Commit

329,112

Developer Tools · Devops And Releases

Set up Husky pre-commit hooks that run lint-staged with Prettier, then your typecheck and test scripts, with the package manager detected.

Skill
59idle
588in use
588up to
Tokens, counted offlineView skill
Model-led1,340 tokens in use

dispatching-parallel-agents

322,961

Agent Workflows · Developer Tools

Splits two or more independent problems across focused subagents, each with its own scope, constraints and expected output.

Skill
26idle
1,340in use
1,340up to
Tokens, counted offlineView skill
Mixed4,484 tokens in use

subagent-driven-development

322,961

Agent Workflows · Developer Tools

Runs an implementation plan with a fresh implementer subagent per task, a spec and quality review after each, and a final branch review.

Skill
17idle
4,484in use
10,486up to
Tokens, counted offlineView skill
Mixed2,220 tokens in use

systematic-debugging

322,961

Code Review And Quality · Developer Tools

A four-phase debugging process that finds the root cause before any fix is proposed.

Skill
21idle
2,220in use
5,201up to
Tokens, counted offlineView skill
Model-led2,330 tokens in use

test-driven-development

322,961

Code Review And Quality · Developer Tools

Enforces red-green-refactor: a failing test first, minimal code to pass it, and deletion of any code written before its test.

Skill
17idle
2,330in use
4,104up to
Tokens, counted offlineView skill
Model-led815 tokens in use

verification-before-completion

322,961

Agent Workflows · Code Review And Quality · Developer Tools

Requires fresh command output as evidence before your agent claims work is done, fixed or passing.

Skill
43idle
815in use
815up to
Tokens, counted offlineView skill
Model-led1,871 tokens in use

frontend-design

198,136

Design And Visual Art · Developer Tools · Frontend And UI Engineering

Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.

Skill
41idle
1,871in use
1,871up to
Tokens, counted offlineView skill
Mixed2,375 tokens in use

mcp-builder

198,136

Developer Tools

Anthropic's skill for building MCP servers: research the API, implement tools in TypeScript or Python, test with the Inspector, then measure the server with an LLM evaluation harness.

Skill
61idle
2,375in use
29,563up to
Tokens, counted offlineView skill
Mixed7,253 tokens in use

skill-creator

198,136

Agent Workflows · Developer Tools

Anthropic's skill for making skills: Claude drafts a SKILL.md, runs test prompts with and without it, shows the results in a review viewer and tunes the description that triggers it.

Skill
64idle
7,253in use
18,660up to
Tokens, counted offlineView skill
Mixed833 tokens in use

webapp-testing

198,136

Code Review And Quality · Developer Tools

Anthropic's skill for testing local web apps: Claude writes native Python Playwright scripts, starts the dev servers with a helper, then inspects screenshots, the DOM and console logs.

Skill
35idle
833in use
833up to
Tokens, counted offlineView skill
Model-led824 tokens in use

react-vite-dashboard

11,108

Developer Tools · Frontend And UI Engineering

Converts Stitch screens into React and Vite dashboards with TanStack Query, DESIGN.md tokens and read-only Web3 patterns.

Skill
38idle
824in use
824up to
Tokens, counted offlineView skill
Mixed2,106 tokens in use

shadcn-ui

11,108

Developer Tools

Guides agents through shadcn/ui work: finding components, installing them with the CLI, theming with CSS variables and extending them with cva.

Skill
31idle
2,106in use
14,070up to
Tokens, counted offlineView skill
Model-led6,466 tokens in use

n8n Agents

6,689

Developer Tools

A guide for designing n8n AI agents: which AI node to use, how to name tools, wire memory, force structured output and gate risky actions behind human review.

Skill
152idle
6,466in use
28,780up to
Tokens, counted offlineView skill
Model-led3,645 tokens in use

n8n Binary and Data

6,689

Developer Tools

A guide to files in n8n: where bytes live, how to read and write them, how to stop transforms from dropping them, and how to pass files to agent tools and chat apps.

Skill
134idle
3,645in use
12,472up to
Tokens, counted offlineView skill
Model-led5,349 tokens in use

n8n Code JavaScript

6,689

Developer Tools

A guide to writing JavaScript in n8n Code nodes: a gate that checks native nodes first, data access, return format, webhook body, sandbox limits and loop pitfalls.

Skill
254idle
5,349in use
32,189up to
Tokens, counted offlineView skill
Model-led2,755 tokens in use

n8n Code Python

6,689

Developer Tools

A guide to native Python in n8n 2.x Code nodes: the two input variables, blocked imports, denied builtins, accepted return shapes and how errors interact with onError.

Skill
226idle
2,755in use
5,186up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers