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 21 of 46 skillsGit Network Shell 70 and up 90 and up Clear all
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-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-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-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
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
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
Model-led3,907 tokens in use

n8n Code Tool

6,689

Developer Tools

A guide to the n8n Custom Code Tool that AI agents call: string in and string out, the query variable, input schemas, sandbox limits and the three signature errors.

Skill
220idle
3,907in use
7,360up to
Tokens, counted offlineView skill
Model-led4,996 tokens in use

n8n Error Handling

6,689

Developer Tools

A guide to n8n error handling: the two-step per-node error output, retryOnFail, 4xx and 5xx webhook responses and Error Trigger workflows for unattended runs.

Skill
128idle
4,996in use
15,907up to
Tokens, counted offlineView skill
Model-led6,063 tokens in use

n8n Expression Syntax

6,689

Developer Tools

A guide to writing correct n8n expressions: double braces, $json and $node, the webhook body trap, a native-node-first order, JMESPath, helpers and silent null errors.

Skill
103idle
6,063in use
11,631up to
Tokens, counted offlineView skill
Model-led8,154 tokens in use

n8n MCP Tools Expert

6,689

Developer Tools

The main guide to the n8n-mcp tools: which tool to call, the two nodeType formats, validation profiles, iterative workflow edits, test runs, credentials and audits.

Skill
135idle
8,154in use
28,684up to
Tokens, counted offlineView skill
Model-led3,534 tokens in use

n8n Multi-Instance

6,689

Developer Tools

A guide to working with several n8n instances over MCP: name the target on each call, use switch sparingly, guard credential writes and recover from misrouted calls.

Skill
194idle
3,534in use
3,534up to
Tokens, counted offlineView skill
Model-led4,739 tokens in use

n8n Node Configuration

6,689

Developer Tools

A guide to configuring n8n nodes: required fields that change with the operation, displayOptions dependencies, get_node detail levels, native data nodes and silent-failure traps.

Skill
125idle
4,739in use
25,838up to
Tokens, counted offlineView skill
Model-led4,611 tokens in use

n8n Sub-workflows

6,689

Developer Tools

A guide to reusable n8n sub-workflows: typed Define Below inputs, all versus each mode, verb-first names, stateless or stateful design and fire-and-forget parallel runs.

Skill
119idle
4,611in use
8,196up to
Tokens, counted offlineView skill
Model-led5,481 tokens in use

n8n Validation Expert

6,689

Developer Tools

Teaches an agent to read n8n-mcp validation results, run the validate-and-fix loop, judge which warnings matter and test a workflow once it validates.

Skill
90idle
5,481in use
21,347up to
Tokens, counted offlineView skill
Model-led5,049 tokens in use

n8n Workflow Patterns

6,689

Developer Tools

Gives an agent six proven n8n workflow architectures, a pattern selection guide, a build checklist and the validate, verify, test, activate sequence.

Skill
144idle
5,049in use
24,105up 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