---
title: "Agent Skills for Testing and Debugging · skilld"
description: "Testing and debugging skills for Claude Code and other agents: test-driven development, coverage assessment, webapp testing, systematic debugging, and the post-mortem after an incident. 95 curated skills."
canonical_url: "https://skilld.dev/skills/testing"
last_updated: "2026-08-20T07:10:39.416Z"
meta:
  "og:description": "Testing and debugging skills for Claude Code and other agents: test-driven development, coverage assessment, webapp testing, systematic debugging, and the post-mortem after an incident. 95 curated skills."
  "og:image": "https://skilld.dev/_og/d/a_Testing%2Band%2Bdebugging%2Bon%2Bskilld%2Cc_Page.takumi%2Ctitle_Testing%2Band%2Bdebugging%2Cdescription_~WW91IHdhbnQgdGVzdHMgdGhhdCBwcm92ZSB0aGUgY2hhbmdlLCBhbmQgYSBjYXVzZSB3aGVuIGl0IGJyZWFrcy4%2Cp_Ii9za2lsbHMvdGVzdGluZyI%2Cs_7Of7IvckKHTWXnzW.png"
  "og:image:alt": "Testing and debugging on skilld"
  "og:image:height": "600"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "Agent Skills for Testing and Debugging"
  "twitter:image": "https://skilld.dev/_og/d/a_Testing%2Band%2Bdebugging%2Bon%2Bskilld%2Cc_Page.takumi%2Ctitle_Testing%2Band%2Bdebugging%2Cdescription_~WW91IHdhbnQgdGVzdHMgdGhhdCBwcm92ZSB0aGUgY2hhbmdlLCBhbmQgYSBjYXVzZSB3aGVuIGl0IGJyZWFrcy4%2Cp_Ii9za2lsbHMvdGVzdGluZyI%2Cs_7Of7IvckKHTWXnzW.png"
  "twitter:image:alt": "Testing and debugging on skilld"
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

# **Testing and debugging**

You want tests that prove the change, and a cause when it breaks.

## Time range

Teach your agent skilld

`npx skilld install skilld --global`

Adds the skilld Skill to your agent for every project.

## Tracks

95 skills

Devs talked about 1 of these skills this week. A list ranked by devs starts at 5.

## **Hand-picked testing and debugging skills**

1. 01

   [/tdd](https://skilld.dev/gh/mattpocock/skills/tdd)

   mattpocock/skills

   Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.312k GitHub stars
2. 02

   [/test-driven-development](https://skilld.dev/gh/obra/superpowers/test-driven-development)

   obra/superpowers

   Use when implementing any feature or bugfix, before writing implementation code312k GitHub stars
3. 03

   [/assessing-test-coverage](https://skilld.dev/gh/bitwarden/ai-plugins/assessing-test-coverage)

   bitwarden/ai-plugins

   Use when determining what test coverage ALREADY exists for a specific change (a PR, Jira key, Tech Breakdown doc, Testmo CSV, changed paths, or named component). Triggers on "what's already tested", "does this PR have tests", "what coverage exists for", "is this component covered", or "which behaviors have no test today". This is a backward-looking inventory of existing coverage for a concrete change. Do NOT use it to recommend or decide which new tests to add ("should I add integration tests here", "are unit tests enough"), to design a test strategy or plan, to run or fix existing tests, or to explain testing concepts like the test pyramid or which layers a repo uses — those are all out of scope.163 GitHub stars
4. 04

   [/systematic-debugging](https://skilld.dev/gh/obra/superpowers/systematic-debugging)

   obra/superpowers

   Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes312k GitHub stars
5. 05

   [/verifying-external-behavior](https://skilld.dev/gh/wdm0006/python-skills/verifying-external-behavior)

   wdm0006/python-skills

   Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make a "fast path" always-false, fakes that encode your assumption rather than the service's behavior, dry-runs that skip the step that fails, and large inputs that were silently read only in part. Use when integrating a new dependency or endpoint, writing a tolerated-status or error branch, choosing a client argument name, testing against a fake, or reviewing code that asserts an upstream contract.111 GitHub stars

6. 06

   [/webapp-testing](https://skilld.dev/gh/anthropics/skills/webapp-testing)

   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.187k GitHub stars
7. 07

   [/autonomous-investigation](https://skilld.dev/gh/deanpeters/product-manager-skills/autonomous-investigation)

   deanpeters/product-manager-skills

   The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.7.8k GitHub stars
8. 08

   [/post-mortem](https://skilld.dev/gh/boshu2/agentops/post-mortem)

   boshu2/agentops

   Compatibility pointer for the canonical postmortem skill.453 GitHub stars

## **More testing and debugging skills, ranked by GitHub stars**

1. 01

   [/diagnosing-superpowers](https://skilld.dev/gh/obra/superpowers/diagnosing-superpowers)

   obra/superpowers

   Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.312k GitHub stars
2. 02

   [/verification-before-completion](https://skilld.dev/gh/obra/superpowers/verification-before-completion)

   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 always312k GitHub stars
3. 03

   [/diagnosing-bugs](https://skilld.dev/gh/mattpocock/skills/diagnosing-bugs)

   mattpocock/skills

   Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.312k GitHub stars
4. 04

   [/compiler-verify](https://skilld.dev/gh/react/react/compiler-verify)

   react/react

   Use when you need to run all compiler checks (tests, lint, format) before committing. Detects whether TS or Rust code changed and runs the appropriate checks.252k GitHub stars
5. 05

   [/extract-errors](https://skilld.dev/gh/react/react/extract-errors)

   react/react

   Use when adding new error messages to React, or seeing "unknown error code" warnings.252k GitHub stars

6. 06

   [/feature-flags](https://skilld.dev/gh/react/react/feature-flags)

   react/react

   Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.252k GitHub stars
7. 07

   [/create-agent-builder-eval](https://skilld.dev/gh/n8n-io/n8n/create-agent-builder-eval)

   n8n-io/n8n

   Authors and calibrates Instance AI evaluations that build standalone n8n Agents through Agent Builder. Use when a change under packages/cli/src/modules/agents affects build-agent routing, Agent setup, model or credential selection, tools, MCP servers, integrations, skills, tasks, testing, or user-facing build responses. Requires LangTracer access before authoring so each finished case can be published.209k GitHub stars
8. 08

   [/create-instance-ai-eval](https://skilld.dev/gh/n8n-io/n8n/create-instance-ai-eval)

   n8n-io/n8n

   Authors a new Instance AI workflow or Agent eval case — written locally as JSON, calibrated against a real build, then pushed to the LangTracer suite CI runs — build cases, behaviour/process cases, credential cases, and seeded (mid-conversation) cases — with intent-driven expectations. Use when adding or changing an Instance AI eval, or debugging why one is flaky.209k GitHub stars
9. 09

   [/debugging-executions](https://skilld.dev/gh/n8n-io/n8n/debugging-executions)

   n8n-io/n8n

   Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from a node or an external service (for example a 401), before you explain the cause to the user.209k GitHub stars
10. 10

    [/gate-tests](https://skilld.dev/gh/vercel/next.js/gate-tests)

    vercel/next.js

    How to use the \`@gate\` / \`@force-gate\` test directives instead of \`it.skip\` or fake-green skip patterns. Use when a test is known-failing under some test-matrix dimension (dev mode, a bundler, an experimental flag like cacheComponents), when converting \`if (isNextDev) return\` guards or env-var \`describe.skip\` branches, when adding a condition to test/lib/gate/conditions.ts, or when keying a fixture's experimental flag on a \_\_NEXT\_TEST\_AXIS letter. Covers directive choice, condition tiers, the test-axis fixture pattern, pitfalls, and verification commands.143k GitHub stars
11. 11

    [/next-dev-loop](https://skilld.dev/gh/vercel/next.js/next-dev-loop)

    vercel/next.js

    Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /\_next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running \`next dev\`.143k GitHub stars
12. 12

    [/router-act](https://skilld.dev/gh/vercel/next.js/router-act)

    vercel/next.js

    How to write end-to-end tests using createRouterAct and LinkAccordion. Use when writing or modifying tests that need to control the timing of internal Next.js requests (like prefetches) or assert on their responses. Covers the act API, fixture patterns, prefetch control via LinkAccordion, fake clocks, and avoiding flaky testing patterns.143k GitHub stars
13. 13

    [/beta](https://skilld.dev/gh/garrytan/gstack/beta)

    garrytan/gstack

    Clean fixture tool skill with no forced reads and no mode table.139k GitHub stars
14. 14

    [/gstack-openclaw-investigate](https://skilld.dev/gh/garrytan/gstack/gstack-openclaw-investigate)

    garrytan/gstack

    Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.139k GitHub stars
15. 15

    [/investigate](https://skilld.dev/gh/garrytan/gstack/investigate)

    garrytan/gstack

    Systematic debugging with root cause investigation. (gstack)139k GitHub stars

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://skilld.dev/#website","@type":"WebSite","description":"Curated agent skills by humans, written by real maintainers in their own GitHub repos","name":"skilld","url":"https://skilld.dev/"},{"@id":"https://skilld.dev/skills/testing#webpage","@type":"WebPage","description":"Testing and debugging skills for Claude Code and other agents: test-driven development, coverage assessment, webapp testing, systematic debugging, and the post-mortem after an incident. 95 curated skills.","name":"Agent Skills for Testing and Debugging","url":"https://skilld.dev/skills/testing","isPartOf":{"@id":"https://skilld.dev/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://skilld.dev/skills/testing"]}]}]}
```