Home / jerseycheese / agent-skills · GitHub

test-fix SKILL.md skillA

test-fix from jerseycheese/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add jerseycheese/agent-skills/test-fix@git:20261016.04e815b

Pins git:20261016.04e815b in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: jerseycheese/agent-skills
Path: skills/test-fix/SKILL.md
Versions recorded: 3
Latest version: git:20261016.04e815b, committed Oct 16, 2026
First version recorded: Jun 28, 2026
Size: 5,579 bytes
Repository stars: 3
License: MIT

Automatically invoke when any test run produces failures: FAIL output, test errors, or assertion failures in unit or E2E suites. Do NOT wait for the user to ask. Hard limit of 3 fix attempts per failure, then stops and escalates. Trigger on: "tests are failing", "fix the tests", "tests are broken".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## When to invoke (auto-trigger)

Invoke automatically whenever:
- A test run outputs one or more FAIL results
- `npm test`, `jest`, or `playwright` exits with a non-zero code due to test failures (not config errors)
- The user says tests are broken or a CI check is red on tests

Do NOT invoke for: build errors, type errors, lint failures — those are not test failures. Hard stop at 3 attempts; do not loop.

# Test Fix with Attempt Budget

## When to Use This Skill

Use this skill when:
- E2E tests are failing
- Unit tests are failing after code changes
- Tests are flaky or intermittent
- Previous fix attempts haven't worked

## Critical Rule

**Maximum 3 fix attempts per test.** After 3 failures, STOP and present options to the user.

## Fix Attempt Checklist

For each failing test, follow this process:

### Attempt 1: Understand and Fix Obvious Issues

1. **Read the test file**
   - Understand what the test is checking
   - Identify all selectors, assertions, and expectations
   - Note any timing assumptions (waits, animations, async operations)

2. **Identify the failure**
   - Read the error message carefully
   - Determine if it's a selector issue, timing issue, or logic issue
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add jerseycheese/agent-skills/test-fix@sha256:bc0e1770c778d56c

The line at the top of this page pins the label git:20261016.04e815b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_6d5urkfntzdenjfi.svg)](https://markdownregistry.com/a/art_6d5urkfntzdenjfi)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jun 28, 2026 and Oct 16, 2026, about one every 55 days.

version	committed	commit	size	audit
git:20261016.04e815b latest	2026-10-16	04e815b	5,579 B	A	view · diff
git:20260725.4a22f66	2026-07-25	4a22f66	5,698 B	A	view · diff
git:20260628.9366aee	2026-06-28	9366aee	5,612 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5579 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

jerseycheese/agent-skills · 3 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6d5urkfntzdenjfi
GET https://markdownregistry.com/api/v1/resolve?ref=jerseycheese/agent-skills/test-fix
GET https://markdownregistry.com/api/v1/blob/bc0e1770c778d56cb85126b75b7e2cc8d92e45d4f4684805079f6c5b36bf930b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jerseycheese/agent-skills

abstraction-finder SKILL.md skill

jerseycheese/agent-skills · skills/abstraction-finder/SKILL.md · Finds recurring patterns worth extracting into shared code and proposes the smallest form for each (helper, util, base…