AGENTS.mdA

AGENTS.md from petrkindlmann/qa-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add petrkindlmann/qa-skills/AGENTS.md@git:20261021.03fbcb2

Pins git:20261021.03fbcb2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
petrkindlmann/qa-skills
Path
AGENTS.md
Versions recorded
5
Latest version
git:20261021.03fbcb2, committed Oct 21, 2026
First version recorded
Mar 30, 2026
Size
11,358 bytes
Repository stars
198
License
MIT

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

# Agent Behavior Specification

How AI agents should discover, load, and use skills from this repository.

## Skill Discovery

On first skill use per session:

1. Check for `.agents/qa-project-context.md` in the user's project root
   - If exists: read it and use as context for all subsequent skill interactions
   - If not: suggest the user creates one using the `qa-project-context` skill
2. Read the activated skill's `SKILL.md` from `skills/<skill-name>/SKILL.md`
3. Follow the skill's Discovery Questions, skip any already answered by qa-project-context
4. Load files from `references/` only when deeper detail is needed — do not read all reference files upfront

## Evidence and execution

- Read the actual project configuration, lockfile, fixtures, and available tools before
  adapting a recipe. Example URLs, credentials, selectors, regions, and fixture names are
  placeholders until connected to project evidence. A dependency range is not the installed version.
- Use available context to resolve routine choices. Ask only for missing input that changes
  the work; an absent optional integration or context file does not prevent useful local work.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add petrkindlmann/qa-skills/AGENTS.md@sha256:5b7c734754bbdaf1

The line at the top of this page pins the label git:20261021.03fbcb2, 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 badge

[![mdr](https://markdownregistry.com/badge/art_qxilwawptndlea55.svg)](https://markdownregistry.com/a/art_qxilwawptndlea55)

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

Versions

The registry has recorded 5 versions of this file, between Mar 30, 2026 and Oct 21, 2026, about one every 51 days.

versioncommittedcommitsizeaudit
git:20261021.03fbcb2 latest2026-10-21 03fbcb2 11,358 BA view · diff
git:20261021.b99ea462026-10-21 b99ea46 11,018 BA view · diff
git:20260610.faa635f2026-06-10 faa635f 9,382 BA view · diff
git:20260521.b8adb512026-05-21 b8adb51 7,365 BA view · diff
git:20260330.59713a42026-03-30 59713a4 5,424 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (11358 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

petrkindlmann/qa-skills · 198 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qxilwawptndlea55
GET https://markdownregistry.com/api/v1/resolve?ref=petrkindlmann/qa-skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/5b7c734754bbdaf186ec78d31a4bd551b5cc95aabe7ac70ab1d0cd3a9b1bfd99

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from petrkindlmann/qa-skills

CLAUDE.md CLAUDE.md file
petrkindlmann/qa-skills · CLAUDE.md
git:20260323.b54e23c · audit B · 198 stars
accessibility-testing SKILL.md skill
petrkindlmann/qa-skills · skills/accessibility-testing/SKILL.md · Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA…
v2.0 · audit A · 198 stars
agentic-browser-testing SKILL.md skill
petrkindlmann/qa-skills · skills/agentic-browser-testing/SKILL.md · Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and…
v1.0 · audit A · 198 stars
ai-bug-triage SKILL.md skill
petrkindlmann/qa-skills · skills/ai-bug-triage/SKILL.md · Hybrid fingerprint + LLM pipeline for bug classification, deduplication, and ticket generation. Normalizes CI logs…
v2.0 · audit A · 198 stars
ai-qa-review SKILL.md skill
petrkindlmann/qa-skills · skills/ai-qa-review/SKILL.md · Review EXISTING test code for quality, smells, and testability issues. Detects test smells across six dimensions —…
v2.0 · audit A · 198 stars
ai-system-testing SKILL.md skill
petrkindlmann/qa-skills · skills/ai-system-testing/SKILL.md · Test AI/LLM features that ship in your product. Covers prompt regression testing, response quality evaluation…
v2.2 · audit F · 198 stars
ai-test-generation SKILL.md skill
petrkindlmann/qa-skills · skills/ai-test-generation/SKILL.md · Use AI to write NEW test code from specs, PRDs, user stories, code diffs, bug reports, or OpenAPI specs. Staged…
v2.0 · audit A · 198 stars
analytics-tracking-testing SKILL.md skill
petrkindlmann/qa-skills · skills/analytics-tracking-testing/SKILL.md · Validate that analytics and marketing tracking fire CORRECTLY: GA4/GTM dataLayer events, Meta/TikTok/LinkedIn pixels…
v1.1 · audit A · 198 stars
api-testing SKILL.md skill
petrkindlmann/qa-skills · skills/api-testing/SKILL.md · Test REST and GraphQL APIs with Playwright APIRequestContext, Supertest, or standalone HTTP clients. Covers schema…
v2.1 · audit A · 198 stars
bug-reproduction SKILL.md skill
petrkindlmann/qa-skills · skills/bug-reproduction/SKILL.md · Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to…
v1.0 · audit A · 198 stars
chaos-engineering SKILL.md skill
petrkindlmann/qa-skills · skills/chaos-engineering/SKILL.md · Validate system resilience through controlled fault injection. Covers hypothesis-driven chaos experiments, failure…
v2.0 · audit A · 198 stars
ci-cd-integration SKILL.md skill
petrkindlmann/qa-skills · skills/ci-cd-integration/SKILL.md · Design CI/CD pipelines that run test suites. Covers GitHub Actions and GitLab CI templates, parallelism and sharding…
v2.0 · audit A · 198 stars

Every file in petrkindlmann/qa-skills

Other files named AGENTS.md

AGENTS.md AGENTS.md file
morluto/rea · AGENTS.md
git:20261015.0e1f0bf · audit A · 352,890 stars
AGENTS.md AGENTS.md file
obra/superpowers · AGENTS.md
git:20260919.5bf4e78 · audit A · 302,424 stars
AGENTS.md AGENTS.md file
affaan-m/ecc · AGENTS.md
git:20261011.412347a · audit A · 284,510 stars
AGENTS.md AGENTS.md file
firecrawl/firecrawl · AGENTS.md
git:20261008.5a75dca · audit A · 193,096 stars
AGENTS.md AGENTS.md file
dietrichgebert/ponytail · AGENTS.md
git:20261008.2a1fe84 · audit A · 170,980 stars
AGENTS.md AGENTS.md file
garrytan/gstack · AGENTS.md
git:20261011.5d64745 · audit A · 136,966 stars
AGENTS.md AGENTS.md file
graphify-labs/graphify · AGENTS.md
git:20260926.98d73fe · audit A · 129,649 stars
AGENTS.md AGENTS.md file
juliusbrussee/caveman · AGENTS.md
git:20260902.d9faebc · audit A · 113,780 stars

Browse by kind, by grade A, or by owner.