Home / cunhaax / ai-workflow · GitHub

adversarial-qa SKILL.md skillA

adversarial-qa from cunhaax/ai-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cunhaax/ai-workflow/adversarial-qa@git:20261004.cccdee6

Pins git:20261004.cccdee6 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cunhaax/ai-workflow
Path: plugins/ai-workflow/skills/adversarial-qa/SKILL.md
Versions recorded: 5
Latest version: git:20261004.cccdee6, committed Oct 4, 2026
First version recorded: Jul 26, 2026
Size: 5,480 bytes
Repository stars: 5
License: MIT

Exploratory QA of a running feature through its UI (Playwright) and/or API (curl) to find issues the plan and committed tests missed; returns findings with evidence, known issues, and blockers. Use when the user asks to QA, probe, or try to break a feature, after code review passes.

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

# /adversarial-qa

Exercise a feature in the running app and surface anything wrong, confusing,
or likely to bite a real user. Go beyond the committed tests; don't
re-verify the spec or review code.

## Input

- Plan text (optional): read Requirements only to understand what the feature
  does, not as a checklist
- Open deferred QA findings list (optional; empty list = "none open", which
  is a value, not an omission)

## Steps

### 1. Get open deferred QA findings

- List passed in → use it as-is
- Otherwise:
  - `AGENTS.md` → *Task Tracking* → *List open deferred QA findings* holds a
    real command/tool call → run it
  - section/bullet absent, `[TODO:]`, or `none` →
    `gh issue list --label known-issue --state open`
  - holds a real command you cannot run (e.g. an MCP tool you don't have) →
    never fall back to `gh` (wrong tracker). Report under *Blockers* "known
    issues not checked: <reason>", skip step 5, continue the rest

### 2. Determine the surface(s)

- From the plan's Requirements (or the diff, if no plan): **UI** (templates,
  views, a controller path rendering a view/fragment/client-driven response),
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cunhaax/ai-workflow/adversarial-qa@sha256:549d9f8c4314b745

The line at the top of this page pins the label git:20261004.cccdee6, 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_xsbvcjjztqz6xml2.svg)](https://markdownregistry.com/a/art_xsbvcjjztqz6xml2)

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

Versions

The registry has recorded 5 versions of this file, between Jul 26, 2026 and Oct 4, 2026, about one every 17 days.

version	committed	commit	size	audit
git:20261004.cccdee6 latest	2026-10-04	cccdee6	5,480 B	A	view · diff
git:20260928.2953a1d	2026-09-28	2953a1d	6,503 B	A	view · diff
git:20260811.0859bac	2026-08-11	0859bac	5,764 B	A	view · diff
git:20260729.8ebcc2b	2026-07-29	8ebcc2b	4,167 B	A	view · diff
git:20260726.3115fd3	2026-07-26	3115fd3	3,301 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 (5480 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

cunhaax/ai-workflow · 5 stars · license MIT · pushed 2026-10-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_xsbvcjjztqz6xml2
GET https://markdownregistry.com/api/v1/resolve?ref=cunhaax/ai-workflow/adversarial-qa
GET https://markdownregistry.com/api/v1/blob/549d9f8c4314b74548a43eb1487ee72a482a2902d528e8e6b312069a9ae68877

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.