plan-qa SKILL.md skillA
plan-qa from foyzulkarim/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add foyzulkarim/skills/plan-qa@git:20260831.b6940c2Pins git:20260831.b6940c2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- foyzulkarim/skills
- Path
dev-pipeline/skills/plan-qa/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260831.b6940c2, committed Aug 31, 2026
- First version recorded
- Aug 23, 2026
- Size
- 18,702 bytes
- Repository stars
- 43
- License
- none declared
Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in parallel), only when the change has a running surface worth driving. Interviews the developer to turn the specs and the diff into an executable QA specification (specs/qa/QA-<N>-<slug>.md) that /execute-qa runs. The agent drives browser and shell; the human steps in only at named handoff points. Use only when the user asks to plan manual QA — never trigger automatically.
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
# Plan-QA Skill You are a collaborative QA planning partner running the **post-implementation QA gate** — a declaration skill, not a numbered phase. Independent of `/review` (Phase 5), the developer decides the order. Automated suites verify what tests can assert; this phase covers the three blind spots they cannot reach: 1. **What a human sees** — elements that are genuinely unclickable, copy that says the right thing, a form that surfaces its own failures. 2. **Whole-request behavior** — real sessions, real redirects, real authorization failures from the actual running server. 3. **Deploy-time risk** — migrations against a live schema, anything the test suite never exercises. The agent cannot QA "against the requirements" cold — the knowledge of *which click-paths matter and where things break invisibly* lives in the developer's head and in the specs. Your job is to extract that knowledge into a QA specification complete enough that executing it (the `/execute-qa` skill) needs no context beyond the artifact. Like plan-requirements and plan-architecture, this is a **declaration skill**: the conversation is the value; the artifact is its record and the execution contract. …
Read the whole file at its exact version.
How to install
mdr add foyzulkarim/skills/plan-qa@sha256:c82c9c9e15e1432bThe line at the top of this page pins the label git:20260831.b6940c2, 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.
[](https://markdownregistry.com/a/art_b6wkwpamssiqkfst)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 23, 2026 and Aug 31, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260831.b6940c2 latest | 2026-08-31 | b6940c2 | 18,702 B | A | view · diff |
| git:20260823.71acb2d | 2026-08-23 | 71acb2d | 14,817 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (18702 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
foyzulkarim/skills · 43 stars · license none declared · pushed 2026-09-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_b6wkwpamssiqkfst GET https://markdownregistry.com/api/v1/resolve?ref=foyzulkarim/skills/plan-qa GET https://markdownregistry.com/api/v1/blob/c82c9c9e15e1432b9b7404534219fee283a1eb547e74f065d64a76046dac476d
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.