Is the QAMap PR QA skill free?

Yes. The skill itself is free from IvoryCanvas/qamap. SkillProof publishes the install command and an independent test verdict at no cost.

What is the QAMap PR QA SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install QAMap PR QA?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use QAMap PR QA with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

QAMap PR QA

Runs a local zero-LLM QA pass over a PR diff and picks the validation command

by IvoryCanvas · IvoryCanvas/qamap

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 30, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 13eadf9

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

The CLI is real and fast — 3.8 seconds on a two-file branch diff, no LLM call, and it correctly pulled the added test contract with its file:line, named the changed file and selected npm test as the validation command; running that command exposed a genuine regression the branch had introduced. What it does not do is find the bugs itself: reading the same nine-line diff unaided surfaced both the breaking change to the existing discount code and a hardcoded 2027 epoch that silently disables a promo, neither of which appeared anywhere in QAMap's scenarios. It degrades on size — pointed at a real 14-file, 1783-line commit range in its own repository it returned a single scenario with an empty assertions list and an empty PR checklist. Useful as a deterministic handoff format and an anti-hallucination contract (it insists an unrun command is never a pass), not as an extra pair of eyes.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What QAMap PR QA does

Wraps the QAMap CLI so that before a pull request goes up, the agent derives change intent, behaviour lifecycle, QA scenarios and the repository's validation command from commits and the diff, with no cloud or LLM call. Triggers when you are preparing, reviewing or finalising a PR, or ask what a change needs to prove before merge. Requires npm and network access, since the skill fetches @ivorycanvas/qamap at run time.

How to install QAMap PR QA

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger QAMap PR QA

/qamap-pr-qa Runs a local zero-LLM QA pass over a PR diff and picks the validation command

It also activates on plain-language prompts like these:

I'm about to open a PR, what should this change be tested for?
Review my branch before I raise the pull request and list QA scenarios
Generate a QA checklist for the diff against main before I merge

Frequently asked questions

Is the QAMap PR QA skill free?: Yes. The skill itself is free from IvoryCanvas/qamap. SkillProof publishes the install command and an independent test verdict at no cost.
Does QAMap PR QA work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Works with setup. The CLI is real and fast — 3.8 seconds on a two-file branch diff, no LLM call, and it correctly pulled the added test contract with its file:line, named the changed file and selected npm test as the validation command; running that command exposed a genuine regression the branch had introduced. What it does not do is find the bugs itself: reading the same nine-line diff unaided surfaced both the breaking change to the existing discount code and a hardcoded 2027 epoch that silently disables a promo, neither of which appeared anywhere in QAMap's scenarios. It degrades on size — pointed at a real 14-file, 1783-line commit range in its own repository it returned a single scenario with an empty assertions list and an empty PR checklist. Useful as a deterministic handoff format and an anti-hallucination contract (it insists an unrun command is never a pass), not as an extra pair of eyes.
What is the QAMap PR QA SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install QAMap PR QA?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use QAMap PR QA with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.