agentleFS
Sign inStart free
gonimargonimar/claude-web-studio/skills/qa-plan/SKILL.md

qa-plan

Skill4 starsChanged 46 days agoMITView on GitHub

Creates the QA plan for a sprint or feature — maps each story's acceptance criteria to test levels/tools/files, test data and environment, regression set, quality risks; writes production/sprints/qa-plan-NN.md. Run at sprint start.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use asset-spec, create-control-manifest and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +7 more from lilangMax

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When HEAD is a story branch, name it and ask one AskUserQuestion: switch to the default branch and commit there (Recommended — a …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

QA Plan

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

Template test-plan.md; the project's test-strategy.md (missing → /test-setup first). In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.

Phase 1: Stories

Sprint/feature → stories → acceptance criteria.

Phase 2: Matrix

Criterion → level (unit/integration/contract/e2e/security/a11y/perf) → tool → file → owner agent; test data; regression set; risks (test-engineer via Task — effort estimate). A criterion no level can automate — a visual or editorial judgement, a third-party flow with no sandbox, a physical device or a real e-mail inbox — gets level manual (a value of the template's Level column), with the steps, the tester and the evidence to keep (a screenshot, a log line) in the row's Manual (steps · tester · evidence) column (template test-plan.md; — on automated rows), and a manual flag the plan's risks section counts ("N criteria manual"). It is never dropped from the matrix, never assigned a tool that cannot test it, and never marked covered by a neighbouring automated test.

Phase 3: Write

Show the matrix as a table in the chat, then "May I write production/sprints/qa-plan-NN.md?" — one AskUserQuestion: write (Recommended) · show the draft/diff first · not now. After the "write" answer: touch .claude/.write-consent (rule 7 — the consent-guard hook checks the marker).

Phase 4: Commit (documents lane)

Right after the write, one commit gate (rule 7 (4), .claude/docs/git-workflow.md § Documents): docs: qa plan NN (docs: qa plan F-NNN for a feature), staging exactly production/sprints/qa-plan-NN.md. Record the gate before asking — <hooks>session-state.sh set Gate "/qa-plan Phase 4: commit?" — and clear it after the answer (<hooks>session-state.sh set Gate "—").

  • On the default branch when no story work is in progress (the normal case at sprint start): one AskUserQuestion — commit (Recommended) · leave uncommitted.
  • When HEAD is a story branch, name it and ask one AskUserQuestion: switch to the default branch and commit there (Recommended — a pipeline-wide document) · commit here (the document belongs to this story) · leave uncommitted.
  • The plan names test files; it does not write them — they are written by /dev-story in the story's branch and never ride the docs: commit.

Nothing is committed without the answer.

Verdict: READY. Next step — one AskUserQuestion: /dev-story (Recommended) · /sprint-plan adjustments · stop here.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free