Skip to content

refactor(skills): redesign qa verification and tighten ralph wording - #619

Merged
baleen37 merged 3 commits into
mainfrom
worktree/drifting-sauteeing-lemur
Apr 15, 2026
Merged

refactor(skills): redesign qa verification and tighten ralph wording#619
baleen37 merged 3 commits into
mainfrom
worktree/drifting-sauteeing-lemur

Conversation

@baleen37

@baleen37 baleen37 commented Apr 15, 2026

Copy link
Copy Markdown
Owner

Summary

  • redesign /qa around verification-first PASS/PARTIAL/FAIL reporting and update its report template
  • add focused regression coverage for the new /qa contract and align the QA redesign plan/spec wording
  • tighten Ralph skill wording and record the latest autoresearch experiment outcomes

Tests

  • bats tests/skills/test_qa_verification_content.bats
  • bats tests/skills/test_qa_verification_content.bats tests/skills/test_skill_content.bats tests/frontmatter_tests.bats tests/integration/plugin_loading.bats
  • bash tests/run-all-tests.sh
  • ./.autoresearch/run.sh

Summary by CodeRabbit

  • New Features

    • QA workflow now focuses on implementation verification (golden path, key edge cases, obvious regressions) with deterministic scope resolution.
    • QA reports now verdict-first with structured output: verdict (PASS/PARTIAL/FAIL), scope source, verification summary, failed scenarios, evidence, and next actions.
  • Documentation

    • Updated QA skill documentation with new verification-first approach and explicit boundaries with the ship workflow.
    • Updated PRD documentation wording for clarity.

Test User added 3 commits April 15, 2026 18:18
@baleen37
baleen37 enabled auto-merge (squash) April 15, 2026 13:02
@baleen37
baleen37 merged commit 03b522d into main Apr 15, 2026
4 of 5 checks passed
@baleen37
baleen37 deleted the worktree/drifting-sauteeing-lemur branch April 15, 2026 13:02
@coderabbitai

coderabbitai Bot commented Apr 15, 2026

Copy link
Copy Markdown

Caution

Review failed

The pull request is closed.

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: d59ad97b-067f-4f6b-8144-63372343f4cd

📥 Commits

Reviewing files that changed from the base of the PR and between f9b29e1 and 72ce93d.

📒 Files selected for processing (7)
  • .autoresearch/autoresearch.jsonl
  • docs/superpowers/plans/2026-04-15-qa-verification-redesign.md
  • docs/superpowers/specs/2026-04-15-qa-verification-redesign-design.md
  • plugins/me/skills/qa/SKILL.md
  • plugins/me/skills/qa/templates/qa-report-template.md
  • plugins/ralph/skills/ralph/SKILL.md
  • tests/skills/test_qa_verification_content.bats

📝 Walkthrough

Walkthrough

This PR redesigns the /qa skill from exploratory bug-hunting to implementation verification with verdict-first outcomes (PASS/PARTIAL/FAIL). It introduces new specification and plan documentation, updates skill workflow and report template, adds validation tests, logs autoresearch runs, and includes minor PRD wording adjustments.

Changes

Cohort / File(s) Summary
QA Skill Redesign Specification
docs/superpowers/specs/2026-04-15-qa-verification-redesign-design.md, docs/superpowers/plans/2026-04-15-qa-verification-redesign.md
New specification and implementation plan for /qa redesign establishing verdict-first contract, scope resolution rules (plan → branch → user override), golden-path/edge-case/regression verification model, and explicit /qa vs /ship boundary enforcement.
QA Skill Implementation
plugins/me/skills/qa/SKILL.md, plugins/me/skills/qa/templates/qa-report-template.md
Rewritten skill documentation shifting from exploratory "Analyze → Explore → Report" to "Scope → Verify → Report" verification approach. Template restructured with verdict-first section, scope-source tracking, and verification summary organized by golden-path/edge-cases/regressions.
QA Verification Testing
tests/skills/test_qa_verification_content.bats
New Bats test suite enforcing skill language semantics, verdict/scope rules, /ship boundary strings, verdict-first template structure, and absence of old bug-hunt framing.
Autoresearch Tracking
.autoresearch/autoresearch.jsonl
Two new autoresearch runs appended (runs 26–27) with metrics and PRD wording refinement descriptions.
Minor PRD Updates
plugins/ralph/skills/ralph/SKILL.md
Wording simplifications to --no-prd flag description and userStories schema phrasing.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

Poem

🐰 From bug hunts wild to verdicts clear,
We verify what matters here—
Golden paths and edge-case thrills,
Reports with scope and truth-first skills!
No more "find all," just trust the flow,
And let the /ship decide to go. ✨

✨ Finishing Touches
📝 Generate docstrings
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch worktree/drifting-sauteeing-lemur

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant