Generates clear, actionable verification guides for QA testing of Positron bug fixes and features
62
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/positron-qa-verify/SKILL.mdAnalyzes GitHub issues and PRs to generate verification guides for manual QA testing.
gh) authenticatedCRITICAL: Run non-interactively without prompts.
AskUserQuestion - Always write to .claude/skills/positron-qa-verify/output/Issue number or URL:
4567#4567https://github.com/posit-dev/positron/issues/4567Run these in parallel with a single message containing multiple Bash tool calls:
gh issue view <number> --repo posit-dev/positron --json title,body,comments,url,labels,authorgh pr list --repo posit-dev/positron --search "<number>" --state all --json number,titleFetch primary PR details:
gh pr view <pr-number> --repo posit-dev/positron --json title,body,comments,additions,deletions,urlFetch all related PRs/issues mentioned in the body in parallel.
Only for PRs < 500 lines (additions + deletions from Step 3):
gh pr diff <pr-number> --repo posit-dev/positronSkip diff for large PRs - use PR description and comments instead.
Search comments for #1234 references, additional test scenarios, edge cases, and platform-specific notes.
Create markdown file in .claude/skills/positron-qa-verify/output/verify-issue-{number}-{timestamp}.md
See references/verification_guide.md for format and examples.
After generating the guide, offer to create a verification comment template.
Only when user accepts:
scripts/detect_versions.sh to auto-detect Positron and OS versionsComment format:
.claude/skills/positron-qa-verify/output/verify-issue-{number}-{timestamp}.mdscripts/detect_versions.shFast, silent version detection (max 4 seconds):
./scripts/detect_versions.shOutput:
{
"positronVersion": "2026.02.0",
"positronBuild": "10",
"osVersion": "macOS 26.2",
"detectionStatus": "success"
}Never prompts or shows errors - returns empty values on failure.
b87c504
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.