decocms/studio/jira-review
Claude Code and agent skill by decocms/studio
- community
Checking that the SKILL.md file is still in the repository.
Review the pull request a Jira issue already carries, QA it on the deploy preview, and record the verdict on the issue. Insert into the prompt of a Jira review or QA column rule.
Install
npx vskill@latest install decocms/studio/jira-reviewSKILL.md
jira-review — review what the other run built
Insert this into the prompt of the Jira column your team reviews in. It is the second of two runs: an earlier column implemented the issue and opened a pull request (jira-execute), and this one judges it.
It is ordinary text once inserted — read it, cut what does not apply to your team, add what does.
You are reviewing someone else's change to a Jira issue. The issue itself is above, web links included.
Find what you are reviewing
- The pull request is normally on the issue as a web link, put there by the run
that implemented it. If it is not, its branch is normally named for the issue key: gh pr list --search "<the issue key>" --state all.
- If there is genuinely no pull request, do not write one. Report that on the
issue and stop.
Review the code
- Check the branch out and read the diff (
gh pr diff <n>, then the files
around it). Does it do what the issue asks; is it reachable from the surface the issue names; does it break something next to it.
- Do NOT implement the fix yourself and do NOT open a pull request. A
reviewer that rewrites the change has reviewed nothing, and a second pull request on one issue is what a human then has to clean up. A small, unambiguous correction is a comment on the issue, not a commit.
QA it on the deploy preview
- The deploy bot comments the preview URL on the pull request
(gh pr view <n> --json comments); the issue's web links may carry it too. If no preview exists yet, poll until it does. A first request may wake a hibernating build; retry until you get real HTML.
- Exercise the behaviour and MEASURE it. Read the value back from the page
rather than inferring it from a name or a spec.
- Compare against production, not only against the spec: the live site is the
"before" and the preview is the "after". A difference you cannot see on both is not evidence. If production is unreachable from this pod, say so in your report rather than passing the card on an untested comparison.
- Capture before/after evidence with
qa-screenshot <url> <path>.png [--mobile],
on desktop AND mobile, and Read each file. A screenshot you never opened is not verification, and mobile is not desktop resized — plenty of these issues only reproduce on one of the two.
Record the verdict on the ISSUE
There is no card for anyone to read. A final message in this run is not a report.
JIRA_COMMENT_ADDposts your review (markdown, tables included). Open with
the verdict in ONE line — approved, or changes requested — naming the pull request and the head commit you reviewed (gh pr view <n> --json headRefOid), then the evidence, then the findings, each naming a file and line or a screenshot. The commit is what tells the next reader whether anything landed after your review.
- A finding is a defect you OBSERVED, not a preference. Say what you did, what
you expected, and what happened instead. If you found nothing, say that plainly rather than padding the list: an invented finding costs more than a missed one here.
- To show evidence, write each screenshot to
/app/org/output/<name>.pngand
reference it in that comment as  — it is uploaded to the issue and rendered inline. A before/after table of two images reads best.
JIRA_REMOTE_LINK_ADDadds the preview you reviewed (key: "preview") if the
implementing run did not already put it on the issue.
JIRA_ISSUE_GETre-reads the issue before you report — a person may have
edited the card, or answered a question on it, while you worked.
JIRA_ISSUE_TRANSITIONcarries the verdict: on a pass, the column your team
hands reviewed work to; on a fail, BACK to the column the implementing run works in. Do this LAST, after the comment is on the card — a transition with no comment beside it is the one nobody can act on. Then re-read the issue and confirm it landed where you meant — a transition's advertised destination is not always where it puts the card, and the failure is silent.
- If you cannot tell which column is which, say so in your comment and leave the
issue where it is. A card parked with an explanation is recoverable; one moved into the wrong column reads as a handoff nobody made.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/sandbox/image/skills/jira-review/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/decocms/studio/jira-review)