agentleFS
0xfurai0xfurai/peekaping/.agents/skills/ticket-review/SKILL.md

ticket-review

Skill1.2k starsChanged 17 days agoMITView on GitHub

Review a ticket's branch, Claude's or your own, against the ticket: every acceptance criterion implemented and tested, gaps fixed, full local run green.

3 other projects use a version of this.

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 1 mentionNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the 0xfurai/peekaping repository that our weekly crawl found: only 2 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. elmoritz/agents-skills-setup★ 4same name
    2. SUDARSHANCHAUDHARI/QACraft★ 2same name
    3. precise-alloy/ritus★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the branch is the user's own work, the brief says to fix it the way they built it.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 3 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

Ticket: review

Start with setup.

1. Pin the criteria

Use the acceptance criteria in the ticket's ## Agent plan. Without a plan (the user implemented straight from the ticket), write them from the ticket the way PLAN.md defines them: one observable behaviour per requirement, numbered AC1, AC2, and so on. With no ticket at all, take them from the PR description or ask the user.

Also pin the branches: the plan's PR stack, or the ticket's branches as they are, bottom to top. Uncommitted changes in the checkout may be the user's unfinished work: ask whether they belong in it, and leave them untouched until they answer.

Done when: you have a numbered list of criteria, the branch list, and a clean or explained working tree.

2. Check

Brief an agent (DELEGATE.md) with only pointers: the ticket key, the criteria, the branch list, and git diff origin/main...<top branch>. Its task:

For each acceptance criterion, report: implemented (file:line), tested (test name), or missing. Then list: changes outside the criteria; likely bugs; GLOSSARY terms misused; UI strings missing from any of the 45 locale files; code that brings back MongoDB storage (ADR 0001: it was removed; the MongoDB monitor type and bun db import-mongo stay). Quote the criterion for each finding. Under 400 words.

3. Fix

Sort the findings, then brief one agent (DELEGATE.md) with every real one: missing or weak tests (red first, as in TESTING.md), missing translations, bugs, code that brings back MongoDB storage. It commits each fix on the branch it belongs to and carries it up the stack (STACK.md).

When the branch is the user's own work, the brief says to fix it the way they built it. A finding whose fix would change their approach or scope goes to the user first, with the brief in PLAN.md.

The same agent then runs the full local run in TESTING.md on each branch merged with origin/main. Repeat the check until it comes back clean.

Done when: every criterion has code and test evidence in a table, no finding is open, and the full local run passes.

Show the user the table. Run alone, end by telling them the next step: /ticket <PP-n> from pr.

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.