pr-audit
Skill292 starsChanged 2 months agoEUPL-1.2View on GitHub
Prüft Pull Requests interner und externer Contributor im KoliBri-Repo gegen ihr verlinktes Issue und führt die Folgeschritte aus. Befehle - `audit` (Standard, schreibt nichts) listet ohne PR-Angabe zuerst alle offenen, reviewbereiten und grünen PRs zur Auswahl auf (alle oder je Contributor, sequenziell oder parallel per Subagent) und liefert danach eine Ampel-Tabelle mit Status (Draft, Ready, Gemergt, Geschlossen), Gesamtstatus (grün, gelb, rot) und den Spalten "Minimalistisch & korrekt zum Issue", "Sauber & ordentlich" und "Sicher" (warn, hint, ready), dazu Out-of-Scope-Änderungen, Folgepunkte und Label-Empfehlungen; das Audit schließt die Code-Kommentar-Prüfung nach der Entscheidungs-Kathedrale aus Abschnitt 4.4 ein (keine Historien- oder Redundanz-Kommentare, Erläuterungen nur so wenig wie unbedingt nötig); `comment` schreibt je offenem PR einen Kommentar in der Sprache des PRs an den Autor, was im Scope des Issues bis Grün zu tun ist; `tickets` legt Folge-Issues an, die den PR als Ursprung nennen; `consolidate` setzt die Folgepunkte gemergter PRs, die ihr ursprüngliches Issue vervollständigen, in einem Sammel-PR um, der die zugehörigen Tickets schließt; `labels` setzt die empfohlenen `release:*`-Labels. Nutze diesen Skill immer, wenn der Nutzer PRs von Internen, Externen, Contributorn oder der Community prüfen, kommentieren, labeln oder daraus Folge-Issues oder einen Sammel-PR machen will - auch bei Formulierungen wie "sind die PRs korrekt und sicher", "review die PRs von <Name>", "gibt es einen neuen Stand bei den PRs", "ist da Schadcode drin", "ist der PR mergebar", "Ampel für die PRs", "prüfe die Code-Kommentare im PR", "fordere den Autor zur Nachbesserung auf", "kommentiere den PR", "leg die Folgetickets an", "setz die Nachbesserungen der gemergten PRs in einem PR um", "korrigier die Release-Labels" oder wenn eine Liste von PR-Links ohne weitere Anweisung kommt.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- marcellocurto/skillstheir own version, first seen Nov 8, 2026
- selfxyz/selftheir own version, first seen Oct 8, 2026
- akitaonrails/my-skillstheir own version, first seen Sep 17, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- selfxyz/self★ 1.3ksame name
- akitaonrails/my-skills★ 283same name
- marcellocurto/skills★ 3same 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- issue-bewertenSkill
- migrate-to-skeletonSkill
- release-integrationSkill
- skeleton-reviewSkill
- theme-redundancy-checkSkill
- triage-contributor-ticketsSkill
- zero-visual-delta-handoffSkill
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.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“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.
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
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.

