agentleFS
rubixkube-iorubixkube-io/rubixkube-for-ai/skills/changes/SKILL.md

changes

Skill1 starsChanged 35 days agoMITView on GitHub

Changes to incidents, recorded under the person's name: report a new incident, correct one, close one, answer what fixed it, run the RCA again, comment. Use when the person wants to create or close an incident, retry an RCA, or leave a note for the team.

3 other projects use a version of this.

Adopted by

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. JiHong88/suneditor★ 2ksame name
    2. tykisgod/quick-question★ 12same name
    3. UltralayerHQ/ultralayer-plugin★ 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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    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:

    Every write is recorded under the signed-in person's name, so confirm before each one: show the exact title, severity and environment (or …

    line 31
  2. Distinctive:

    Never close an incident because it looks quiet.

    line 33

“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

When to use

  • "Report an incident: checkout is slow" / "Create an incident for the DB failover"
  • "Close INC-…" / "It was the rollback that fixed it" / "Run the RCA again"
  • "Add a comment: we found the OOM at 03:12"

Tools

  • report_incident(environment_id, message, severity, where?, description?). The answer carries the new incident id, the console link and a note that the RCA runs in the background: check get_incident after a few minutes, then get_rca.
  • edit_incident(incident_id, message?, severity?, affects?): only what changes.
  • close_incident(incident_id) when it is resolved.
  • get_incident_resolution then answer_incident_resolution(incident_id, choice, note?): choice is a candidate number, no_change if it recovered on its own, or other with a note.
  • retry_rca(incident_id) for a failed or poor RCA. It goes back in the queue; the new RCA takes a few minutes.
  • post_comment(kind, id, body, reply_to?) on an incident, Task or RCA. Markdown. Write for the team: findings and evidence, not the chat.

Rules

Every write is recorded under the signed-in person's name, so confirm before each one: show the exact title, severity and environment (or the comment text) and wait for a yes. Never close an incident because it looks quiet; close it when the person says it is resolved. Do not promise an RCA result; say when to check back.

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.