incident-review
Skill5 starsChanged 2 months agoMITView on GitHub
find why something broke with an agent doing the reading, without letting it write the story
5 other projects use a version of this.
Adopted by
Most recently taken up by
- guang-lee-cn/scaffold-skillstheir own version, first seen Nov 8, 2026
- apokamo/kajitheir own version, first seen Nov 8, 2026
- feverZHONG/liya-incident-reviewtheir own version, first seen Oct 8, 2026
- Tuteliq/claude-plugintheir own version, first seen Aug 10, 2026
- fabianmagrini/skillstheir own version, first seen May 10, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- apokamo/kaji★ 16same name
- guang-lee-cn/scaffold-skills★ 2same name
- fabianmagrini/skills★ 1same name
- feverZHONG/liya-incident-review★ 0same name
- Tuteliq/claude-plugin★ 0same 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.
- agent-budgetSkill
- code-reviewSkill
- commit-disciplineSkill
- dependency-checkSkill
- eval-before-mergeSkill
- plan-firstSkill
- safe-refactorSkill
- test-firstSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
read-only first: no fixes during the review.
- Distinctive: line 13
timeline from evidence: every line points at a log entry, a commit or a trace.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
incident-review
after something breaks, the agent is fast at the reading and too quick with the cause. its theory arrives fluent and mostly right, and mostly is the problem. so:
- read-only first. no fixes during the review. the scope fence (patterns/guardrails.md) is empty: it reads logs, diffs and the run journal, and touches nothing.
- timeline from evidence. every line points at a log entry, a commit or a trace. a line it can't point at is a guess - mark it and keep going.
- reproduce before you name a cause. a red test that fails the way it failed live (test-first). until then the cause is a lead.
- split trigger, cause and gap. what set it off, why that broke things, and which check should have caught it. then who else calls the broken path (dependency-check).
- close the gap, not just the bug. the fix goes through the loop like any change; the gap becomes an invariant in a spec or a line in eval-before-merge's bar.
the review ends with two artifacts: the red test, and the check that was missing. a write-up with neither is a story about the incident.
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.