failure-analyzer
Skill0 starsChanged 48 days agoMITView on GitHub
Diagnose reproducible failures from logs and state evidence, separating observed facts from hypotheses.
In this repository9 other files it gives its agents.
- content-qaSkill
- eval-engineering-liteSkill
- evidence-contentSkill
- faq-builderSkill
- meeting-to-actionsSkill
- project-handoffSkill
- requirement-clarifierSkill
- research-synthesizerSkill
- workflow-plannerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use when a test, deployment, retrieval or workflow step fails and evidence is available.
- Distinctive: line 29
Run the smallest test, update the diagnosis and preserve failures as regression cases.
- Distinctive: line 30
Only then propose a fix and re-run the original failing path.
- Very specific: line 34
If the failure cannot be reproduced, mark cause UNKNOWN and specify missing observation.
- Very specific: line 42
Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance.
≈ “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
Failure Analyzer
Purpose
Choose the smallest informative next experiment, not a speculative rewrite.
When to Use
Use when a test, deployment, retrieval or workflow step fails and evidence is available.
Inputs
expected, observed, logs, reproduction_steps, recent_changes.
Outputs
symptom, likely_causes[], evidence[], unknowns[], next_experiment, regression_case.
Workflow
- Reproduce the failure and capture exact command, version, environment and symptom.
- Separate observed facts from possible causes.
- Rank hypotheses by evidence and choose one discriminating read-only or reversible experiment.
- Run the smallest test, update the diagnosis and preserve failures as regression cases.
- Only then propose a fix and re-run the original failing path.
Failure Handling
If the failure cannot be reproduced, mark cause UNKNOWN and specify missing observation. Do not edit baselines to manufacture a pass.
Example
synthetic_unverified: retrieval returns zero matching chunks; inspect chunking and access filters before prompts.
Tests
Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance. This is a structural test, not model-quality evidence.
Limitations
Logs may omit the causal event; do not claim certainty from correlation alone.
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.