hypothesis-validation
Skill13 starsChanged 3 months agoMITView on GitHub
Given a hypothesis, take the necessary investigation steps to validate, invalidate, or reach an inconclusive result for the hypothesis.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- deep-investigationSkill
- on-call-handoffSkill
- suggest-follow-upsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
After identifying possibly relevant context, dig deep into the most relevant pieces of context to gather enough evidence to validate, …
- Distinctive: line 32
After gathering enough evidence, draw a final conclusion about the hypothesis.
- Distinctive: line 40
Do not use this skill to run a full investigation.
≈ “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
Hypothesis Validation
Investigate the related context for a given hypothesis holistically. Record evidence and conclude whether the hypothesis is validated, invalidated, or inconclusive.
Procedure
1: Context hydration
Scan the conversation for:
- alert or incident metadata
- service names, environment names, region hints
- timestamps or time ranges
- symptoms (errors, latency, downtime)
- links to external pieces of context
The goal here is getting a quick hydration of possibly relevant context for the hypothesis before doing a deeper dive.
2: Dig deep
After identifying possibly relevant context, dig deep into the most relevant pieces of context to gather enough evidence to validate, invalidate, or reach an inconclusive result for the hypothesis.
Record findings as you dig. Follow the Evidence rules in the agent instructions. Call evidence_record, evidence_remove, and evidence_list as those rules say.
3: Draw conclusions
After gathering enough evidence, draw a final conclusion about the hypothesis. The conclusion for the hypothesis should be "validated", "invalidated", or "inconclusive". Include a description that cites the most important pieces of evidence used to draw the conclusion.
Result
A synthesized conclusion for the hypothesis.
Boundaries
- Do not use this skill to run a full investigation. Use the deep investigation skill.
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.