experimentation
Skill10 starsChanged 6 days agoMITView on GitHub
When thinking cannot settle something, run a small, cheap, reversible test, learn from the result, and adjust. Use when a question stays open after thinking it through, or on /experimentation.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- realjaymes/marketingagentskillstheir own version, first seen Oct 21, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
- andreaskelm/pm-braintheir own version, first seen Oct 17, 2026
- nahid-sparktales/agent-dispatchertheir own version, first seen Sep 21, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- andreaskelm/pm-brain★ 235same name
- realjaymes/marketingagentskills★ 68same name
- nahid-sparktales/agent-dispatcher★ 59same name
- vindreshsingh/engineering-skills★ 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 repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- design-principlesSkill
- groupingSkill
- idea-qualitySkill
- info-foragingSkill
- investingSkill
- listeningSkill
- misfitsSkill
- motivationSkill
- needs-to-signalsSkill
- optionalitySkill
- perspectiveSkill
- purposeSkill
- testingSkill
- verify-before-shipSkill
- resume-deep-diveSkill
- review-resumeSkill
- inspiring-ideaSkill
- next-goalSkill
- side-quest-recommendSkill
- still-want-itSkill
- find-the-argumentSkill
- make-presentation-slideSkill
- agent-evalsSkill
- behavior-viewSkill
- black-boxSkill
- clean-arch-domainSkill
- mutation-testingSkill
- structure-viewSkill
- test-oracleSkill
- unit-testsSkill
- user-storiesSkill
- white-boxSkill
- negotiationSkill
- readableSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
5
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
- Distinctive: line 13
When thinking cannot settle something, run a small, cheap, reversible test, learn from the result, and adjust.
- Distinctive: line 23
Learn from the test on purpose: Before the test, define what you are trying to learn: state what result would change your decision and when …
- Distinctive: line 28
Optional extension: when fear blocks action: When fear rather than missing information is blocking action, make the feared outcome …
- Distinctive: line 36
Do not test when existing knowledge can settle the question or there is no time to learn from the result.
- Distinctive: line 38
Do not transfer experimental risk to others without their knowledge and agreement.
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
/experimentation
When thinking cannot settle something, run a small, cheap, reversible test, learn from the result, and adjust.
Principles
- Keep the test small, cheap, and reversible, so a wrong guess costs little and leaves room for the next test. Make it easy to stop or undo, and risk only what you can afford to lose. Start with the smallest test that could teach something, and try several paths cheaply instead of making one large bet.
- Learn from the test on purpose. Before the test, define what you are trying to learn: state what result would change your decision and when you will stop. After the test, let the evidence change your next action, including when the result is inconclusive.
Optional extension: when fear blocks action. When fear rather than missing information is blocking action, make the feared outcome concrete: what could go wrong, how could you prevent it, and how could you recover? Then choose a bounded first step. Research is the right move when missing information is the real blocker. A useful check is whether additional thinking can realistically resolve the uncertainty; if not, try a bounded experiment.
Boundaries.
- Do not test when existing knowledge can settle the question or there is no time to learn from the result.
- Do not transfer experimental risk to others without their knowledge and agreement; keep unavoidable risk small and let them decline.
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.