potter-self
Skill7 starsChanged 11 days agoLicence not identifiedView on GitHub
PromptPotter L4 self-optimization — Claude and the operator read a round's artifacts, diagnose why candidates underperformed, and decide what evidence to buy before another paid round. Use at the round-1 gate or a halted loop; on L4, `promptpotter-self`, L1 stall, mode collapse, flat stratification, near-duplicate candidates, candidates ignoring the critique or task_context, l1_generate parse failures, tuning `l1_generate/1` in potter's pipeline.yaml; on opening a `round_NNNN.json`, "why did L1 do that?", "improve the optimizer prompt"; when weighing the next experiment (panel width, seed count, cells, is a result real). Also AUTHORED MODE ("you are the proposer", "you write the arms", "hand-authored round") and the tuning thread ("continue the tuning", "work the board", "next card", "get the price down"). Fires even when "L4" is not said.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- webapp/CLAUDE.mdCLAUDE.md
- digestSkill
- potter-boxSkill
- potter-releaseSkill
- potter-runSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.