empirical-prompt-tuning
Skill0 starsChanged 4 months agoLicence not identifiedView on GitHub
Evaluate text instructions written for agents (a skill, a slash command, a task prompt, a CLAUDE.md section, a rules file, or a code generation prompt) through an unbiased separation of 3 roles (tuner / executor / checker), and improve them iteratively with a fixed friction taxonomy and a statistical adoption gate. Converged verification assets are turned into portable fixtures. Use when the user says "empirical-prompt-tuning", "prompt tuning", "I want to measure instruction quality", "I want to harden this skill", "why is this prompt hard to follow", or "check whether the rule is being obeyed". It is the sister skill of `trigger-eval` (which measures the selection layer, description to firing) and covers the body layer, the quality of execution.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- H-ymt/skillstheir own version, first seen Nov 8, 2026
- h-wata/claude-skillstheir own version, first seen Oct 13, 2026
- mizchi/skillstheir own version, first seen Oct 2, 2026
- ivgtr/claude-skillstheir own version, first seen Jul 21, 2026
- 15yotsuka/claude-skillstheir own version, first seen May 22, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- mizchi/skills★ 369same name
- 15yotsuka/claude-skills★ 0same name
- h-wata/claude-skills★ 0same name
- H-ymt/skills★ 0same name
- ivgtr/claude-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 repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- releaseSkill
- artifactsSkill
- attack-reviewSkill
- brainstormSkill
- briefSkill
- codebase-reviewSkill
- commitSkill
- context-auditSkill
- cycleSkill
- decision-journalSkill
- design-generateSkill
- design-guideSkill
- design-lintSkill
- design-scaffoldSkill
- design-validateSkill
- doc-auditSkill
- doc-checkSkill
- doc-writeSkill
- generate-review-rulesSkill
- github-issueSkill
- goal-decompositionSkill
- goal-loopSkill
- handoffSkill
- investigateSkill
- issueSkill
- iterateSkill
- ledgerSkill
- loop-triageSkill
- migrate-cycles-to-plansSkill
- mockup-diffSkill
- parallel-cycleSkill
- plan-implementSkill
- plan-reviewerSkill
- planSkill
- problem-solvingSkill
- refactorSkill
- review-depsSkill
- review-testingSkill
- sharedSkill
- skill-improveSkill
- skill-interface-auditSkill
- skill-regressionSkill
- skill-reviewerSkill
- spec-verifySkill
- sweep-fixSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- trigger-evalSkill
- using-workflowSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 12 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
6
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.