grill-science-with-docs
Skill1 starsChanged 5 months agoNo licenceView on GitHub
A relentless interview that sharpens a scientific claim and closes the loop on it, producing durable records as it goes — a Claim Record (what is asserted, what decision it serves, what would falsify it, what is already known), an Evidence Ledger (what the source actually supports vs what you assumed, with every correction logged), and a Findings Record (what was settled, what was ruled out, what remains open). Four phases — FRAME, GROUND, TEST, CLOSE — each behind a gate that requires human confirmation. Use when forming or testing a hypothesis, analysing evidence you did not generate, extending someone's preliminary result, or deciding whether a line of enquiry is worth continuing.
In this repository24 other files it gives its agents.
- browser-quote-shopSkill
- catalog-to-trackerSkill
- clean-meeting-noteSkill
- data-dictionarySkill
- epub-to-kindleSkill
- hub-from-outlineSkill
- logseq-to-obsidianSkill
- log-to-journalSkill
- md-to-docxSkill
- md-to-pptx-editableSkill
- morning-planSkill
- normalize-date-filenamesSkill
- note-to-mocSkill
- passport-photo-checkSkill
- photo-print-layoutSkill
- photo-year-collageSkill
- ppt-template-to-cssSkill
- project-mgrSkill
- review-weekSkill
- session-to-skillSkill
- skill-auditorSkill
- syllabus-to-knowledge-treeSkill
- tax-history-trackerSkill
- vault-entity-noteSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — 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.

