foundational-thinking
AGENTS.md0 starsChanged 4 months agoMITView on GitHub
Two agent skills, codified from classical method: - socratic-inquiry — use when a request turns on an abstract quality word (reliable, scalable, clean, better...) that nobody has defined, when a cause is asserted rather than demonstrated, or when a question presupposes its own answer. Not for choosing between named options. Dissolves an ill-formed question into a well-formed one. - scholastic-disputation — use when a choice between two or more named options is owed, including when their success criteria are still…
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- scholastic-disputationSkill
- socratic-inquirySkill
- using-foundational-thinkingSkill
The file
Files
foundational-thinking
Two agent skills, codified from classical method:
socratic-inquiry— use when a request turns on an abstract quality word (reliable, scalable, clean, better...) that nobody has defined, when a cause is asserted rather than demonstrated, or when a question presupposes its own answer. Not for choosing between named options. Dissolves an ill-formed question into a well-formed one.scholastic-disputation— use when a choice between two or more named options is owed, including when their success criteria are still vague; also when conflicting recommendations need adjudicating, when your own call is challenged, or when a decision must be written down and defended later. Builds a determination that survived its objections.
Invoke either by name; the runtime loads the body on demand. Full skill definitions are in
skills/, and the source material plus the routing logic between the two methods is in
principles/README.md — both relative to the foundational-thinking repo root, which is not
necessarily the directory this file was loaded into.
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.