using-foundational-thinking
Skill0 starsChanged 4 months agoMITView on GitHub
Use when starting any conversation - establishes when to check socratic-inquiry and scholastic-disputation before responding, so they aren't only invoked when they happen to occur to you.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sudeepgupta90/my-ai-marketplaceword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- sudeepgupta90/my-ai-marketplace★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- scholastic-disputationSkill
- socratic-inquirySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
If you were dispatched as a subagent to execute a specific task, ignore this skill.
- Very specific: line 11
If you think there is even a 1% chance socratic-inquiry or scholastic-disputation applies to what you are about to do, you ABSOLUTELY MUST …
- Distinctive: line 15
IF ONE OF THESE SKILLS APPLIES, YOU DO NOT HAVE A CHOICE.
- Distinctive: line 46
If a request has both a named-option choice and an undefined quality word (e.g.
≈ “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.
Files
<SUBAGENT-STOP>
If you were dispatched as a subagent to execute a specific task, ignore this skill.
</SUBAGENT-STOP><EXTREMELY-IMPORTANT>
If you think there is even a 1% chance `socratic-inquiry` or `scholastic-disputation`
applies to what you are about to do, you ABSOLUTELY MUST invoke it via the `Skill` tool
before proceeding.IF ONE OF THESE SKILLS APPLIES, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
</EXTREMELY-IMPORTANT>
The rule
Check the two conditions below before doing the work, not after. If it turns out neither applies, proceed normally — you don't need permission to skip them.
socratic-inquiry— the request turns on an abstract quality word (reliable, scalable, secure, robust, maintainable, clean, fast, simple, better, production-ready...) that nobody has defined; or a cause is asserted rather than demonstrated ("the bug is X, go fix X"); or a question presupposes its own answer ("which of these should we delete?"). Not for choosing between named options — that's the other skill.scholastic-disputation— a choice between two or more named options is owed ("X or Y?", "which should we use?"), including when their success criteria are still vague; or conflicting recommendations need adjudicating; or your own call is challenged; or a decision needs to be written down and defended later.
Then announce "Using [skill] to [purpose]" and follow it exactly.
When a process skill also applies
scholastic-disputation and socratic-inquiry take priority over process skills like
brainstorming or systematic-debugging whenever their own trigger condition is present in
the same request — even if the request is also framed as brainstorming or debugging:
- A named-option choice in the request goes to
scholastic-disputationfirst, even under "let's brainstorm" framing — brainstorming's context-gathering happens inside disputation's own process (stating each option's case), not as a separate phase before it. - An undefined quality word with no options named goes to
socratic-inquiryfirst, to get the term defined before brainstorming or debugging builds on an assumed meaning. - If a request has both a named-option choice and an undefined quality word (e.g. "a
more scalable X — A or B?"), it goes to
scholastic-disputationalone — the equivocal term gets pinned down inside disputation's own distinguo step, not resolved separately first.
Red flags
These thoughts mean STOP — you're about to supply a definition or a verdict nobody gave you:
| Thought | Reality |
| "I know what 'robust' means here" | A familiar meaning is not the user's meaning. Check. |
| "I'll just pick the sensible option" | If it's a named-option choice, that's scholastic-disputation's job. |
| "The bug is obviously X" | An asserted cause is a hypothesis, not a finding. Check. |
| "This is just a quick question" | Quick questions can still turn on undefined words. Check. |
| "I already explained my reasoning" | Explaining a verdict isn't the same as having disputed it. |
User instructions
User instructions (CLAUDE.md, direct requests) take precedence over this skill, which in turn overrides default behavior. Only skip these checks when the user has explicitly told you to.
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.