agentleFS
Sign inStart free
ccomkhjccomkhj/skills/socrates/SKILL.md

socrates

Skill10 starsChanged 19 days agoMITView on GitHub

Socratic interrogation of the user's own recurring, unsupported belief, mined from their past Claude Code prompts, ending in aporia and a short action debrief. Targets a personal premise, not a plan (grilling) or a problem frame (first-principles).

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feynman and brainstorm.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • neurofooSkill

    feynman

    Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or preparing to teach.

    Also in 3 projects that use this

  • nicolasestremSkill

    brainstorm

    Structured idea generation and solution exploration with systematic analysis.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Very specific:

    Run python3 -I ${CLAUDE_SKILL_DIR}/scripts/collect.py [--all] [--days N] (default: this project's last 10 sessions).

    line 11
  2. Distinctive:

    When the user concedes, say "Aporia.", reveal the premise, and stop questioning.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Socrates

  1. Run python3 -I ${CLAUDE_SKILL_DIR}/scripts/collect.py [--all] [--days N] (default: this project's last 10 sessions). Add this session's prompts and any topic in the arguments.
  2. Find one premise the user keeps relying on without support. Keep it to yourself. If none is evident, say so and ask for a topic; never invent one.
  3. Interrogate: one counter-question per turn, each quoting the user's own words with its date. No answers, reassurance, or lectures. Never quote secrets. Reply in the user's language.
  4. When the user concedes, say "Aporia.", reveal the premise, and stop questioning. The user can quit anytime (no debrief then). After ~7 questions without aporia, stop and say where it was heading.
  5. Debrief: three things Socrates would tell them; what they had wrong; the question they really needed to answer; one change for today, split into three steps for this week.
  6. Offer (never automatic) to save the premise, real question, and action as one WikiBrain memory note per ~/personal/WikiBrain/GUIDELINES.md, with no transcript quotes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free