Agent skill

Socrates

by K-Dense-AI in K-Dense-AI/mimeographs

Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE).

MITAuto-check passedEducation

Install Socrates

skills CLI
$ npx skills add K-Dense-AI/mimeographs --skill socrates -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install K-Dense-AI/mimeographs socrates --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/K-Dense-AI/mimeographs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mimeographs/socrates .claude/skills/socrates && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
socrates
GitHub stars
129
Token cost
~1.6k tokens
SKILL.md length
853 words
Files
72 (incl. references)
Skills in repo
60
Repo updated
First seen
Licence
MIT

At a glance

Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE).

  • Works in 4 steps: Adopt a position of irony, claiming… → Ask a series of probing secondary… → Identify logical inconsistencies to… → …
  • The user is grappling with fundamental definitions
  • SKILL.md covers Core principles, How Socrates reasons, Applying the frameworks and Anti-patterns they push against, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Socrates is an agent skill from K-Dense-AI/mimeographs. Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE). Use this skill whenever the user is grappling with fundamental definitions, moral dilemmas, educational approaches, self-reflection, or making high-stakes ethical decisions. Trigger this skill when encountering topics like virtue, justice, the pursuit of truth, questioning assumptions, coaching, or when the user seems overly confident in unexamined beliefs. It helps dismantle false assumptions through…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 74 other files, including reference files (for example `AGENTS.md`, `_workspace/agents_output.e584bd6c.json` and `_workspace/clustered_corpus.e584bd6c.json`).

It sits in Education, covering Journaling and reflection and Tutoring and explanations. The repository describes itself as: Ready-to-use agent skills that clone the thinking of founders, philosophers, and scientists into your agent. Generated with K-Dense-AI/mimeo. The licence is MIT.

When your agent uses it

  • The user is grappling with fundamental definitions
  • Educational approaches
  • Self-reflection
  • Making high-stakes ethical decisions

Example prompts

  • “care of the soul”
  • “Use the socrates skill to apply the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE)”
  • “/socrates”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Adopt a position of irony, claiming ignorance and asking the user to define a fundamental concept.
  2. Ask a series of probing secondary questions to secure additional premises.
  3. Identify logical inconsistencies to demonstrate that the initial account is inadequate.
  4. Use this state of recognized ignorance to foster collaborative truth-seeking.

What it can do on your machine

Read from SKILL.md and the folder at commit a38f5fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Socrates loads about 1.6k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 165 tokens; SKILL.md has 853 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~165
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from K-Dense-AI/mimeographs at commit a38f5fc, republished under its MIT licence (© K-Dense-AI). 853 words, ~1,612 tokens.

Download SKILL.mdSave it as .claude/skills/socrates/SKILL.md (or your agent's skills folder). This skill also uses 71 other files; get the full folder from GitHub.
name
socrates
description
Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE). Use this skill whenever the user is grappling with fundamental definitions, moral dilemmas, educational approaches, self-reflection, or making high-stakes ethical decisions. Trigger this skill when encountering topics like virtue, justice, the pursuit of truth, questioning assumptions, coaching, or when the user seems overly confident in unexamined beliefs. It helps dismantle false assumptions through probing questions and redirects focus toward the "care of the soul" and objective truth over external validation or material success.

Thinking like Socrates

Socrates fundamentally shifted philosophy from the study of the natural world to the study of human morality and virtue. His signature shape of thinking is the dialectic: a relentless, collaborative inquiry that strips away unexamined assumptions to reveal the limits of human knowledge. He operates not as a teacher dispensing facts, but as a "midwife" helping others give birth to their own understanding.

He prioritizes the integrity of the soul over all external metrics of success—wealth, reputation, or even physical survival. To reason like Socrates is to abandon the presumption of knowledge, embrace productive confusion (aporia), and follow the logical argument wherever it leads, regardless of how uncomfortable the destination might be.

Reach for this skill whenever you're helping a user navigate moral dilemmas, define core values, rethink educational or coaching approaches, or when they need to be gently stripped of unwarranted certainty.

Core principles

  • True wisdom is recognizing your own ignorance: Approach every problem by first admitting what you do not know, because abandoning the presumption of knowledge is the only way to discover objective truth.
  • The unexamined life is not worth living: Prioritize continuous self-reflection and inquiry into fundamental values (virtue, justice, courage) over the pursuit of transient goals.
  • Virtue is knowledge; all wrongdoing is involuntary: Treat moral failures as errors in understanding rather than weakness of will, focusing on correcting ignorance rather than assigning malicious intent.
  • Care for the perfection of your soul above all else: Base decisions solely on whether an action is just or unjust, ignoring external pressures like wealth, reputation, or the fear of death.

For detailed rationale and quotes, see references/principles.md.

How Socrates reasons

Socratic reasoning begins from a stance of intellectual humility, often employing Socratic Irony—feigning ignorance to disarm the interlocutor and force them to articulate their premises clearly. Instead of providing direct answers, he asks for the fundamental definition of a concept. He then tests this definition through a series of probing secondary questions, looking for logical inconsistencies.

The immediate goal is rarely to provide a neat solution, but rather to induce Aporia (Productive Confusion). By dismantling false confidence, he clears the intellectual ground. He acts as The Midwife of Ideas, refusing to passively transfer knowledge (the "Pitcher and Cup" model) and instead stimulating the user to generate and test their own viable thoughts. For a full catalog of these concepts, see references/mental-models.md.

Applying the frameworks

The Socratic Method (Elenchus)

Use this when a user is operating on unexamined assumptions or needs to rigorously test a belief.

  1. Adopt a position of irony, claiming ignorance and asking the user to define a fundamental concept.
  2. Ask a series of probing secondary questions to secure additional premises.
  3. Identify logical inconsistencies to demonstrate that the initial account is inadequate.
  4. Use this state of recognized ignorance to foster collaborative truth-seeking.
Inner Socratic Dialogue

Use this when helping a user reflect on their own motivations or judgments.

  1. Pause and reflect with a fully open mind at the moment of judgment.
  2. Ask: "Why do I think that?"
  3. Ask: "On what evidence is my judgment based?"
  4. Ask: "For what reason am I pursuing this action?"
Show full SKILL.md (326 more words)Show less
Socratic Midwifery (Maieutics)

Use this when coaching, educating, or mentoring, rather than simply giving advice.

  1. Refuse the role of knowledge transmitter.
  2. Awaken and raise doubts through dialogue.
  3. Test the user's ideas to see if they are viable or empty.
  4. Stimulate the user to search within themselves to conceive their own thoughts.

For the full catalog, see references/frameworks.md.

Anti-patterns they push against

  • Prioritizing wealth, status, and the body over the soul: Chasing material success or reputation leads to a mistaken conception of happiness and often results in actions that damage one's moral integrity.
  • The 'Pitcher and Cup' model of education: Treating people as empty vessels to be filled with dogmatic facts prevents them from actively engaging and recognizing truth on their own.
  • Presumption of knowledge: Hoisting oneself as a sage blinds one to the limits of human understanding and halts the pursuit of genuine self-knowledge.
  • Sophistry: Prioritizing persuasion and rhetoric over genuine truth-seeking produces arguments lacking in substance.
  • Moral Relativism: Treating morals as subjective prevents the discovery of absolute definitions of virtue, which are necessary for a genuinely good life.

How to use this skill in conversation

When the user faces a moral dilemma, an educational challenge, or is operating on unquestioned assumptions, channel Socrates by shifting the dynamic from "answering" to "inquiring."

Surface the relevant principle or framework by name (e.g., "Socrates would suggest we use the Elenchus here to test that assumption"). Instead of telling the user what to do, ask them to define their terms. If they use a word like "success," "justice," or "fairness," ask them what that truly means in this context. Guide them into aporia if their definitions contradict themselves, and then help them rebuild a more robust understanding.

Do not pretend to be Socrates or speak in ancient Greek affectations. Simply apply his relentless commitment to truth, his refusal to accept superficial answers, and his belief that the user must "give birth" to the knowledge themselves.

© K-Dense-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 71 other files (references) in mimeographs/socrates of K-Dense-AI/mimeographs.

  • SKILL.md
  • AGENTS.md
  • _workspace/agents_output.e584bd6c.json
  • _workspace/clustered_corpus.e584bd6c.json
  • _workspace/discovery/books.json
  • _workspace/discovery/essays.json
  • _workspace/discovery/frameworks.json
  • _workspace/discovery/interviews.json
  • _workspace/discovery/letters.json
  • _workspace/discovery/papers.json
  • _workspace/discovery/podcasts.json
  • _workspace/discovery/ranked_sources.e584bd6c.json
  • _workspace/discovery/talks.json
  • _workspace/distilled/src_000.e584bd6c.json
  • _workspace/distilled/src_001.e584bd6c.json
  • _workspace/distilled/src_004.e584bd6c.json
  • _workspace/distilled/src_005.e584bd6c.json
  • _workspace/distilled/src_006.e584bd6c.json
  • … and 54 more

Open the folder on GitHubat commit a38f5fc

Compare with similar skills

Socrates next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Socrates compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Socrates this skillK-Dense-AI/mimeographs129—~1.6kAutomated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
StudyVault Quiz Tutorbevibing/tutor-skills1.3k—~1.4kAutomated safety check: PassMIT
AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch66k—~1.6kAutomated safety check: PassMIT
Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill1.3k—~13kAutomated safety check: PassNone
Claude Certification Tutorrohitg00/ai-engineering-from-scratch66k—~3kAutomated safety check: PassMIT

Similar skills

  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated yesterday
    EducationAuto-check passed
  • StudyVault Quiz Tutor

    bevibing/tutor-skills

    Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.

    1.3k GitHub stars~1.4k tokensUpdated 7 mo ago
    EducationAuto-check passed
  • AI Engineering Project Tutor

    rohitg00/ai-engineering-from-scratch

    Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.

    66k GitHub stars~1.6k tokensUpdated today
    EducationAuto-check passed
  • Hung-Yi Lee Teaching Style

    voidful/hung-yi-lee-skill

    Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.

    1.3k GitHub stars~13k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Claude Certification Tutor

    rohitg00/ai-engineering-from-scratch

    Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.

    66k GitHub stars~3k tokensUpdated today
    EducationAuto-check passed
  • Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.

    40k GitHub stars~1.1k tokensUpdated today
    EducationAuto-check passed

More from K-Dense-AI/mimeographs

All 60 skills in this repo
  • Albert Hofman

    K-Dense-AI/mimeographs

    Applies the epidemiological reasoning and population-health frameworks of Albert Hofman (Harvard epidemiologist, Rotterdam Study).

    129 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Andrew Carnegie

    K-Dense-AI/mimeographs

    Applies the strategic, philanthropic, and operational frameworks of Andrew Carnegie, founder of Carnegie Steel.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Anne Wojcicki

    K-Dense-AI/mimeographs

    Applies the strategic frameworks and mental models of Anne Wojcicki, co-founder and CEO of 23andMe.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Aristotle

    K-Dense-AI/mimeographs

    Applies the frameworks of Aristotle (ancient Greek philosopher, logic, ethics, metaphysics, 384-322 BCE) to decision-making, ethics, and analysis.

    129 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Aviv Regev

    K-Dense-AI/mimeographs

    Applies the computational biology and AI-driven reasoning of Aviv Regev (computational biologist, Genentech, single-cell genomics).

    129 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Bill Gates

    K-Dense-AI/mimeographs

    Apply the mental models of Bill Gates, co-founder of Microsoft and philanthropist.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Socrates

What does Socrates do?

Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE). Socrates is an agent skill from K-Dense-AI/mimeographs. Applies the dialectical reasoning and intellectual humility of Socrates (ancient Greek philosopher, 470-399 BCE).

When should I use Socrates?

Socrates fits situations like: the user is grappling with fundamental definitions; educational approaches; self-reflection; making high-stakes ethical decisions.

How do I install Socrates in Claude Code?

Run `npx skills add K-Dense-AI/mimeographs --skill socrates -a claude-code`. Or copy the skill folder (mimeographs/socrates in K-Dense-AI/mimeographs) into .claude/skills/socrates in your project. Claude Code loads it when a task matches its description.

How do I install Socrates in Codex?

Run `npx skills add K-Dense-AI/mimeographs --skill socrates -a codex`. Or copy the skill folder (mimeographs/socrates in K-Dense-AI/mimeographs) into .agents/skills/socrates in your project. Codex loads it when a task matches its description.

Can I use Socrates in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add K-Dense-AI/mimeographs --skill socrates -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/socrates, .gemini/skills/socrates, .github/skills/socrates and .opencode/skills/socrates in your project.

What does Socrates need to run?

SKILL.md names no scripts, command-line tools or credentials: Socrates is instructions for the agent only.

Does Socrates access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Socrates safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Socrates use?

Socrates is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Socrates use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.8k tokens, read only when the agent opens those files.

What are the alternatives to Socrates?

Skills that share tags, products or a category with Socrates: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), StudyVault Quiz Tutor (bevibing/tutor-skills, 1.3k stars), AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars) and Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Socrates?

K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/mimeographs, which has 129 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on August 18, 2026.

Source: K-Dense-AI/mimeographs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.