Agent skill

Pinker Teach For Understanding

by AHepi in AHepi/DeepReason

Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision.

MITAuto-check passedEducation

Install Pinker Teach For Understanding

skills CLI
$ npx skills add AHepi/DeepReason --skill pinker-teach-for-understanding -a claude-code

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

GitHub CLI
$ gh skill install AHepi/DeepReason pinker-teach-for-understanding --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/AHepi/DeepReason.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pinker-teach-for-understanding .claude/skills/pinker-teach-for-understanding && 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
pinker-teach-for-understanding
GitHub stars
141
Token cost
~1.8k tokens
SKILL.md length
912 words
Files
3 (incl. references)
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision.

  • Works in 8 steps: Define an observable destination → Diagnose the learner model → Decompress expert chunks → …
  • The user explicitly requests Pinkers approach to teaching
  • SKILL.md covers Choose the mode, Build the lesson, Produce useful outputs and Maintain the attribution…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pinker Teach For Understanding is an agent skill from AHepi/DeepReason. Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision. Use when the user explicitly requests Pinker's approach to teaching, invokes this skill, wants a difficult idea explained to a specified audience, or asks for a lesson, tutoring sequence, course segment, or teaching audit grounded in his work. Describe this as Pinker-informed teaching, not as a validated pedagogy created by Steven Pinker.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/teaching-evidence.md` and `references/teaching-patterns.md`).

It sits in Education, covering Tutoring and explanations. The licence is MIT.

When your agent uses it

  • The user explicitly requests Pinkers approach to teaching
  • Invokes this skill
  • Wants a difficult idea explained to a specified audience
  • Asks for a lesson

Example prompts

  • “/pinker-teach-for-understanding”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Define an observable destination
  2. Diagnose the learner model
  3. Decompress expert chunks
  4. Construct a phenomenon-first explanation
  5. Make epistemic structure visible
  6. Require learner reasoning
  7. Use feedback diagnostically
  8. Revise in two passes

What it can do on your machine

Read from SKILL.md and the folder at commit 9607fba. 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

Pinker Teach For Understanding loads about 1.8k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 912 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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 AHepi/DeepReason at commit 9607fba, republished under its MIT licence (© AHepi). 912 words, ~1,828 tokens.

Download SKILL.mdSave it as .claude/skills/pinker-teach-for-understanding/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
pinker-teach-for-understanding
description
Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision. Use when the user explicitly requests Pinker's approach to teaching, invokes this skill, wants a difficult idea explained to a specified audience, or asks for a lesson, tutoring sequence, course segment, or teaching audit grounded in his work. Describe this as Pinker-informed teaching, not as a validated pedagogy created by Steven Pinker.

Pinker: Teach for Understanding

Produce a change in what the learner can reconstruct and use, not merely a smooth presentation. Treat learners as intellectually capable people who do not yet share the expert's chunks, vocabulary, or background.

Choose the mode

  • Explain the method: State Pinker's direct advice, his observable teaching practices, this workflow's derivations, independent instructional evidence, and important limits separately.
  • Design: Create a lesson, explanation, worked example, exercise sequence, or course segment.
  • Teach: Run a responsive tutoring exchange. Ask one useful diagnostic at a time and adapt to the learner's response.
  • Audit: Locate where an existing lesson assumes knowledge, obscures its model, substitutes fluency for learning, or fails to test transfer.

Read references/teaching-evidence.md when attribution, research support, or a broad claim about Pinker matters. Read references/teaching-patterns.md for ready-to-use designs and audits.

Build the lesson

1. Define an observable destination

Name the phenomenon or consequential question and the performance expected afterward. Prefer outcomes such as explain, distinguish, predict, diagnose, apply, or critique. Do not use “understand” alone.

2. Diagnose the learner model

Establish the audience, purpose, prior knowledge, likely misconceptions, language needs, accessibility needs, time, and setting. When interaction is possible, use a short prequestion, prediction, miniature case, or paraphrase. Do not assume that imagining a novice defeats the curse of knowledge.

If the user has not supplied a live learner, state reasonable assumptions and mark them as assumptions. Provide diagnostic questions the user can run later.

3. Decompress expert chunks

Write down:

  • the central claim in one sentence;
  • the causal or logical chain, one link at a time;
  • indispensable terms, acronyms, premises, and referents;
  • prerequisites classified as known, teach now, or defer;
  • a concrete instance for every important abstraction.

Define necessary technical vocabulary at first useful contact. Do not purge terminology that the learner must eventually command.

4. Construct a phenomenon-first explanation

Use this default arc when it fits:

  1. Present a real observation, question, demonstration, case, or paradox.
  2. Connect it to something the learner already knows.
  3. Show a concrete case.
  4. Name the general principle.
  5. Walk through the mechanism or reasoning without hidden steps.
  6. State the conclusion, scope, and live uncertainty.

Pair generalizations with examples and state what each example demonstrates. For an analogy, map the corresponding parts and identify where the analogy stops working. Do not use an entertaining analogy as a substitute for the mechanism.

5. Make epistemic structure visible

Distinguish claim, evidence, inference, assumptions, alternative explanations, uncertainty, and what could change the conclusion. Separate correlation from causation and an illustration from evidence. Preserve genuine controversy while staging detail so that a novice first gains a defensible orientation.

6. Require learner reasoning

Include at least one immediate check. For a lesson of roughly ten minutes or more, or any multi-part explanation, use checks at more than one level:

  • Reconstruction: explain the mechanism in the learner's own words;
  • Discrimination: distinguish it from a tempting near-miss;
  • Prediction: infer an outcome before it is revealed;
  • Application: use it in a new case;
  • Critique: identify an assumption, counterexample, or rival account.

Do not use “Does that make sense?” as the only check. Recognition, assent, and verbal familiarity are weak evidence of learning.

Show full SKILL.md (386 more words)Show less
7. Use feedback diagnostically

Keep feedback to the learner separate from evidence for the teacher.

Give the learner specific information about the target, the current gap, and a useful next move. For the teacher, collect errors, paraphrases, pauses, questions, transfer attempts, or assessment results that reveal where the model failed.

If no representative learner has tried the explanation, say that it is untested. Put this in a planning or handoff note rather than inside a standalone learner-facing artifact. Never invent learner feedback or claim the lesson has been validated.

8. Revise in two passes

First repair content: truth, model, evidence, missing prerequisites, alternatives, and qualification. Then repair presentation: sequence, examples, transitions, sentence load, terminology, modality, and pacing. A polished misconception is still a failed lesson.

For instruction extending over time, add spaced retrieval and varied transfer tasks. Make learners choose which reasoning tool applies rather than naming it in every prompt.

Produce useful outputs

For a lesson plan, return the learner assumptions, destination, explanation arc, learner actions, checks with expected evidence, likely misconceptions, and revision signals. Keep teacher language separate from planning notes when that helps delivery.

For a live explanation, begin with the phenomenon and adapt. Do not front-load the provenance ledger unless the user asks about the method.

For an audit, lead with the highest-impact failure, show the learner symptom it can cause, and give a concrete repair. Distinguish correctness problems from presentation preferences.

For a method explanation, use plain provenance labels when useful: direct Pinker advice, observed Pinker practice, workflow inference, independent evidence, and boundary.

Maintain the attribution boundary

  • Call the result a Pinker-informed workflow. Pinker has not published or validated one comprehensive teaching theory.
  • Treat his Rationality course as evidence of design choices, not proof that its sequence is optimal.
  • Do not infer that literacy, mathematics, or disciplinary knowledge will emerge naturally from claims about spoken-language acquisition.
  • Do not derive learning styles, left/right-brain teaching, fixed ability, genetic destiny, or a blanket preference for discovery learning from Pinker's work.
  • Treat enthusiasm as motivational guidance, not proof of learning.
  • Do not present lists of fallacies or biases as sufficient for general critical-thinking transfer.
  • Do not turn Pinker's contested claims about language, evolutionary psychology, violence, progress, or politics into instructional premises.
  • Preserve accessibility, alternative modalities, true uncertainty, formal validity, and safety requirements over stylistic neatness.

© AHepi, 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 2 other files (references) in .claude/skills/pinker-teach-for-understanding of AHepi/DeepReason.

  • SKILL.md
  • references/teaching-evidence.md
  • references/teaching-patterns.md

Open the folder on GitHubat commit 9607fba

Compare with similar skills

Pinker Teach For Understanding 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.

Pinker Teach For Understanding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pinker Teach For Understanding this skillAHepi/DeepReason141—~1.8kAutomated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
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
StudyVault Quiz Tutorbevibing/tutor-skills1.3k—~1.4kAutomated 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 2 days 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
  • 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
  • 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 AHepi/DeepReason

All 30 skills in this repo
  • Pinker Clarity Workflow

    AHepi/DeepReason

    Orchestrate a Steven Pinker-grounded workflow for teaching, explanatory writing, or material that must do both.

    141 GitHub stars~1.5k tokensUpdated 29 days ago
    Auto-check passed
  • Pinker Write For Readers

    AHepi/DeepReason

    Draft, revise, teach, or audit expository prose using Pinker's cognitive approach to style: classic presentation, reader modeling, curse-of-knowledge repair, coherent information order, deliberate…

    141 GitHub stars~2.1k tokensUpdated 29 days ago
    Auto-check passed
  • Example Battery

    AHepi/DeepReason

    Build a battery of concrete instances BEFORE writing or evaluating any definition, pin, or semantic clause (Reed step 1).

    141 GitHub stars~811 tokensUpdated 29 days ago
    Auto-check passed
  • Authoring Skills

    AHepi/DeepReason

    Rules for writing, editing, and retiring skill and workflow files for LLM agents.

    141 GitHub stars~1.7k tokensUpdated 29 days ago
    Auto-check passed
  • Deepreason Orchestrator

    AHepi/DeepReason

    Entry point for any DeepReason problem. An agent skill from AHepi/DeepReason.

    141 GitHub stars~1.1k tokensUpdated 29 days ago
    Auto-check passed
  • Dr Audit Orchestrator

    AHepi/DeepReason

    Router for the code-audit family. An agent skill from AHepi/DeepReason.

    141 GitHub stars~1.1k tokensUpdated 29 days ago
    Auto-check passed

Categories

Questions about Pinker Teach For Understanding

What does Pinker Teach For Understanding do?

Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision. Pinker Teach For Understanding is an agent skill from AHepi/DeepReason. Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision.

When should I use Pinker Teach For Understanding?

Pinker Teach For Understanding fits situations like: the user explicitly requests Pinkers approach to teaching; invokes this skill; wants a difficult idea explained to a specified audience; asks for a lesson.

How do I install Pinker Teach For Understanding in Claude Code?

Run `npx skills add AHepi/DeepReason --skill pinker-teach-for-understanding -a claude-code`. Or copy the skill folder (.claude/skills/pinker-teach-for-understanding in AHepi/DeepReason) into .claude/skills/pinker-teach-for-understanding in your project. Claude Code loads it when a task matches its description.

How do I install Pinker Teach For Understanding in Codex?

Run `npx skills add AHepi/DeepReason --skill pinker-teach-for-understanding -a codex`. Or copy the skill folder (.claude/skills/pinker-teach-for-understanding in AHepi/DeepReason) into .agents/skills/pinker-teach-for-understanding in your project. Codex loads it when a task matches its description.

Can I use Pinker Teach For Understanding 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 AHepi/DeepReason --skill pinker-teach-for-understanding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pinker-teach-for-understanding, .gemini/skills/pinker-teach-for-understanding, .github/skills/pinker-teach-for-understanding and .opencode/skills/pinker-teach-for-understanding in your project.

What does Pinker Teach For Understanding need to run?

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

Does Pinker Teach For Understanding 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 Pinker Teach For Understanding 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 Pinker Teach For Understanding use?

Pinker Teach For Understanding 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 Pinker Teach For Understanding use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Pinker Teach For Understanding?

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

Who maintains Pinker Teach For Understanding?

AHepi (a GitHub user) maintains it in AHepi/DeepReason, which has 141 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on September 10, 2026.

Source: AHepi/DeepReason on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.