Teach
cursor/plugins
Explain a body of work plainly so a person actually understands it.
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…
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AHepi/DeepReason pinker-write-for-readers --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .claude/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.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/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .claude/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AHepi/DeepReason pinker-write-for-readers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .agents/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .agents/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AHepi/DeepReason pinker-write-for-readers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .cursor/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .cursor/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AHepi/DeepReason.git --path .claude/skills/pinker-write-for-readers--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AHepi/DeepReason pinker-write-for-readers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .gemini/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .gemini/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AHepi/DeepReason pinker-write-for-readersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .github/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .github/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AHepi/DeepReason pinker-write-for-readers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/pinker-write-for-readers .opencode/skills/pinker-write-for-readers && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pinker-write-for-readers" agent skill from https://github.com/AHepi/DeepReason/tree/main/.claude/skills/pinker-write-for-readers into .opencode/skills/pinker-write-for-readers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinker-write-for-readers", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pinker-write-for-readersDraft, 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…
Pinker Write For Readers is an agent skill from 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 syntax, evidence-based usage, feedback, and revision. Use when the user explicitly requests Pinker's writing approach, invokes this skill, or asks for a Pinker-grounded draft, edit, style lesson, or prose diagnosis. Apply principles without imitating Steven Pinker's distinctive voice.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/revision-diagnostics.md` and `references/writing-evidence.md`).
The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 9607fba. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pinker Write For Readers loads about 2.1k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 1,077 words of instructions outside code blocks.
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.
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.
The full file from AHepi/DeepReason at commit 9607fba, republished under its MIT licence (© AHepi). 1,077 words, ~2,135 tokens.
.claude/skills/pinker-write-for-readers/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Help one mind reconstruct a truthful, coherent model from a linear string of words. Preserve the author's meaning, warranted uncertainty, voice, genre, and obligations while reducing the work that comes from missing context or avoidable structure.
Read references/writing-evidence.md when attribution or research support matters. Read references/revision-diagnostics.md for a diagnostic sequence and edit-report format.
Identify subject, purpose, audience, medium, genre, register, length, stakes, house style, source constraints, and content that must not change. Infer low-risk details when possible. Ask only when a missing choice would materially change the result.
Build an internal reader ledger: what the reader likely knows, what must be introduced, which terms are legitimate, which assumptions require explanation, and what the reader should understand or do after reading. Show it only when the user requests process detail or when unresolved assumptions materially affect the answer.
Check claims, evidence, quotations, logical validity, attributions, scope, and uncertainty. Never improve apparent confidence by removing a qualification that changes the proposition. Verify current or externally checkable claims when the task requires it.
Identify what the passage is about and what it says about that topic. Lead with the phenomenon, problem, object, or consequential question when the genre permits. Do not reproduce the writer's path of discovery if the reader needs the problem before the solution.
Choose a comprehensible order: causal, chronological, general-to-specific, problem-to-solution, comparison, or another explicit logic. Keep a recognizable topic or protagonist across related sentences. Use stable names for recurring concepts.
Make the relation between propositions recoverable—continuation, example, generalization, contrast, concession, cause, result, sequence, or attribution. Add a connector when the reader could reasonably infer the wrong relation, without narrating every editorial move.
For much public and explanatory prose, stage an intellectually equal writer directing an equal reader's attention to something in the world. Present the subject instead of foregrounding the writer's professional activity, process, apologies, or section management.
Treat classic style as a designed stance, not literal transparency or a claim of omniscience. Do not impose it wholesale on contracts, procedures, methods sections, formal proofs, safety warnings, advocacy, ceremonial prose, poetry, fiction, or any genre with a different communication situation.
Assume equal intelligence, not equal background. Diagnose unexpanded acronyms, specialist terms presented as ordinary words, hidden premises, missing inferential steps, abstract labels without referents, ambiguous pronouns, and examples whose relevance remains unstated.
Pair generalizations with examples. Define necessary terminology at first useful contact. Make actors, actions, causes, times, and quantities visible when abstraction conceals them. Retain efficient abstractions once the reader can recover their meaning.
Prefer given information before new information and lighter material before heavier material when these improve first-pass processing. Keep subjects near their verbs, use parallel syntax for genuine parallels, and repair garden paths, dangling modifiers, ambiguous attachment, unstable referents, and telegraphic compression.
Do not use sentence length as a proxy for difficulty. A long, well-structured sentence may be clearer than a short ambiguous one.
Choose active or passive voice intentionally. Passive may be best when the affected entity is already the topic, the agent is unknown or irrelevant, familiar information belongs first, or a heavy agent belongs later. Flag it when it needlessly hides responsibility or compounds actionless abstraction.
Cut repetition, clichés, throat-clearing, defensive metadiscourse, and status display that add no meaning. Replace needless nominalizations with actors and verbs when doing so preserves precision. Keep true conditions, exceptions, evidence limits, and domain terms.
Read aloud for backtracking, awkward rhythm, unintended emphasis, and articulation friction. Sound is a diagnostic for flow, not for truth.
For a disputed rule, distinguish grammar, ambiguity, register, convention, house style, and taste. Ask whether careful writers observe it, whether it preserves a useful distinction, and whether the proposed correction improves clarity and grace. Consult current references when the decision matters.
Do not enforce folklore based only on Latin analogy, etymology, or a commentator's preference. Some arbitrary conventions still bind because a genre or audience expects them.
When possible, ask a representative reader to paraphrase the claim and identify the first point of confusion. Reader feedback is evidence about communication, not a vote on truth or an instruction to accept every preference.
If no reader test occurred, say so rather than claiming readability has been validated. A cooling-off interval can make the draft less familiar and expose gaps.
For AI-assisted prose, run a final factual and anti-banality pass. Replace canned framing, generic uplift, empty symmetry, and plausible-sounding unsupported claims with specific observations, grounded examples, and defensible relationships.
When revising, lead with the revised text. Follow with a compact rationale only when requested or useful. Explain material changes through the reader effect—missing context, ambiguity, backtracking, false relation, excess load, or register mismatch—not through commandments.
When auditing, prioritize truth and meaning, global coherence, knowledge gaps, syntax, then local usage and rhythm. Do not bury a structural failure under copyedits.
When teaching, show a strong or repaired passage, ask the learner to notice its effect, name the cognitive or rhetorical principle, contrast alternatives, assign a constrained rewrite, and test first-read comprehension.
© AHepi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in .claude/skills/pinker-write-for-readers of AHepi/DeepReason.
Open the folder on GitHubat commit 9607fba
Pinker Write For Readers 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pinker Write For Readers this skillAHepi/DeepReason | 141 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Teachcursor/plugins | 10k | 9 repos | ~1.4k | Automated safety check: Pass | None | |
| Prosestatic-web-server/static-web-server | 2.4k | — | ~971 | Automated safety check: Pass | Apache-2.0 | |
| Beautiful Prosesickn33/agentic-awesome-skills | 47k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Crossframe Teachsickn33/agentic-awesome-skills | 47k | 1 repos | ~943 | Automated safety check: Pass | MIT | |
| Teachvinvcn/mattpocock-skills-zh-CN | 4.7k | — | ~1.3k | Automated safety check: Pass | MIT |
cursor/plugins
Explain a body of work plainly so a person actually understands it.
static-web-server/static-web-server
Author or edit any prose for the Static Web Server (SWS) project — documentation, design docs, READMEs, PR descriptions, issue bodies, commit message bodies, or other human-readable text — following…
sickn33/agentic-awesome-skills
A hard-edged writing style contract for timeless, forceful English prose without modern AI tics.
sickn33/agentic-awesome-skills
A skill your agent uses when CrossFrame Suite routes explicit Chinese teaching of CrossFrame concepts, misreading boundaries, plain-language examples, signals, or exercises.
vinvcn/mattpocock-skills-zh-CN
在这个工作区中教用户一个新技能或概念。
Yuan1z0825/nature-skills
Creates a source-grounded Chinese-English reader for a research paper, with aligned text, figures, tables and equations, or answers questions about a given passage.
AHepi/DeepReason
Orchestrate a Steven Pinker-grounded workflow for teaching, explanatory writing, or material that must do both.
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.
AHepi/DeepReason
Build a battery of concrete instances BEFORE writing or evaluating any definition, pin, or semantic clause (Reed step 1).
AHepi/DeepReason
Rules for writing, editing, and retiring skill and workflow files for LLM agents.
AHepi/DeepReason
Entry point for any DeepReason problem. An agent skill from AHepi/DeepReason.
AHepi/DeepReason
Router for the code-audit family. An agent skill from 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…. Pinker Write For Readers is an agent skill from 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 syntax, evidence-based usage, feedback, and revision.
Pinker Write For Readers fits situations like: the user explicitly requests Pinkers writing approach; invokes this skill; asks for a Pinker-grounded draft; prose diagnosis.
Run `npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a claude-code`. Or copy the skill folder (.claude/skills/pinker-write-for-readers in AHepi/DeepReason) into .claude/skills/pinker-write-for-readers in your project. Claude Code loads it when a task matches its description.
Run `npx skills add AHepi/DeepReason --skill pinker-write-for-readers -a codex`. Or copy the skill folder (.claude/skills/pinker-write-for-readers in AHepi/DeepReason) into .agents/skills/pinker-write-for-readers in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AHepi/DeepReason --skill pinker-write-for-readers -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-write-for-readers, .gemini/skills/pinker-write-for-readers, .github/skills/pinker-write-for-readers and .opencode/skills/pinker-write-for-readers in your project.
SKILL.md names no scripts, command-line tools or credentials: Pinker Write For Readers is instructions for the agent only.
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.
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.
Pinker Write For Readers is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k 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.
Skills that share tags, products or a category with Pinker Write For Readers: Teach (cursor/plugins, 10k stars), Prose (static-web-server/static-web-server, 2.4k stars), Beautiful Prose (sickn33/agentic-awesome-skills, 47k stars) and Crossframe Teach (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.