david-perell-voice

david-perell-voice is a skill for Claude Code from jpeslar1/john-peslar-ai-skills. It costs 282 tokens per session (3,895 once invoked), scanned A, original, MIT.

A style guide based on David Perell’s writing about learning and creative work. It uses personal openings, named ideas, quotations with explanations, and sustained physical metaphors.

In plain words
What is it for?
Use it for writing advice, learning essays, reading notes, and reflective posts about creative work.
Why use it?
It helps an agent turn an abstract lesson into a memorable essay with a clear structure. It also supports explanations for readers who are learning a subject from the beginning.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the voice-dna plugin — 79 skills shipped together

Good fit Use it for writing advice, learning essays, reading notes, and reflective posts about creative work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpeslar1/john-peslar-ai-skills/david-perell-voice
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jpeslar1/john-peslar-ai-skills --skill david-perell-voice
Clone the repo
git clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skills

Made for: Claude Code.

Or install voice-dna, the plugin that ships this one along with the rest of its 79 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for david-perell-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice)
Your own site
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for david-perell-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/david-perell-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 282 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00282 $0.03895
Opus 5.5 $0.00113 $0.01558
Sonnet 5.5 $0.00056 $0.00779
Haiku 4.5 $0.00028 $0.00390

Measured 18d ago against content hash 2efb2a846e40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

david-perell-voice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

david-perell-voice/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

David Perell Voice DNA

David Perell is the C-minus college writer who turned a 90-minute morning writing habit into a writing school, then into a podcast about how writers write. The voice opens on a confession or a named character in a scene, coins a Title Case term for the idea and reuses it like private vocabulary, borrows an attributed line from Jerry Garcia or Raymond Chandler and glosses it for the Internet, and develops one physical metaphor (sap into syrup, weights on a bar) for a whole paragraph before compressing the essay into a short aphorism. He is referential, earnest, self-implicating, and quietly contrarian toward modern defaults like speed-reading and "find your niche." Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

  • The opening line is one short declarative paragraph standing alone, then the explanation: "I was a terrible writer growing up." / "Words are the atomic unit of the internet." Median sentence around 14 words.
  • A long explanatory sentence is resolved by a 3-6 word aphorism: "Testing the limits of your ideas is the fastest way to improve them and raise your intelligence." then "Re-writing is re-thinking."
  • Fragments stacked for emphasis: "True learning requires contemplation. And implementation. And a commitment to reflecting on great ideas over and over again."
  • Roughly 45 percent of paragraphs are one line; notes run 150-300 words with one idea, essays run 1,500-4,000 with a named term and several attributed quotes.
  • Native length: a 200-word note, a 2,500-word essay, or a one-line X aphorism ("Read to collect the dots, write to connect them").

Hook patterns

  1. The confession - "I was a terrible writer growing up. I got a C- in my college writing class." Deploy as the first paragraph of a how-I-learned piece; the failure must be the user's.
  2. The named character - a person in a scene who embodies the error: "Mike boastfully reads 100 books per year. He listens to audiobooks at 3x speed whenever he drives and swears he can remember it all." Deploy to open a contrarian take; the character is a type, not a real target.
  3. The atomic claim - a flat definitional line: "Words are the atomic unit of the internet." / "People don't read as much as they say they do." Deploy to open a note.
  4. The attributed line - "Jerry Garcia once said: 'You want to be the only person who does what you do.'" Deploy to open a framework note, followed by the gloss that names the term.
  5. The deplored phrase - "I deplore the phrase: 'Find Your Niche.' It's always felt too passive." Deploy to open a piece that replaces a common instruction with a better one.
  6. The existential admission - "This AI boom has set off an existential crisis in me." Deploy to open a long personal post; he later points out that this is the move ("I pulled you in by talking about a battle I'm fighting").

Read the full file on GitHub · 168 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 18d ago First seen · 168 lines · 282 tokens per session scan A 2efb2a846e40

Subscribe to this mod's changes

david-perell-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 282 tokens to every session and 3,895 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.

Related

david-perell-voice compared with skills from other repositories

david-perell-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
david-perell-voicejpeslar1/john-peslar-ai-skillsSkill1218d agoMITA282Claude Code
hr-onboardingnexu-io/open-designSkill106kyesterdayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32kyesterdayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4k25d agoApache-2.0A25Claude Code, Codex