mark-ritson-voice

mark-ritson-voice is a skill for Claude Code from jpeslar1/john-peslar-ai-skills. It costs 220 tokens per session (4,005 once invoked), scanned A, original, MIT.

A writing guide for creating evidence-led marketing columns in a style inspired by Mark Ritson, a marketing professor and Marketing Week columnist. It describes sentence rhythm, humour, examples, and source use.

In plain words
What is it for?
Use it to draft marketing commentary that challenges industry fads, explains ideas with evidence, and ends with a direct instruction.
Why use it?
It helps turn vague requests for a particular marketing voice into concrete writing rules. It also keeps claims tied to a supplied voice corpus and source map.

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 to draft marketing commentary that challenges industry fads, explains ideas with evidence, and ends with a direct instruction.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-voice)
Your own site
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-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 mark-ritson-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-ritson-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,005 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 $0.00220 $0.04005
Opus 5.5 $0.00088 $0.01602
Sonnet 5.5 $0.00044 $0.00801
Haiku 4.5 $0.00022 $0.00400

Measured 18d ago against content hash 76ab22b18744, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mark-ritson-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.

mark-ritson-voice/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mark Ritson Voice DNA

Mark Ritson is the marketing professor who swears at the slide. His Marketing Week column takes whatever the industry is currently excited about (programmatic, the metaverse, brand purpose, DTC darlings, the end of the CMO) and holds it against a chart, a revenue number, or a basic strategic axiom until it looks small, then says so in a single expletive clause. The voice is long evidence sentences broken by one-word fragments, a sporting or pub analogy that makes the fallacy absurd, single quotes around the jargon he is sneering at, and a flat imperative to close. He defends the boring fundamentals (targeting, TV, product, Coke and P&G) with the same glee he uses to flatten the fads. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

  • A long, loaded setup sentence of 35-60 words that stacks the hype in the reader's own mouth ("through the power of Big Data, amazing AI and the magical healing power of algorithms your ad will find its perfect consumers while you sleep"), then a chain of fragments: "It is shitfuckery. And of the highest possible order."
  • Fragment chains of one to four words carry the emphasis: "Nothing new. But they were all just excellent. Flawless." / "It's not only an odd question. But the right one." / "As. We. Know. It."
  • Sentences begin with And or But as a matter of routine; they are his main connective.
  • Paragraphs run 2-4 sentences in columns and 1-2 lines on LinkedIn. Columns run 800-1,500 words, framework pieces up to 3,000.
  • The profanity arrives once or twice per column at the point of maximum certainty, never in the opening sentence and never scattered.
  • Direct address to the reader as a co-conspirator: "I might just wrap it up here in paragraph four if that's OK with you?"

Hook patterns

  1. You have recently been told - open by restating the fashionable advice the reader has just received from a vendor or agency, in its most inflated form: "If you are any kind of marketer with any kind of budget you've recently been told not to worry about targeting." Deploy as the first paragraph of any fad takedown.
  2. The column about nothing - announce that there is no news, and that the absence is the point: "This is a column about nothing... Nothing newsworthy has happened to Coca-Cola. It has just continued to be Coke. And I realised last week that was an awesome achievement." Deploy when praising boring excellence.
  3. The number that shrinks the hype - put the darling's figure next to the incumbent's: "Last year Liquid Death did $263m in revenue... given Coke does that every 72 hours, maybe marketers need to tone it down a bit." Deploy to deflate a growth narrative in two sentences.
  4. Look at the chart - refuse to argue beyond the evidence: "That's really all I wanted to say in this week's column. I might just wrap it up here in paragraph four." Deploy when one dataset settles the question.
  5. Here's an unpopular perspective - state the flat contrarian answer before the argument: "how about neither? This obsession with the CMO role is indicative of fuck all." Deploy to open a piece that rejects both sides of a debate.
  6. The absurd analogy - make the fallacy ridiculous with sport or daily life: "It's like arguing that midfielders are more important than Manchester United." Deploy as the pivot from evidence to verdict, once per argument.

Read the full file on GitHub · 173 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 · 173 lines · 220 tokens per session scan A 76ab22b18744

Subscribe to this mod's changes

mark-ritson-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 220 tokens to every session and 4,005 once invoked, about $0.0009 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

mark-ritson-voice compared with skills from other repositories

mark-ritson-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mark-ritson-voicejpeslar1/john-peslar-ai-skillsSkill1218d agoMITA220Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code