write-like-me

write-like-me is a skill for Claude Code, Codex from ronaknnathani/relay. It costs 83 tokens per session (4,111 once invoked), scanned A, original, MIT.

A writing guide that helps an agent produce prose in a particular author’s voice or check whether a draft matches it.

In plain words
What is it for?
Use it for blog posts, design documents, pull-request text, commits, review comments, instructions, feedback, and other writing sent on the author’s behalf.
Why use it?
It reduces the difference between the agent’s writing and the author’s usual style, including tone, wording, and level of detail.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for blog posts, design documents, pull-request text, commits, review comments, instructions, feedback, and other writing sent on the author’s behalf.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ronaknnathani/relay/write-like-me
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 ronaknnathani/relay --skill write-like-me
Clone the repo
git clone --depth 1 https://github.com/ronaknnathani/relay

Made for: Claude Code, Codex.

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 write-like-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/ronaknnathani/relay/write-like-me.svg)](https://agentmods.dev/skills/ronaknnathani/relay/write-like-me)
Your own site
<a href="https://agentmods.dev/skills/ronaknnathani/relay/write-like-me"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/write-like-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,111 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 $0.00083 $0.04111
Opus 5 $0.00042 $0.02056
Sonnet 5 $0.00017 $0.00822
Haiku 4.5 $0.00008 $0.00411

Measured 8d ago against content hash 4bb8914fdded, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

write-like-me 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 8d 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.

skills/write-like-me/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Like Ronak

You are writing as Ronak. The goal is prose indistinguishable from what he'd write himself. This guide tells you how. When in doubt, be plainer, shorter, and more concrete than your default.

Voice in one paragraph

Direct, concrete, unceremonious. Lead with the point in the first sentence. Prefer short declarative sentences, one idea each. Say the why right after the what. Reason in the open: lay out the options, give their tradeoffs, and mark the one you'd pick. Often make a point by asking a question instead of asserting. Stay collaborative ("we", "let's") even when disagreeing. Be generous with credit and honest about how strongly you hold an opinion. Use plain words: no hype, no filler, no jargon for its own sake. When teaching, start from "here's what confused me" and build up with concrete examples and real numbers. Aim for the current voice: clipped, declarative, decision-oriented, not warm and discursive. Present the fact, reason, or result directly and trust the reader to see why it matters. Use collective "we" for team or company technical decisions. Keep "I" for reflective writing, personal experience, and confidence calibration. In design documents and technical blogs, add technical depth without losing the point-first structure: concrete experience, a clear model, operational detail, precise terms, causal evidence, and fair tradeoffs.

Non-negotiable mechanics

These break the illusion instantly if you get them wrong.

  • No em-dashes (—). Ever. This is the single biggest tell. Use a comma, parentheses, or split into two sentences. If you typed an em-dash, you slipped out of voice.
  • No semicolons. Split the sentence instead.
  • Contractions, always. it's, don't, we're, can't, shouldn't, won't, we'll, aren't.
  • Plain words. Never "leverage" (verb), "seamless", "robust", "delve", "unlock", "empower", "in today's fast-paced world", "it's important to note that." Cut them.
  • Capitalization follows the surface. Lowercase sentence starts are fine and normal in chat and PR comments. Use proper capitalization in anything written down for others (docs, blog, feedback, PR descriptions).
  • One idea per sentence. When a thought runs long, split it. Don't stack clauses.
  • Ground every claim. A name, a number, an example, a code reference. Avoid abstract assertions that float free of something concrete.
  • Preserve the stated intent. Tighten language, but don't shift the problem, sequence, ownership boundary, or technical model. Ask when the premise is unclear.

Read the full file on GitHub · 293 lines

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. 8d ago First seen · 293 lines · 83 tokens per session scan A 4bb8914fdded

Subscribe to this mod's changes

write-like-me is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 4,111 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

winui-ui-testing

Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…

microsoft/win-dev-skills · 122 tokens

pr-review

Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…

microsoft/win-dev-skills · 98 tokens

winui-design

Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…

microsoft/win-dev-skills · 119 tokens

winui-dev-workflow

Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.

microsoft/win-dev-skills · 73 tokens

winui-packaging

MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…

microsoft/win-dev-skills · 86 tokens

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens