humanizing-writing

A writing guide for revising Chinese or English prose that sounds machine-made, generic, or unlike its author. It covers everyday writing, technical documentation, and pull request descriptions.

In plain words
What is it for?
Use it to review or rewrite prose without translating it unless asked. It also guides precise technical documentation and pull request descriptions that state the problem, change, checks, and limits.
Why use it?
It helps remove formulaic or promotional wording while keeping the original meaning, evidence, and personal voice.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/zhpeng24/devkit/humanizing-writing
Any agent
npx skills add zhpeng24/devkit --skill humanizing-writing
Clone the repo
git clone --depth 1 https://github.com/zhpeng24/devkit

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.01160
Opus 5 $0.00023 $0.00580
Sonnet 5 $0.00009 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured yesterday against content hash 29d23ee41b69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanizing-writing 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 yesterday.

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/humanizing-writing/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizing Writing

Core Principle

Keep the writer's meaning, evidence, and recognizable voice. Replace only the patterns that make the prose feel generic or manufactured; do not translate unless asked.

Route the Task

Apply the relevant routes before drafting:

Chinese input -> read references/chinese-patterns.md
English input -> read references/english-patterns.md
Mixed input -> read both only when both prose portions require editing
Everyday writing -> preserve personality and uneven rhythm
Technical documentation -> prefer precise, neutral, current-state wording
PR description -> state problem, actual change, verification, and each stated limitation at its exact scope

For Chinese everyday writing, apply the Chinese catalog before drafting: lead with the source's concrete person, place, time, or action, and retain every supported action. When the user asks to preserve all facts, protect the concrete, source-backed facts—not generic significance or promotional framing that merely labels those facts. Remove a generic significance, promotional outcome, or future-looking claim when it has no independent support and merely restates or inflates adjacent concrete actions. Preserve a claim with independent support, named attribution, a citation, or a specific verifiable result; if its status is unclear, ask rather than delete it. Do not replace a removed claim with a softer inferred effect.

For English everyday writing, apply the English catalog before drafting: lead with the source's concrete person, place, time, or action, and retain every supported action. Remove generic significance, promotional framing, speculative gap-filling, or an upbeat future claim when it is unsupported and merely inflates or restates adjacent concrete actions. Preserve a claim with independent support, named attribution, a citation, or a specific verifiable result; if its status is unclear, ask rather than delete it. Do not replace a removed claim with a softer inferred effect. Author samples and explicit preferences remain controlling.

Read the full file on GitHub · 73 lines

Files

What ships with it

3 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. yesterday First seen · 73 lines · 46 tokens per session scan A 29d23ee41b69

Subscribe to this mod's changes

humanizing-writing is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,160 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens