clear-writing

A writing and editing guide for producing clear, natural-sounding prose and removing common patterns that make text feel machine-written.

In plain words
What is it for?
Use it when writing or revising prose, making text sound more human, or applying a specific voice style.
Why use it?
It reduces padding, predictable structure, exaggerated language, and other habits that can make otherwise useful writing feel artificial.

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/cdeistopened/skill-stack/clear-writing
Any agent
npx skills add cdeistopened/skill-stack --skill clear-writing
Clone the repo
git clone --depth 1 https://github.com/cdeistopened/skill-stack

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,768 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 $0.00100 $0.01768
Opus 5 $0.00050 $0.00884
Sonnet 5 $0.00020 $0.00354
Haiku 4.5 $0.00010 $0.00177

Measured 2d ago against content hash 4d11843803b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clear-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 2d 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.

public/skills/clear-writing/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clear Writing

Clear writing is just clear writing. It doesn't pad around substance. It doesn't perform.

This skill works by subtraction. The AI's natural patterns are: elaborate, balance, summarize, kicker. Strip those away and what's left sounds human.

Copy Voice (The Disease)

The default register every LLM produces when you don't give it something specific to aim at. It reads like the offspring of a TED talk and a LinkedIn post. You recognize it when you see it: the sentences are all the right length, the paragraphs each make one point, and every section ends on something that sounds like it should be cross-stitched onto a throw pillow.

Specific hallmarks:

  • Crafted kickers - last sentence resolves into an aphorism. "The constraints don't create the voice. They protect it."
  • Negation cascades - "No rules. No curriculum. Just curiosity." Three things something isn't, then a landing on a warm noun.
  • Antithesis pairs - "Not X. Y." as a mic drop. The training data is marinated in this.
  • Performative simplicity - lists the complicated things, waves them away, lands on the simple thing with a flourish.

The fix is not listing don'ts (that makes the model organized around its prohibitions). The fix is writing TOWARD a specific register - load a style reference and let the examples teach. The constraints below catch drift back toward copy voice. They don't create a voice. They prevent the default from creeping back in.

Hard Constraints

These are measurable. Follow them exactly.

  1. No more than two sentences on any single point before moving on
  2. No correlative constructions ("X isn't just Y - it's Z") - state the point directly
  3. No more than one "just" per 500 words
  4. No more than one "actually" per 500 words
  5. No hedge words unless you genuinely don't know (might, could, perhaps, possibly, seems)
  6. No passive voice unless the actor is genuinely unknown
  7. No boldface for emphasis in body text
  8. No em dashes. Use hyphens with spaces - like this
  9. No exclamation marks
  10. No adjective triplets ("bold, beautiful, brilliant")
  11. No sentence fragments used for drama ("Simple. Clear. Effective.")
  12. Limit transitions to: but, and, so, then, because

Read the full file on GitHub · 132 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. 2d ago First seen · 132 lines · 100 tokens per session scan A 4d11843803b8

Subscribe to this mod's changes

clear-writing is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,768 once invoked, about $0.0005 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 2026-08-30.

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