write-prose

A writing guide for producing clear, natural prose for people to read, including documentation, articles, emails, and release notes.

In plain words
What is it for?
Use it before writing or editing human-facing prose such as READMEs, documentation, announcements, comments longer than a line, or other project text.
Why use it?
It helps remove formulaic or overly artificial wording from explanatory text. It emphasizes plain sentences that state one idea clearly.

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/answerdotai/skill-plugins/write-prose
Any agent
npx skills add AnswerDotAI/skill-plugins --skill write-prose
Clone the repo
git clone --depth 1 https://github.com/AnswerDotAI/skill-plugins

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,463 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 $0.00092 $0.03463
Opus 5 $0.00046 $0.01732
Sonnet 5 $0.00018 $0.00693
Haiku 4.5 $0.00009 $0.00346

Measured yesterday against content hash 47f51d599d4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-prose 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.

plugins/claude-aai/skills/write-prose/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Prose That Doesn't Sound Like AI

Guidelines for writing clear, human-sounding prose. Based on the Anti-Slop Reference. Apply these when writing documentation, blog posts, READMEs, or any prose.

Here is a passage from The Economist. Its house style is the register most prose this skill covers should default to: documentation, explanation, argument.

No form of emissions reduction, though, can quickly bend the current trajectory.[1][2] Endurance is what remains.[3][14] Making air conditioning more efficient, cheap and widespread[10] saves lives[6] and fits well with other policy goals, like making clean electricity cheap to produce and consume.[7] Ten years ago a commitment to phase out the fluorinated gases in cooling systems was reached in Kigali, the capital of Rwanda.[8][9] There is scope for extra international efforts to improve the machinery that uses them.[7][19] This could double the cooling benefit of phasing out the gases.[6]

Each sentence sets out to say one thing, says it, and stops.

It is simple plain English prose. It carries no byline and needs none. Plainness, not personality, does the work. It's not trying to sell anything. It lets you figure out what the takeaways are.

Write like that.

Here, on the other hand, is a horrendous rewrite, as sloppy as possible:

In this piece, we'll dive deep into the fascinating world of cooling![1] 🌡️[15] Here's the thing:[2] emissions reduction alone isn't going to cut it. In today's rapidly-warming world,[4] it's not about quick fixes — it's about endurance.[3] When it comes to[5] air conditioning, a technology that cools indoor air,[20] one might argue[5] that a comprehensive, holistic approach — making units more efficient, more affordable, and more accessible[10] — could potentially help save countless lives in some cases,[6] while seamlessly aligning with broader policy goals like fostering[7] clean, affordable electricity for all, and also, it's worth noting,[5] building on the pivotal commitment to phase out fluorinated gases that was reached ten years ago in Kigali — the vibrant capital of Rwanda —[16] a commitment that has reshaped the landscape of cooling policy and continues to empower stakeholders[9] across the realm of climate diplomacy.[8]

But here's where it gets really exciting.[11] 🤯 The Kigali deal isn't just a treaty — it's a game-changer.[3] The machinery that leverages[7] these gases gets a myriad of enhancements via this framework,[19] which could unlock further benefits, and which, honestly,[5] may potentially double the cooling upside of phasing them out, depending on context.[6][8] Getting there is just[12] a matter of commitment. Furthermore, as we can see,[5] the journey ahead is a rich tapestry of innovation — a testament[7] to what we can achieve when we navigate this challenge together. In conclusion:[5] the bottom line?[13] Endurance is the name of the game — in other words, success is all about sticking with it for the long haul.[14] 💪

Do NOT write like that.

The numbers below refer to the [bracketed] markers in both passages. Where a number appears in each, the pair is the sloppy and the plain version of the same thing. Entries 17 and 18 are paragraph-scale tells that a one-paragraph sample cannot show.

  1. Throat-clearing: an opener that announces the piece instead of starting with the subject: "In this piece, we'll...", "Let's dive into...", "Let's explore...", "In this section, we will...". Don't clear your throat. The first sentence should do real work.
  2. Announce-then-deliver: a label and a colon in place of stating the fact ("The fix: retry on timeout", "Startup: the win", "Here's the thing: ..."). The label is scaffolding. State the fact as a sentence: "Retrying on timeout fixes it."
  3. Not-X-but-Y: "It's not X, it's Y" / "isn't just X, it's Y", the #1 LLM rhetorical crutch. State the positive directly. Restructure every time.
  4. Today's-world opener: "In today's [fast-paced/digital/modern] world...".
  5. Filler phrases: they add zero information; state the thing directly.
    • "It's worth noting that..." / "It's important to note that..." / "Notably, ..." / "Importantly, ..." / "Interestingly, ..."
    • "As we can see..." / "As mentioned earlier..."
    • "In conclusion, ..." / "To summarize, ..."
    • "Furthermore, ..." / "Moreover, ..." / "Additionally, ..." -> use "and", "also", or just start a new sentence. If every paragraph opens with "However" or "Furthermore", drop the transition word and start with the actual subject.
    • "When it comes to..." / "In the realm of..."
    • "One might argue that..." / "It could be suggested that..."
    • "A [comprehensive/holistic/nuanced] approach to..." -> "an approach to"
    • "honest"/"honestly"/"to be honest" as a throat-clear ("the honest tradeoff", "honestly, it's fine"): in speech this flags a rare, significant admission; sprinkled everywhere it's noise. Delete it in nearly every case.
  6. Hedging: the worst offender. "This approach may potentially help improve performance in some cases" means nothing. Say "this is faster" or say "we haven't benchmarked this yet". The original commits: "saves lives", "could double".
  7. Inflated diction: puffed-up words where plain ones exist: enhance/leverage for improve/use, plus seamlessly, fostering, pivotal, myriad, landscape, realm, empower, journey, tapestry, testament, navigate. The Banned Words lists below are the fuller reference.
  8. Sentence sprawl: one over-long sentence stacking clauses that should be separate sentences, chained with "so", "which", "but", and "and", each extending or qualifying the last. Write one idea per sentence. When a draft sentence joins two thoughts, try the split. Keep the join only when the connection itself is the point.
  9. Artifact-as-agent: the commitment "has reshaped the landscape" and "continues to empower". Really, people reached a commitment; say what happened, with the actors in place. Three stacked habits make these sentences (e.g. "Your tests shaped the ones that landed"):
    • Artifact as agent: an inanimate subject performs a verb only a person can do ("your tests shaped", "this PR introduces", "the change enables"). The person who did the work vanishes.
    • Oblique reference instead of naming: the object is pointed at through a relative clause or metaphor ("the ones that landed") rather than named ("our new tests").
    • Narrative compression into a single transitive clause: a who-did-what story (I read your tests, adapted them, committed mine) flattened into "X verbed Y", an aphorism that sounds polished because it discards the actors and the order of events. Common as a sentence-final flourish.

Read the full file on GitHub · 93 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. yesterday First seen · 93 lines · 0 tokens per session scan A 47f51d599d4c

Subscribe to this mod's changes

write-prose is a skill published in the GitHub repository AnswerDotAI/skill-plugins (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 3,463 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 2026-08-31.

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