agentleFS
aliraza2025aliraza2025/receipts/skills/plain-copy/SKILL.md

plain-copy

Skill3 starsChanged 5 days agoMITView on GitHub

Rewrites product, portfolio, and launch copy into plain, specific language by removing AI-sounding filler, em dashes, inflated verbs, and vague outcomes, without adding any new claims. Use when the user asks to edit, polish, humanize, de-AI, or simplify copy, or when text "sounds like ChatGPT".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run claim-receipts first: if the text contains numbers or outcomes.

    line 12
  2. Distinctive:

    No em dashes: Use a period, comma, colon, or parentheses instead.

    line 18
  3. Distinctive:

    Numbers keep their scope: Never drop a denominator, date, or sample description while shortening.

    line 23
  4. Distinctive:

    Before (a deliberately bad draft): "Leveraging cutting-edge AI, CrediClip seamlessly empowers users to unlock the truth behind short-form …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plain copy

Plain copy says what happened, for whom, and how you know. This skill edits for clarity and removes the patterns that make writing sound generated, while never adding facts.

Workflow

  1. Run claim-receipts first if the text contains numbers or outcomes. Plain wording on a false claim is still false.
  2. Edit using the rules below.
  3. Return the rewrite, then a short list of the changes that altered meaning (not every word swap).

Rules

  • No em dashes. Use a period, comma, colon, or parentheses instead.
  • Concrete over abstract. "Cut quoting time on calls" over "streamlined operational workflows". If you cannot make it concrete from the source, keep it short and general rather than inventing specifics.
  • Plain verbs. built, shipped, measured, cut, fixed, tested, wrote. Avoid: leverage, utilize, empower, unlock, elevate, revolutionize, supercharge, seamless, robust, cutting-edge, game-changing, delve, tapestry, landscape, realm.
  • No filler frames. Cut "In today's fast-paced world", "It's worth noting that", "At the end of the day", "Not only X but also Y" when X and Y are not a real contrast.
  • No reflexive triplets. Lists of three adjectives or three parallel clauses only when there really are three things.
  • Numbers keep their scope. Never drop a denominator, date, or sample description while shortening.
  • Say who did it. Replace vague "we" with the actual actor when the source makes it clear.
  • Keep honest hedges, cut empty ones. "On a 19-link benchmark" stays. "Arguably", "potentially", "in many ways" go.
  • Short sentences, one idea each. Aim for an average under 20 words.

Example

Before (a deliberately bad draft): "Leveraging cutting-edge AI, CrediClip seamlessly empowers users to unlock the truth behind short-form video, delivering robust credibility insights at scale."

After: "CrediClip takes a TikTok, Instagram, or YouTube Shorts link and returns a credibility score, risk flags, and the evidence behind them. When it cannot recover enough evidence, it says so."

Meaning changes: removed "at scale" (no source); added the abstention sentence only because the product's documented behavior includes it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.