agentleFS
jhonatan-oliveiradevjhonatan-oliveiradev/agent-skills/skills/editing-for-clarity-and-tone/SKILL.md

editing-for-clarity-and-tone

Skill1 starsChanged 3 months agoMITView on GitHub

Use when revising existing prose for clarity, concision, structure, readability, or an explicitly requested tone while preserving the original meaning and factual content.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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. Distinctive:

    If the user asks for fact-checking, research, or substantive expansion, treat that as a separate task.

    line 22
  2. Distinctive:

    Structure: put the reader's needed context before dependent detail.

    line 27
  3. Distinctive:

    Sentences: prefer direct subjects and verbs, remove filler, reduce nested qualifiers, and keep necessary nuance.

    line 28
  4. Distinctive:

    Prefer the smallest change that achieves the requested improvement.

    line 36
  5. Distinctive:

    Do not normalize every paragraph into the same cadence, add generic transitions, or make a personal draft sound like corporate copy unless …

    line 38
  6. Very specific:

    Use humanizing-generated-prose when the explicit problem is generic or AI-shaped writing and the revision needs pattern-level …

    line 42
  7. Distinctive:

    When the user asks for a rewrite, return the complete revised text.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Editing for Clarity and Tone

Overview

Improve an existing draft without silently changing what it says. The governing contract is fidelity first, then clarity, structure, density, and tone.

Establish the Editing Contract

Identify:

  • the exact text in scope;
  • audience and genre when known;
  • requested tone, formality, length, or house style;
  • facts and claims that must remain unchanged;
  • protected spans: quotations, citations, URLs, code, identifiers, names, dates, numbers, legal wording, headings, or user-marked text.

If the user asks for fact-checking, research, or substantive expansion, treat that as a separate task. Do not disguise new claims as editing.

Edit in Passes

  1. Meaning: resolve only ambiguities that can be fixed without guessing. Flag uncertainty rather than inventing intent.
  2. Structure: put the reader's needed context before dependent detail; merge repetition and split overloaded paragraphs when useful.
  3. Sentences: prefer direct subjects and verbs, remove filler, reduce nested qualifiers, and keep necessary nuance.
  4. Terminology: make repeated concepts consistent without replacing precise domain language with generic synonyms.
  5. Tone: adjust distance, warmth, formality, confidence, and rhythm to the requested situation. Tone must not change the certainty of factual claims.
  6. Length: cut redundancy before cutting evidence, conditions, exceptions, or action-critical detail.
  7. Fidelity check: compare the revision against the source for changed numbers, names, claims, citations, scope, obligations, and conclusions.

Minimum-Effective-Edit Rule

Prefer the smallest change that achieves the requested improvement. Distinctive phrasing is not a defect simply because another sentence would sound smoother.

Do not normalize every paragraph into the same cadence, add generic transitions, or make a personal draft sound like corporate copy unless that is the explicit target.

Boundary With Humanization

Use humanizing-generated-prose when the explicit problem is generic or AI-shaped writing and the revision needs pattern-level naturalization while preserving protected content. Use this method for broader editorial work where clarity, tone, structure, or concision is the primary goal.

Deliverable

When the user asks for a rewrite, return the complete revised text. Add explanation only when requested or when a material ambiguity, protected conflict, or substantive change needs disclosure.

Reference Signals

GDS/ONS plain-language guidance supports user-focused structure, concise sentences, task-centered headings, and common language. Microsoft and Google style guidance reinforce direct, helpful, accessible prose and consistency for global audiences.

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.