agentleFS
philoserfphiloserf/claude-code-config/skills/editor/SKILL.md

editor

Skill14 starsChanged 4 days agoMITView on GitHub

Copy edits prose while preserving voice and register, and gives magazine-editor notes on non-fiction. Use when asked to edit, copy edit, proofread, revise, polish, tighten, or rewrite essays, articles, drafts, or fiction, or for an editorial pass on a non-fiction piece's idea, structure, facts, and ending. Flags wordiness, passive voice, clichés, hedging, and nominalizations.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use doctor.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    doctor

    Diagnose an Amplifier CLI environment through the CLI doctor agent. USE WHEN a user requests CLI runtime, settings or missing-capability inspection. DO NOT USE for project bugs or other hosts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 5

    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:

    If $ARGUMENTS is a file path, Read it.

    line 12
  2. Distinctive:

    Before editing, read the full piece and identify its register.

    line 18
  3. Distinctive:

    When asked for an editorial pass, editor's notes, or whether a non-fiction piece is ready, edit the piece rather than its sentences, as a …

    line 50
  4. Distinctive:

    Facts and attribution: every checkable assertion (names, numbers, dates, quotes, causal claims, superlatives), each marked as known, …

    line 58
  5. Distinctive:

    When asked to rewrite, produce clean copy only.

    line 66
  6. Distinctive:

    Use American spelling and usage.

    line 127

“Common” is measured: kept by at least 6 in 10 of the 12 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

Copy Editor

Step 0: Handle Input

If $ARGUMENTS is a file path, Read it. If it is prose pasted inline, edit that directly. If it is empty, ask for the piece.

Never write back to the source file unless asked. Edit Mode output (bracketed flags) is a response only, shown to the user, not written to the file. Rewrite Mode output is also shown in the response by default; only use Write to replace the file's contents if the user explicitly asks to have the file updated in place.

Step 1: Detect the Register

Before editing, read the full piece and identify its register. The piece's voice and form determine which rules apply and which to relax.

RegisterCharacteristicsAdjust
Personal essayFirst-person, reflective, intimateFull Orwell. Flag hedging aggressively. Protect personal cadence.
Analytical/expositoryImpersonal or first-plural, argument-driven, may use technical vocabularyOrwell applies, but tolerate domain-specific terms that are load-bearing for the audience. Don't push toward first-person.
Narrative fictionThird-person, dialogue, scenes, pacingFlag wordiness and dead metaphors, but respect deliberate passive voice, sentence fragments, and stylistic repetition used for effect.
PoetryLineated, compressed, image-drivenLimit edits to clarity and word economy. Do not flag line breaks, fragments, or compression as errors. Rhythm and sound override prose rules.
How-to/guideInstructional, imperative mood, structuredEdit the prose sections (intros, explanations). Leave lists, steps, and recipes alone unless they contain errors.

Step 2: Apply Voice Priority (in order)

  1. The author's voice and register — words, rhythm, perspective, and intended audience
  2. Orwell's clarity rules — see orwell.md
  3. Economist mechanics — punctuation, word economy, jargon removal

Modes

Edit Mode (default)

Flag issues inline with [brackets] immediately after problematic text. Provide suggested fix after each flag. Preserve author's voice.

Bracket flag types: [wordy], [passive], [cliché], [reader-trigger], [dead metaphor], [vague], [nominalization], [hedge], [prep pile-up], [cut: reason], [use: replacement]

Original: I was literally dying of embarrassment as I made my way through the doorway.
Edited: I was literally [dead metaphor] dying of embarrassment [cut: implied] as I made my way [wordy] through the doorway [use: door].
Fixes: "I was dying as I walked through the door." or "I flushed as I walked through the door."

Editorial Mode

When asked for an editorial pass, editor's notes, or whether a non-fiction piece is ready, edit the piece rather than its sentences, as a non-fiction magazine editor. Load magazine-editor.md first; it holds the stance and principles. Fiction and poetry get Edit Mode instead.

Return notes, not markup, in this order:

  1. The idea: one sentence stating what the piece argues or reveals. If you cannot write it, say so and stop; that is the only note.
  2. Lede: whether it promises exactly what the piece delivers, and where the piece actually starts if the opening clears its throat.
  3. Cold reader: each point where a reader with no context would ask who, why now, or so what, or would stop reading, quoted and located.
  4. Proportion: what is overweight, what is starved, what belongs in another piece.
  5. Facts and attribution: every checkable assertion (names, numbers, dates, quotes, causal claims, superlatives), each marked as known, believed, or told, and each claim whose source the reader cannot see.
  6. Ending: whether it earns its size.
  7. The one change: the single change that would matter most.

Phrase notes on judgment as queries. State notes on fact, law, and fairness to named people flatly. Leave sentence-level flags to Edit Mode unless asked for both.

Rewrite Mode

When asked to rewrite, produce clean copy only. No markup, no explanations, no meta-commentary. Maintain:

  • The piece's existing register and voice (don't shift analytical to personal or vice versa)
  • Sentence variety and personal cadence
  • The author's meaning exactly
  • Sound like the author, not an editor

Orwell's Rules (second to voice and register — see Step 2)

  1. Cut familiar metaphors and similes
  2. Short words over long
  3. Cut every cuttable word
  4. Active voice over passive
  5. Plain English over jargon and foreign phrases
  6. Break any rule to avoid barbarism

For expanded guidance and examples: orwell.md

Hedging

Flag conditional mood and qualifiers that weaken declarative prose. Common hedging words: could, might, may, perhaps, maybe, generally, arguably, probably, somewhat, tends to, it seems.

Flag when:

  • The author states a belief or conclusion but softens it with conditionals
  • Multiple hedges pile up in a single paragraph (compounds the weakness)
  • A closing line lands soft instead of hard
  • "Generally" or "probably" weakens a preference the author clearly holds

Keep when:

  • Speculative tone is the piece's voice (exploring uncertainty deliberately)
  • The hedge is in quoted or attributed speech (not the author's voice)
  • The hedge does real epistemic work (philosophical or scientific qualifiers)
  • The word is past-tense ability ("could absorb it"), not future conditional
  • Analytical writing uses appropriate qualification ("the data suggests" is not hedging — it's precision)

In rewrite mode: Replace conditional mood with present or future declarative. Cut qualifiers that add nothing. Pay special attention to closing lines — they must land.

Nominalizations

A nominalization turns a verb or adjective into a noun, usually weakening the sentence:

  • "implementation" → "implemented"
  • "realization" → "realized"
  • "improvement" → "improved"

Flag when: The verb form would be shorter, more direct, and more active.

Keep when: The noun form is standard in the register (e.g., "investigation" in analytical writing) or when the noun is the true subject.

Clichés

See cliches.md for the full list. When flagging, suggest a concrete replacement or recommend cutting entirely.

Reader Triggers

See reader-triggers.md for the full catalog: overused vocabulary ("delve", "tapestry"), formulaic structures (negative parallelism, "Not X. Not Y. Just Z.", bold-first bullets), and composition-level patterns (fractal summaries, the belabored metaphor, signposted conclusions). These patterns say nothing about who wrote a passage—people wrote every one of them long before language models did—but readers primed to hunt for AI prose react to them, and that reaction costs the writer. Run this check on every piece, regardless of register, and flag on reader effect, never as a verdict on origin: do not say a passage reads as machine-written. Flag each instance with [reader-trigger]. A single em dash or one "it's not X, it's Y" rarely trips anyone; flag it, but note in the suggested fix when it can stay as the piece's one instance. Em dashes and parentheticals are a legitimate style; flag them only when they stack. A cluster is what trips a wary reader—call that out explicitly when it appears.

Constraints

Use American spelling and usage. Keep direct statements direct and add no qualifier the author did not use. Either flag a problem or leave it; never suggest the author "consider" something.

Structural Guidance

Openings

Flag throat-clearing. The piece should begin with its subject, not with setup. If the first paragraph could be cut without losing anything, flag it.

Transitions

Cut mechanical transitions (Additionally, Furthermore, Moreover, In conclusion). If the logic requires a transition, the paragraphs may be in the wrong order.

Endings

Flag summary endings that repeat what the piece already said. Flag morals stated explicitly when the piece already showed them. The best endings either land on a concrete image or stop the moment the point is made.

Output Format

Edit Mode

Return text with [bracketed flags] inline. After the flagged passage, provide suggested fixes. Group related fixes when efficient.

Rewrite Mode

Return clean copy only. No markup, no tracked changes, no commentary.

When Asked to Explain

Explain the specific edit requested. Do not explain the editing philosophy unless asked.

Quality Check

After editing, verify:

  1. Voice preserved — Read the edited version aloud. Does it still sound like the author?
  2. Meaning unchanged — Compare each substantive change against the original. No new claims, no removed claims.
  3. Register consistent — Confirm the register detected in Step 1 matches the output. An analytical piece shouldn't become personal, and vice versa.
  4. No over-editing — If more than ~40% of sentences are flagged, reconsider: is the piece genuinely problematic, or are you imposing preferences?
  5. Endings land — Read the final paragraph. Does it end with weight, or trail off?
  6. Reader triggers checked — reader-triggers.md patterns reviewed regardless of register (see Reader Triggers)

Reference Files

  • orwell.md — Load when applying Orwell rules to dense prose or when unfamiliar with a rule
  • cliches.md — Load when a piece contains 3+ suspected clichés
  • reader-triggers.md — Load on every piece to check for patterns that trip wary readers
  • word-choices.md — Load when encountering confused words or heavy jargon
  • examples.md — Load on first use to calibrate editing intensity
  • magazine-editor.md — Load whenever Editorial Mode runs

Do not use when

  • Restructuring a draft or changing its argument: Editorial Mode names what is wrong with structure and argument, but the skill never rewrites them
  • Editing code, YAML, or configuration files — prose only

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.