agentleFS
jpoindexterjpoindexter/design-case-study-skills/skills/technical-microcopy-editor/SKILL.md

technical-microcopy-editor

Skill1 starsChanged 4 months agoMITView on GitHub

Run an accuracy, clarity, and brevity edit on technical design case-study copy. Use when prose contains vague UX jargon, imprecise system claims, passive voice, inconsistent terms, inflated ownership, unsupported metrics, long captions, or when the draft should become materially shorter without losing quantitative evidence or technical meaning.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify names, numbers, units, ownership, sequence, system behavior, and claim status against supplied artifacts.

    line 12
  2. Distinctive:

    before/after word counts and reduction percentage.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Technical Microcopy Editor

Edit in three ordered passes. Read references/acb-edit.md.

Pass 1 — Accuracy

Verify names, numbers, units, ownership, sequence, system behavior, and claim status against supplied artifacts. Flag contradictions and unverifiable statements. Do not polish a false claim.

Pass 2 — Clarity

Replace abstract jargon with concrete actors, actions, objects, states, and consequences. Give each sentence one primary job. Keep terminology consistent with the product and architecture. This is McKay's "clear and natural" test applied to prose about the product rather than the product itself: use the language a competent person would actually say out loud, not a system emitting status (McKay).

Pass 3 — Brevity

Target a 30% word-count reduction unless doing so would remove evidence or necessary causal explanation. Delete repetition, throat-clearing, and self-congratulation. Prefer direct verbs and information-bearing headings. Kubie's distinction is the filter: keep THE THING (the claim, the evidence, the causal link) and cut NOT THE THING (the process narration, the hedging, the credit-taking) — most bloat is NOT THE THING dressed up as content (Kubie).

Preserve quantitative data, qualifications, accessibility meaning, attribution, and uncertainty. Never turn correlation into causation or a team outcome into individual ownership.

Output

Return:

  1. the edited copy;
  2. before/after word counts and reduction percentage;
  3. an accuracy issue list;
  4. a terminology normalization list;
  5. any sentence retained despite length because it carries necessary evidence.

Example

Input:

I designed an intuitive and seamless workflow that significantly improved outcomes.

Expected outcome:

I redesigned the retry flow. In the moderated test, 8 of 10 participants recovered
without support. [Evidence needed: baseline and attribution.]

Sources

  • Everett McKay, UI Is Communication (Morgan Kaufmann, 2013) — the clarity pass's "clear and natural" standard: language a person would actually say, not system-speak.
  • Scott Kubie, Writing for Designers (A Book Apart, 2018) — the brevity pass's THE THING vs NOT THE THING cut.
  • Michael J. Metts & Andy Welfle, Writing Is Designing (Rosenfeld Media, 2020) — plain-language grounds for why brevity and accuracy can't trade against each other; cut filler, never cut a caveat.

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.