Agent skill · Frontend

writing-quality-editor

Writing Quality Editor (WQE) composes, assesses, revises, and adapts user-facing writing so it reads naturally while preserving meaning, claims, intent, voice, conditions, numbers, identifiers, exceptions, and risks. Use when a user asks to write, review, polish, fix, improve, supplement, clarify, translate, localize, or make a document sound natural; no skill or mode name is required. Covers README, onboarding, release notes, manuals, UI, errors, gallery copy, research-backed briefs, technical comparisons, and natural English↔Korean adaptation. If a host repository workflow owns document clas

kyungseogithub.com/kyungseoGitHub ↗
claude-codecodexApache-2.0
Install
npx skills add kyungseo/skillstead --skill writing-quality-editor --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 9
SKILL.md size: 19 KB
Bundled scripts: none
Version: 0.10.1
Path: skills/writing-quality-editor/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 69
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Writing Quality Editor Create or improve writing so it feels native to its audience and purpose without inventing what it is allowed to mean. ## Package Map | File | Load rule | | --- | --- | | `references/review-rubric.md` | Always load before assessing or changing text | | `references/en-ko-adaptation.md` | Load for `Adapt` mode or any bilingual parity review | | `references/research-backed-compose.md` | Load for `Compose` when required facts must be gathered from public sources | If a required reference cannot be loaded, stop before revising. Return a partial assessment and name the missing contract instead of improvising it. ## Choose The Mode Do not require the user to name this skill or choose a mode. Infer the mode from the requested outcome, the relationship between the source and target text, and whether the user authorized a change. Treat verbs and phrases as contextual evidence, not as a fixed keyword list. | User intent | Mode | | --- | --- | | Write, draft, or build a new document from facts, a brief, or research | `Compose` | | Review, check, diagnose, comment on, or identify problems without asking for replacement text | `Assess` | | Fix, polish, improve, supplemen

What's inside
Steps it walks through
  1. Package Map
  2. Choose The Mode
  3. Respect Host Artifact Workflows
  4. Establish The Editing Contract
  5. Bound The Meaning Before Writing
  6. Separate What Is Said From How It Reads
  7. What register may change
  8. What register may never change
  9. Where this applies
  10. Choose A Revise Strategy
  11. Write And Edit For Natural, Skilled Results
  12. Run The Delta Audit
  13. Output Contract
  14. Assess
Ships with 8 files
  • CHANGELOG.md
  • LICENSE.txt
  • README.ko.md
  • README.md
  • agents/openai.yaml
  • references/en-ko-adaptation.md
  • references/research-backed-compose.md
  • references/review-rubric.md
More from skillstead
All skills →
About this skill
What does the writing-quality-editor skill do?

Writing Quality Editor (WQE) composes, assesses, revises, and adapts user-facing writing so it reads naturally while preserving meaning, claims, intent, voice, conditions, numbers, identifiers, exceptions, and risks. Use when a user asks to write, review, polish, fix, improve, supplement, clarify, translate, localize, or make a document sound natural; no skill or mode name is required. Covers README, onboarding, release notes, manuals, UI, errors, gallery copy, research-backed briefs, technical comparisons, and natural English↔Korean adaptation. If a host repository workflow owns document clas

How do I install it?

Run `npx skills add kyungseo/skillstead --skill writing-quality-editor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From kyungseo/skillstead, a repository with 69 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going