# Va Content Quality Editor

> Edit requested prose for clarity, precision, tone, and unnecessary AI-style phrasing. Use when the user asks for editorial review or rewriting.

- Skill: `roche-k/va-content-quality-editor` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add roche-k/va-content-quality-editor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/roche-k/va-content-quality-editor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: roche-k (https://skillmd.com/u/roche-k)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/roche-k/va-content-quality-editor

---


# Content Quality Editor

Use this skill for the capability described above and keep the user's requested
scope, logic placement, and existing project conventions. Read the relevant
sections of [the domain guide](references/guide.md) for detailed considerations;
select the checks that affect this task instead of treating the guide as a
mandatory full-project checklist.

## Workflow

1. Identify the audience, business decision, available evidence, and requested deliverable.
2. Apply the relevant framework to that evidence, separating observed results from hypotheses.
3. Deliver concrete recommendations or the requested content with tradeoffs and unresolved assumptions.

## Task-specific focus

- Identify the content file or receive content via stdin
- Run unslop to strip AI writing patterns automatically
- Review the output for any remaining issues: passive voice stacks, unnecessary qualifiers, hollow transitions
- Apply light edits — preserve the author's voice, don't rewrite from scratch
- Return the cleaned content with a brief diff summary

## Applying the guidance

Use only tools and services actually available in the session. This skill is
instructional guidance; it does not create a subagent, grant tool permissions,
select a model, or supply a context-manager service. Related specialists are
optional; this skill works independently.

Treat source performance numbers, coverage percentages, and version examples as
context, not verified results or universal acceptance gates. Preserve the user's
test and artifact rules. Report only observed outcomes and disclose checks that
could not run. Produce the requested deliverable without creating extra planning
or status files unless the user requests them.