Editorial — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Editorial (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Open-source editorial skills for AI content creation, by Wordful.
This is a collection of skills designed to help writers, marketers, and content teams ship work that holds up — without the formulaic patterns that mark a draft as machine-generated.
Strip AI writing patterns from a prose draft. Returns the cleaned draft — no commentary, no findings, no grade. Where a passage cannot be safely cut, leaves a [NEEDS SPECIFIC: ...] placeholder for the human writer to fill in. Add --report for an optional diagnostic block.
More skills coming.
Inside Claude Code, run:
/plugin marketplace add word-ful/editorial
/plugin install dissolve-ai@editorialThat's it. Updates apply automatically when new versions ship.
If you'd rather clone and symlink:
git clone https://github.com/word-ful/editorial.git ~/wordful-editorial
ln -s ~/wordful-editorial/dissolve-ai ~/.claude/skills/dissolve-aiThen restart Claude Code.
See each skill's README for invocation details.
MIT. See LICENSE.
Issues and PRs welcome. See CONTRIBUTING.md.
Created by Wordful, content ops for AI-forward marketing teams. https://wordful.com
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.