skills-writing — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skills-writing (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.
[shane.logsdon.io](https://shane.logsdon.io) — writing and projects on agentic workflows, web standards, and payments engineering.
Writing quality and style skills for Claude Code. Six skills covering voice, house style, plain language, controlled technical English, grounded interviewing, and review.
Install via the slogsdon-claude-code-config marketplace.
workflow-stage-draft runs these in order: interview → draft → humanize → ms-style-pass. writing-review sits alongside as the read-only diagnostic and is the agent-side input to the copy gate: it reports, the human decides.
Profiles/voice.md is authoritative for voice across every skill here. Where a skill's defaults and that profile disagree, the profile wins.
scripts/ holds two diagnostic linters vendored byte-identical from addyosmani/clarity (MIT): strip_markdown.py reduces a draft to the prose a reader actually reads, and prose_stats.py reports cadence, hedge/booster density, anchor density, and stock-lexis hits. No composite score, by design — see scripts/README.md for why and for how to read the numbers.
MIT — see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.