critic — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited critic (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.
Skills for an AI critic that helps writing and proofreading texts.
The bundle ships four skills, each focused on a single editing task:
— diagnose flaws in an argument without rewriting the prose.
— enforce one sentence per line and indented continuations in Markdown, TeX, and .txt.
— fix punctuation, capitalization, and line length in .srt files produced by Whisper or similar engines.
— tighten wording, cut filler, and fix grammar without changing the author's voice.
Suppose you write with [Claude Code]. You do not need to clone this repository — install the bundle as a plugin straight from GitHub. Inside a Claude Code session, run:
/plugin marketplace add https://github.com/yegor256/plugins
/plugin install critic@yegor256The first command registers the [yegor256/plugins] marketplace, which lists every plugin maintained under the yegor256 account; the second installs the critic plugin from it, which exposes every skill under skills/ to your sessions automatically.
To update later, run /plugin marketplace update yegor256; to remove, run /plugin uninstall critic@yegor256.
[yegor256/plugins]: https://github.com/yegor256/plugins
[Claude Code]: https://code.claude.com/docs/en/skills
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.