dotnet-coverage-kit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited dotnet-coverage-kit (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.
livlign/claude-skills — bespoke heroes, honest audits. Two Claude Code plugins for working with GitHub repos: repo-visuals designs README hero visuals, repo-doctor audits READMEs and prescribes fixes.
Claude Code plugins for working with GitHub repos — designing README heroes, auditing READMEs.
Featured in rohitg00/awesome-claude-code-toolkit — the curated list of Claude Code plugins, agents, and MCP servers.
/plugin marketplace add livlign/claude-skillsAlready added the marketplace? Run/plugin marketplace update livlignto pick up newly-published plugins (e.g.repo-doctor) and version bumps.
Thumbnails — click through to see the live hero in each repo.
<table> <tr> <td width="50%" valign="top"> <sub><a href="https://github.com/htmlhint/HTMLHint"><b>htmlhint/HTMLHint</b></a></sub> <a href="https://github.com/htmlhint/HTMLHint"><img src="./assets/showcase/htmlhint.png" alt="HTMLHint hero"></a> </td> <td width="50%" valign="top"> <sub><a href="https://github.com/gui-cs/Terminal.Gui"><b>gui-cs/Terminal.Gui</b></a></sub> <a href="https://github.com/gui-cs/Terminal.Gui"><img src="./assets/showcase/terminal-gui.png" alt="Terminal.Gui hero"></a> </td> </tr> <tr> <td width="50%" valign="top"> <sub><a href="https://github.com/kunwar-shah/claudex"><b>kunwar-shah/claudex</b></a></sub> <a href="https://github.com/kunwar-shah/claudex"><img src="./assets/showcase/claudex.png" alt="claudex hero"></a> </td> <td width="50%" valign="top"> <sub><a href="https://github.com/rullerzhou-afk/clawd-on-desk"><b>rullerzhou-afk/clawd-on-desk</b></a></sub> <a href="https://github.com/rullerzhou-afk/clawd-on-desk"><img src="./assets/showcase/clawd-on-desk.png" alt="clawd-on-desk hero"></a> </td> </tr> <tr> <td width="50%" valign="top"> <sub><a href="https://github.com/affaan-m/everything-claude-code"><b>affaan-m/everything-claude-code</b></a></sub> <a href="https://github.com/affaan-m/everything-claude-code"><img src="./assets/showcase/everything-claude-code.png" alt="everything-claude-code hero"></a> </td> <td width="50%" valign="top"> <sub><a href="https://github.com/emtyty/ast-graph"><b>emtyty/ast-graph</b></a></sub> <a href="https://github.com/emtyty/ast-graph"><img src="./assets/showcase/ast-graph.png" alt="ast-graph hero"></a> </td> </tr> </table>
| Plugin | Install | What it does |
|---|---|---|
| repo-visuals | /plugin install repo-visuals@livlign | Designs bespoke README hero visuals — animated GIF, static PNG, or animated SVG — through a structured discovery dialog. |
| repo-doctor | /plugin install repo-doctor@livlign | Audits a repo's README against best-practice patterns and produces a prioritized P0/P1/P2 punch list of fixes. |
repo-visualsScans the target repo, recommends a format that fits its identity, proposes scenarios, designs a bespoke HTML stage, previews it in your browser, and exports a retina-quality artifact — then optionally opens the upstream PR.
What a run looks like:
> /repo-visuals
pick mode → semi-auto · scan repo → 30 tools detected
recommend → animated GIF, 1200×675 · brief locked
build HTML → preview in browser → ship
export → hero.gif (2.4 MB) · open PR #42Why it's different
repo-doctorAudits a README the way a senior maintainer would — does the "what is this" sentence land, is install-to-first-success short enough, does the audience-jargon match, are there drift signals (stale versions, badge sprawl, dead links). Read-only diagnostic by default; opens a PR only on explicit ask.
What a run looks like:
> /readme-doctor
scan repo → classify category (CLI tool · library · framework · …)
audit → score 9 criteria with evidence
output → P0/P1/P2 punch list, each with a one-line fix
health score: 69/100Easiest entry points: submit a hero to the showcase, report a real failure as an issue, or pick something from the wishlist.
Full guide → CONTRIBUTING.md
Personal project, evolving fast — expect breaking changes pre-1.0.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.