dancolta

GitHub Repo Audit — Security skill for Claude Code

Security community

Your repo has a working product but the README is losing you stars.

How to install GitHub Repo Audit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dancolta/github-repo-audit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What GitHub Repo Audit does

Your repo has a working product but the README is losing you stars. github-repo-audit runs 5 specialist agents in parallel to audit README, positioning, and discoverability — then drafts a severity-ranked fix list and applies approved changes via Claude Code.

Alternatives in Security

/chain — Build an A→B→C exploit chain for higher severity and payout 927 ★
Brand Strategy — Define or audit a brand — positioning, visual identity system, voice and tone, and brand architecture 309 ★
Audit Changes — Review all changes in the current working tree (staged and unstaged) 90 ★

README

8-bit arcade-style cover: a CRT terminal showing 'REPO AUDIT — 5 AGENTS · 1 VERDICT' flanked by 5 pixel-art specialist sprites (Comp, Market, Prod, UX, SEO), with severity stamps (CRITICAL, HIGH, MED) below

github-repo-audit

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Claude Code Skill](https://img.shields.io/badge/Claude_Code-Skill-orange)](https://docs.anthropic.com/en/docs/claude-code) [![GitHub stars](https://img.shields.io/github/stars/dancolta/github-repo-audit?style=social)](https://github.com/dancolta/github-repo-audit)

**Audits your GitHub repo's public surface across 5 dimensions, in parallel.**

*For solo OSS maintainers whose working product is buried under a weak README.*

**What this isn't:** a code linter, a security scanner, or a generic LLM "rewrite my README" prompt. It looks at how your repo is *perceived* — by humans skimming GitHub, by Google, and by AI engines summarizing your project. Nothing else.

github-repo-audit producing a severity-ranked issue list with 5 specialist agents in parallel — end-frame shows the approval gate before any changes are written

Your README should feel like [ripgrep](https://github.com/BurntSushi/ripgrep)'s or [bat](https://github.com/sharkdp/bat)'s — opinionated, scannable, and confident about what it is and isn't. Not like a SaaS landing page.

How it works

flowchart LR
    A[/github-repo-audit URL/] --> B[Intake: ground truth]
    B --> C{5 agents in parallel}
    C --> D1[competitive-analyst]
    C --> D2[market-researcher]
    C --> D3[product-strategist]
    C --> D4[ui-ux-designer]
    C --> D5[content-marketer]
    D1 & D2 & D3 & D4 & D5 --> E[Synthesis]
    E --> F[Severity-ranked issue list]
    F --> G{Approval gate}
    G -->|approved| H[Apply: README + gh repo