claude-skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited claude-skills (Plugin) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Personal Claude Code skill / command collection by gggodlin.
Reading list, not a tool. Browse, fork, copy what you like; nothing here is guaranteed to work on your machine. Read CONTEXT.md before installing.
Install as-is. No personal framework dependencies.
| Name | Type | What it does |
|---|---|---|
review-html | skill | Render long spec/plan markdown into interactive Traditional Chinese HTML for review |
review-zh | skill | Auto-generate Traditional Chinese review copy of English markdown |
ai-image-gen | skill | Single entry point for any image generation request |
changelog-check | command | Fetch Shopify changelog entries since last check |
Tied to author's personal stack. Treat as templates; expect to fork and adapt. Each has a ## Prerequisites section.
| Name | Type | What it does |
|---|---|---|
research-before-answer | skill | Research discipline for fact questions: individual layer (wiki+memory) + external parallel |
video-research | skill | NotebookLM CLI baseline + personal-context layered analysis |
figma-context-budget | skill | Context-efficient Figma MCP usage patterns |
wiki-promote | command | Promote mature memory conclusions to publishable wiki entity |
memory-audit | command | Memory system health diagnosis |
memory-checkpoint | command | Manual memory write (vendor model workaround) |
sync-claude-setting-cross-platform | command | Cross-machine ~/.claude/ sync flow |
pr-review | command | Dual-model PR review (Opus + Codex) |
git clone https://github.com/gggodlin/claude-skills.git
cp -r claude-skills/skills/* ~/.claude/skills/
cp claude-skills/commands/* ~/.claude/commands/The manual cp approach is intentional: read it before installing.
<details> <summary>Advanced</summary>
npx skills@latest add github:gggodlin/claude-skills (vercel-labs CLI)curl or GitHub web UI</details>
This is a public mirror for reading.
~/.claude/ periodically; expect periods of inconsistency.0BSD — take it, no attribution required.
借鑑來源 / Inspirations:
.claude/ directory style (this repo follows the same philosophy)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.