configure-edt — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited configure-edt (Agent Skill) 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.
What type of work are you doing?
These are always installed regardless of context:
anti-slop (quality gate)taste-audit (automated checks)common/taste.md, common/writing-quality.md, common/accessibility.mddesign-reviewer, copy-editorBased on Step 1 selection, copy relevant skills and agents.
{
"hooks": {
"PostToolUse": [
{
"matcher": "tool == 'Edit' && tool_input.file_path matches '\\.(tsx|jsx|html|css)$'",
"hooks": [{"type": "command", "command": "node scripts/hooks/check-ai-slop.js"}]
}
]
}
}Run node tests/run-all.js to confirm all components are properly installed.
# Clone the repo
git clone https://github.com/0xDragoon/everything-design-taste.git
cd everything-design-taste
# Install dependencies
npm install
# Full install (all skills, agents, rules)
./install.sh --profile full
# Selective install
./install.sh --profile product-design
./install.sh --profile brand-design
./install.sh --profile strategic
./install.sh --profile leadership~/.claude/ (applies to all projects).claude/ (applies to current project only)~/.claude/skills/ or .claude/skills/~/.claude/rules/ or .claude/rules/~/.claude/agents/ or .claude/agents/~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.