Compile one portable agent skill manifest into practical starter files for multiple coding agents.
SaferSkills independently audited skillport (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.
One portable skill manifest, practical starter files for multiple coding agents.
Skill repos often say "works with Claude Code, Codex, Cursor, Gemini, and Copilot" by hand. SkillPort turns that into a repeatable build step: write one skillport.json, validate it, and compile target-specific instruction files.
git clone https://github.com/redkoai/skillport.git
cd skillport
npm test
npm run demoThe demo writes generated files to:
dist/demo/{
"name": "Precise Debugging",
"description": "Make an agent identify concrete failure modes instead of generic advice.",
"instructions": "Name the exact failure mode, identify the likely state boundary, and propose one concrete fix.",
"targets": ["universal", "codex", "claude", "cursor", "gemini", "copilot"]
}Build:
node ./bin/skillport.js build --manifest examples/skill/skillport.json --out dist/demoGenerated outputs:
SKILL.mdcodex/AGENTS.mdclaude/CLAUDE.mdcursor/.cursor/rules/precise-debugging.mdcgemini/GEMINI.mdcopilot/.github/copilot-instructions.mdskillport.manifest.jsonGenerated files are practical starter outputs, not a promise that every agent treats them as an official plugin package. The point is portability, reviewability, and less manual drift.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.