OpenAgentSkill Task
Task: Scan a project for security risks
Intent: Find risky dependencies, exposed secrets, unsafe patterns, and practical remediation steps.
Agent prompt: Find the best skill for scanning a code project for security risks and producing prioritized remediation steps.

Success criteria:
- Prioritizes findings
- Explains remediation
- Separates warnings from confirmed issues

Do not use when:
- The scan touches production secrets
- The result is used as a formal compliance audit
- Repository access is incomplete

Resolve API:
https://www.openagentskill.com/api/agent/resolve?task=Find%20the%20best%20skill%20for%20scanning%20a%20code%20project%20for%20security%20risks%20and%20producing%20prioritized%20remediation%20steps.&agent=codex&max_risk=medium

Ranked skills:
1. Code Review (mattpocock-code-review)
   Match score: 811
   Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
   Trust: 91/100 Production candidate
   Audit: 94/100 Safe to try
   Install: npx skills add mattpocock/skills --skill code-review
   Detail: https://www.openagentskill.com/skills/mattpocock-code-review
   Install API: https://www.openagentskill.com/api/skills/mattpocock-code-review/install
---
2. Awesome Codex Skills (composiohq-awesome-codex-skills)
   Match score: 808
   A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
   Trust: 82/100 Strong shortlist
   Audit: 87/100 Safe to try
   Install: npx skills add ComposioHQ/awesome-codex-skills
   Detail: https://www.openagentskill.com/skills/composiohq-awesome-codex-skills
   Install API: https://www.openagentskill.com/api/skills/composiohq-awesome-codex-skills/install
---
3. Vercel React Best Practices (vercel-react-best-practices)
   Match score: 805
   React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
   Trust: 91/100 Production candidate
   Audit: 94/100 Safe to try
   Install: npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
   Detail: https://www.openagentskill.com/skills/vercel-react-best-practices
   Install API: https://www.openagentskill.com/api/skills/vercel-react-best-practices/install
---
4. Andrej Karpathy Skills (multica-ai-andrej-karpathy-skills)
   Match score: 797
   A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
   Trust: 85/100 Strong shortlist
   Audit: 87/100 Safe to try
   Install: npx skills add multica-ai/andrej-karpathy-skills
   Detail: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills
   Install API: https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install
---
5. Scanners Box (we5ter-scanners-box)
   Match score: 794
   A powerful and open-source toolkit for hackers and security automation - 安全行业从业者自研开源扫描器合辑
   Trust: 87/100 Production candidate
   Audit: 92/100 Safe to try
   Install: npx skills add We5ter/Scanners-Box
   Detail: https://www.openagentskill.com/skills/we5ter-scanners-box
   Install API: https://www.openagentskill.com/api/skills/we5ter-scanners-box/install