SkillRank vs SkillSpector
AI-agent skill evaluation and security scanning compared
skillrank helps developers discover, install, and evaluate coding-agent skills, while SkillSpector scans skills for security risks before installation. The main difference is scope: skillrank measures a skill’s effect on task outcomes, whereas SkillSpector assesses potential security issues.
SkillRank: Find and Evaluate AI-Agent Skills
SkillRank is a Rust CLI and public registry for finding, installing, and evaluating skills used by Claude Code, Codex, Copilot, and other agents. Its paired evals measure skill effects on token use, speed, and success, and it integrates with BuildBetter ZeroShot.
SkillSpector: Scan AI Agent Skills for Security Risks
SkillSpector is a Python security scanner for Claude Code, Codex, Gemini CLI, and MCP agent skills. Its LangGraph-based pipeline combines static checks with optional LLM review to flag vulnerabilities and risky behavior before installation.
| SkillRank | SkillSpector | |
|---|---|---|
| Language | Rust | Python |
| License | MIT | Apache-2.0 |
| Stars | 0 | 20.6k |
| Forks | 0 | 1.8k |
| Last analyzed | Oct 22, 2026 | Oct 20, 2026 |
Key differences
- skillrank pairs runs with and without a skill and reports changes in success, tokens, turns, time, and cost; SkillSpector analyzes files for suspicious behavior and dependency vulnerabilities.
- skillrank is a Rust CLI with skill search, installation, recommendations, and local registry support; SkillSpector is a Python scanner for local files, repositories, URLs, and archives.
- skillrank supports MCP tools for Claude Code and Codex; SkillSpector offers an MCP server for agent-driven security scans.
- skillrank uses the MIT license for its CLI and core library, while its hosted registry and website use Elastic License 2.0; SkillSpector uses Apache-2.0.
- skillrank evaluations run on the user's agent and depend on the task suite and trial count; SkillSpector combines static checks with optional LLM analysis and does not execute or sandbox skills.
- The supplied project figures list skillrank at 0 stars and 0 forks, and SkillSpector at 19.3k stars and 1.7k forks.
Choose SkillRank if you…
- want to test whether a skill changes task success, effort, time, or cost on your agent.
- need to find, install, or recommend skills for a repository and track verified installations.
- want a local registry or MCP-based skill management for Claude Code or Codex.
Choose SkillSpector if you…
- need to review a skill for suspicious instructions, risky code, or dependency vulnerabilities before installation.
- want security scan reports in terminal, JSON, Markdown, or SARIF for people or CI workflows.
- need static checks with optional LLM explanations, baselines, or agent-driven MCP scanning.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.