菜单
Run, interpret, or modify Skylos safely. Use when the user asks to scan code with Skylos, explain SKY-* findings, triage dead-code false positives, audit security/secrets/SCA/LLM behavior, update Skylos rules/docs/CI, benchmark analyzer behavior, or change this repository safely.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skylos |
| description | Run, interpret, or modify Skylos safely. Use when the user asks to scan code with Skylos, explain SKY-* findings, triage dead-code false positives, audit security/secrets/SCA/LLM behavior, update Skylos rules/docs/CI, benchmark analyzer behavior, or change this repository safely. |
Use this skill to work with Skylos without rediscovering the CLI, output shape, test surface, and security guardrails.
references/cli.md.references/repo-workflow.md.references/security.md.
For scanner bypasses, LLM evidence filters, cloud/CI policy, or severity
classification, use $skylos-security.references/dead-code.md.references/ci.md.Read only the reference needed for the current task.
skylos . -a --format json for agent-readable scans.skylos . --diff origin/main --format json for PR-focused review..get(key, []); empty arrays may be omitted.git add .; stage exact paths.skylos/agents or skylos/llm; those
are Skylos runtime modules.Invoke explicitly with $skylos, or rely on automatic selection when the task
mentions Skylos scans, SKY-* findings, static analysis, security hardening,
dead-code false positives, benchmarks, or this repo's analyzer internals.
Run, interpret, or modify Skylos safely. Use when the user asks to scan code with Skylos, explain SKY-* findings, triage dead-code false positives, audit security/secrets/SCA/LLM behavior, update Skylos rules/docs/CI, benchmark analyzer behavior, or change this repository safely.
Investigate and harden Skylos security behavior. Use when the user asks to validate a security finding, reproduce a scanner bypass, assess false negatives, review LLM evidence filters, analyze CI/cloud policy trust boundaries, classify severity, or add regression tests for security-sensitive analyzer behavior.
Investigate and harden Skylos security behavior. Use when the user asks to validate a security finding, reproduce a scanner bypass, assess false negatives, review LLM evidence filters, analyze CI/cloud policy trust boundaries, classify severity, or add regression tests for security-sensitive analyzer behavior.