‹ 首页

openskills-runtime-debug

@geeksfino · 收录于 1 周前

Diagnose openskills-runtime execution failures in sandboxed paths (Landlock, seatbelt, native script execution, wasm execution) and produce root-cause-first findings with minimal-risk remediation steps.

场景沙盒调试运行时故障排查

适合你，如果需要在受限环境中定位执行失败原因

/ 下载安装
openskills-runtime-debug.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add geeksfino/openskills/openskills-runtime-debug
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- geeksfino/openskills/openskills-runtime-debug
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify geeksfino/openskills/openskills-runtime-debug
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
62GitHub stars
~310上下文体积 · 单文件
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · Apache-2.0 · 6274675

OpenSkills Runtime Debug

Use this skill when debugging runtime failures in runtime/ and execution paths used by run_skill_target, native scripts, or sandbox enforcement.

Primary Targets
  • runtime/src/executor.rs
  • runtime/src/native_runner.rs
  • runtime/src/wasm_runner.rs
  • runtime/src/permissions.rs
  • runtime/tests/*sandbox*
  • runtime/tests/seatbelt_tests.rs
Workflow
  1. Reproduce with the smallest command that fails.
  2. Classify failure bucket:
  3. sandbox policy issue
  4. feature/config mismatch
  5. script/tool resolution issue
  6. wasm runtime issue
  7. Confirm behavior against tests and existing fallback logic.
  8. Propose the smallest safe fix that preserves security boundaries.
  9. Re-run focused tests, then broader runtime tests.
Recommended Commands
cargo check -p openskills-runtime
cargo test -p openskills-runtime
cargo test -p openskills-runtime seatbelt_tests -- --nocapture
Debug Heuristics
  • Treat silent degradation in sandbox setup as high risk.
  • Prefer explicit error propagation over ignored Result.
  • If fallback behavior is intentional, confirm it is visible in logs and tests.
  • Keep macOS and Linux behavior differences explicit in findings.
Output Format

Return:

  1. Root cause
  2. Impact surface
  3. Fix proposal
  4. Verification evidence
  5. Residual risks
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…