Openskills runtime debug

Skill Geeksfino/openskills/.cursor/skills/openskills-runtime-debug

Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing

Install

npx -y skills add Geeksfino/openskills --skill openskills-runtime-debug

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

1.6 KB, as published. Nobody here has run it

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

Reproduce with the smallest command that fails.
Classify failure bucket:
- sandbox policy issue
- feature/config mismatch
- script/tool resolution issue
- wasm runtime issue
Confirm behavior against tests and existing fallback logic.
Propose the smallest safe fix that preserves security boundaries.
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:

Root cause
Impact surface
Fix proposal
Verification evidence
Residual risks