Unified Reasoning
ReviewAudited by ClawScan on May 10, 2026.
Overview
This mostly looks like a reasoning helper, but the included wrapper tries to execute an unlisted implementation file, so the runnable code is not fully reviewable.
Review the full implementation before installing. In particular, verify whether `unified_reasoning.py` or the referenced PowerShell engine exists outside the manifest, and avoid letting this skill influence important autonomous decisions until the code is complete and inspectable.
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If an unlisted `unified_reasoning.py` file is present or added later, it could run under the skill’s privileges without being part of this review; if it is absent, the skill may simply fail to work.
The wrapper automatically tries to load and execute a local implementation file, but the supplied manifest only includes SKILL.md and unified_wrapper.py. That makes the actual implementation unavailable for review and creates an unlisted-code/provenance gap.
self._load_original() ... Path(__file__).parent / "unified_reasoning.py" ... spec.loader.exec_module(module)
Do not trust or deploy the skill until the author includes the full implementation in the manifest or removes the dynamic loader. Review any `unified_reasoning.py` file before allowing it to run.