Skill audit report
Koharu audit report.
ML-powered manga translator, written in Rust.
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, dependency risk, and installability.
The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
PASS86
4.7K GitHub stars
Recent maintenance
PASS100
Pushed today
License clarity
PASS86
GPL-3.0
README/SKILL.md completeness
INFO74
Public metadata needs stronger README/SKILL.md context
Dependency risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add mayocream/koharu
Repository evidence
PASS86
https://github.com/mayocream/koharu
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add mayocream/koharu
Repository
88
https://github.com/mayocream/koharu
License
86
GPL-3.0
Maintenance
100
Pushed today
AI review
88
Approved with no listed issues
README/SKILL.md completeness
84
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Adoption
88
4.7K GitHub stars
Warnings
No major warnings detected from available metadata.
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options
Related skills to audit next
Maths Cs AI Compendium
Become a cracked AI/ML Research Engineer
4.5K stars · Audit report
Ceres Solver
A large scale non-linear optimization library
4.5K stars · Audit report
PINTO Model Zoo
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
4.4K stars · Audit report