Skill audit report
Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TNR, judge validation, inter-rater agreement, Cohen's kappa, bias detection, or "is my automatic evaluation trustworthy." Merges the calibrate and align functions into one skill.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
816 GitHub stars
Stars/forks activity
INFO71
816 stars, 65 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
1mo since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO72
command execution surface
Install availability
PASS92
npx skills add agentscope-ai/OpenJudge --skill align-human
Install command safety
PASS92
standard package or runtime install path
Permission surface
INFO62
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/03-align-human
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add agentscope-ai/OpenJudge --skill align-human
Repository
88
https://github.com/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/03-align-human
License
86
Apache-2.0
Maintenance
88
1mo since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
86
Usable description available
Dependency risk
72
command execution surface
Install command safety
92
standard package or runtime install path
Permission surface
62
shell or command execution, filesystem or document access
Stars/forks activity
71
816 stars, 65 forks; issue activity unavailable in current metadata
Adoption
88
816 GitHub stars
Warnings
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
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175K Stars · Audit report
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85K Stars · Audit report
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K Stars · Audit report