Nm Leyline Evaluation Framework

Patterns for building evaluation and scoring systems, quality gates, rubrics, and decision frameworks. Use for any scored assessment

This skill is documentation-only: it provides templates and code examples for building scoring/threshold systems and does not require credentials or install anything. Before using it in an automated agent: (1) review and adapt the example commands/tests—the SKILL.md includes generic 'run --help' and 'pytest -v' checks but no bundled binaries or tests; (2) if you intend to automate decisions based on these thresholds, validate them with historical data and add veto/safety checks to avoid unwanted automated actions; (3) the agent may call this skill autonomously (normal default), so ensure decision rules and escalation paths are explicit and safe for your environment.

Type: OpenClaw Skill Name: nm-leyline-evaluation-framework Version: 1.0.0 The bundle provides a comprehensive framework for evaluation, scoring, and decision-making, including documentation and examples for weighted criteria and thresholds. While SKILL.md contains repetitive 'Verification' instructions suggesting the agent run commands like 'pytest' or check '--help' flags, these appear to be artifacts of the porting process from the 'claude-night-market/leyline' project rather than malicious prompt injections. There is no evidence of data exfiltration, unauthorized execution, or persistence mechanisms in any of the files.