从纪要、聊天或项目材料中提取决策、负责人、截止时间、前提假设与撤销条件。；use for decision, meeting, governance workflows；do not use for 编造不存在的决策, 替代法律审计.

This skill appears to be what it says: a local, read-only (by default) tool to extract and structure decisions. Before installing or running: - Review scripts/run.py (already included) — it only uses the Python standard library and does not make network calls or run shell pipes. - When running, prefer --dry-run first and avoid pointing the script at system or repository roots that may contain secrets (e.g., /, ~/.ssh, CI config dirs). The script will read many file types and could surface sensitive lines if you feed it a directory with credentials. - If you plan to let the agent invoke the skill autonomously, be deliberate about allowed inputs (restrict directories/files) so it cannot be asked to scan unexpected local paths. - Run the provided smoke test locally to confirm behavior (python3 scripts/run.py --input examples/example-input.md --output out.md) and inspect outputs before using on sensitive data.

Type: OpenClaw Skill Name: decision-ledger Version: 1.0.0 The 'decision-ledger' skill bundle is a legitimate utility designed to extract and organize decisions, owners, and deadlines from meeting notes and project materials. The core logic in scripts/run.py is a versatile reporting tool that supports structured data extraction, directory auditing, and security pattern scanning (e.g., detecting hardcoded secrets or dangerous commands), which aligns with the stated 'governance' and 'audit' use cases. The script follows safe practices by masking detected secrets in its output and lacks any indicators of data exfiltration, unauthorized execution, or malicious intent.