claim-ledger-to-tasks
扫描 topic 的 digests Claim Ledger，把“未核验 + 数字高影响”条目转成 tasks（核验待办）。
When & Why to Use This Skill
The claim-ledger-to-tasks skill is designed to automate the transition from raw data extraction to actionable verification. It scans topic digests for unverified, high-impact numerical claims and automatically converts them into structured tasks. This skill is essential for maintaining data integrity by ensuring that critical facts and figures are systematically tracked and verified before final use.
Use Cases
- Content Accuracy Auditing: Automatically identifying and flagging unverified statistics from video transcripts or meeting digests to ensure factual correctness in published materials.
- Research Workflow Automation: Streamlining the process of turning raw information into a prioritized list of verification tasks for researchers and analysts.
- Data Integrity Management: Filtering high-impact numerical data points from large volumes of automated summaries to prevent the propagation of ASR (Automatic Speech Recognition) noise or inaccuracies.
| name | claim-ledger-to-tasks |
|---|---|
| description | 扫描 topic 的 digests Claim Ledger，把“未核验 + 数字高影响”条目转成 tasks（核验待办）。 |
触发条件
当某个 topic 下已经批量产出了 digest（含 Claim Ledger），需要把“未核验的关键数字/口径”拆成可追踪的核验待办时使用。
目标
- 输入：
topic_id - 输出：在
tasks中创建一批“核验”任务（默认status=pending），并带上topic_id与bvid等标签，便于看板/筛选。
SOP
确认 topic
topic_id：例如bili_up_414609825_touyanxianji
dry-run 预览（推荐）
python3 scripts/claim_ledger_to_tasks.py --topic <topic_id> --dry-run --max-total 20 --max-per-digest 2
正式创建 tasks
python3 scripts/claim_ledger_to_tasks.py --topic <topic_id> --max-total 80 --max-per-digest 2- 输出 JSON 默认建议落到：
state/tmp/claim_tasks_created_*.json（便于回溯）
验证创建结果
- 可用
tasksMCP 或本地脚本查询：topic_id 过滤确认数量与标题是否合理。
- 可用
过滤规则（当前实现）
- 只处理：
核验状态=unverified - 只挑选：包含“数字 + 单位/百分比”等紧凑数值事实，并结合关键词打分（每条 digest 取 TopN）
- 目的：降低 ASR 噪声导致的“泛泛而谈”任务污染