Agent skill

claim-ledger

将研究与写作中的主张转成“Claim-Evidence-Boundary”可核验账本。用于在产出前强制补齐证据、反证、边界与可发布性判断,防止无依据断言并提升复用性。

Stars 0
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/hexbee/hello-skills/tree/main/skills/claim-ledger

SKILL.md

Claim Ledger

何时使用

当用户出现以下意图时使用本技能:

  • “先做研究框架/证据链,再写内容”
  • “判断某观点是否可发、是否站得住”
  • “把资料堆整理成可发布结论”
  • “让 AI 先出 Ledger 再出线程/长文”

核心定义

Claim Ledger 把每条观点拆成三部分:

  • Claim:要让读者相信的主张
  • Evidence:支持该主张的证据
  • Boundary:成立条件与失效条件

目标:让每个结论都可追溯、可反驳、可复核。

最小字段(必填 9 项)

每条 Claim 一行,必须包含:

  1. Claim IDC01/C02/...
  2. Claim:一句可检验陈述
  3. Type事实/解释/预测/建议
  4. Confidence高/中/低
  5. EvidenceE01,E02...(至少 2 条)
  6. Source GradeS/A/B/⚠️
  7. Counter:至少 1 条反证/反例;无则写“未找到,风险=高”
  8. Boundary:成立条件 + 失效条件
  9. Publishability可发/需改写/不可发

Evidence Card 规范

每条证据必须是可复核卡片,而非泛化描述。字段:

  • Source:标题 + 作者/机构 + 日期
  • Link:URL 或文档定位
  • Quote/Data:关键原话或数字
  • Supports:支持 Claim 的哪一部分
  • ReliabilityS/A/B/⚠️ + 评级理由
  • Freshness是/否(是否过时)

经验规则:

  • 事实型 Claim:至少 1 条 SA
  • 解释型 Claim:至少 2 条跨来源交叉
  • 预测/建议型 Claim:必须有历史对比或失败条件,否则降为低置信度

六步流程(从资料堆到可发布)

  1. 先写 5 条候选 Claim(先定义要证明什么)
  2. 给每条 Claim 标注类型(事实/解释/预测/建议)
  3. 每条补 2-4 条证据(优先一手源)
  4. 强制补反证/反例(没有也要显式记录)
  5. 写边界(成立条件与失效条件)
  6. 打置信度和可发布性(必要时降调措辞)

质量闸门(必须执行)

以下任一不满足,则禁止进入内容生成:

  • 任一 Claim 证据少于 2 条
  • 任一 Claim 缺少 Counter
  • 任一 Claim 缺少 Boundary
  • 预测/建议 Claim 无失败条件

处理规则:

  • 证据不足:降级为“猜测(低置信度)”
  • 语气要求:不得使用确定性措辞

与内容生产的映射

线程映射(推荐)

  • 3 个 Claim × 4 条推 = 12 条线程
  • 每组 4 条顺序:
    1. Claim
    2. Evidence
    3. Boundary
    4. Action

长文映射(推荐)

每个 Claim 作为一节:

  • 结论 -> 证据 -> 反方风险 -> 边界 -> 小结/清单

默认输出格式

  1. Claim Ledger 表(至少 3 条 Claim)
  2. Evidence Cards(与 Ledger 的 E# 对齐)
  3. Gate Check(逐条列出通过/失败项)
  4. 若 Gate 全通过,才生成目标内容(线程/长文/脚本)

执行指令模板

text
先输出 Claim Ledger(至少 3 条 Claim,每条 >=2 条证据 + >=1 条反证 + 边界)。
未满足质量闸门前,不允许生成正文。
若证据不足,必须降级为“猜测(低置信度)”,并避免确定性语气。

参考模板与示例

需要直接套用表格和卡片时,读取:

  • references/templates.md

需要自动校验 Ledger 质量闸门时,运行:

  • scripts/validate_ledger.py --file <ledger.md>

Expand your agent's capabilities with these related and highly-rated skills.

hexbee/hello-skills

analogy-commentary

Turn source content into a familiar analogy framework, then produce concise commentary angles and a short take. Use when the user asks whether a post, article, speech, or idea is “like” a known story, theory, faction, historical pattern, or strategic lens.

0 0
Explore
hexbee/hello-skills

deep-productivity

Master deep work productivity through the three types of work framework (Building, Maintenance, Recovery). Use when user needs to: (1) Build a sustainable deep work routine with just 1 hour/day, (2) Create vision/anti-vision for life direction, (3) Structure goals using the 10-year → 1-year → 1-month → 1-week hierarchy, (4) Apply project-based learning to bridge skill gaps, (5) Identify lever-moving tasks that actually progress goals, (6) Balance focus work with necessary recovery for creativity.

0 0
Explore
hexbee/hello-skills

multi-agent-systems

Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolation for high-volume operations, (3) Parallelizing independent research tasks, (4) Creating specialized agents with focused tool sets, (5) Building verification subagents for quality assurance, or (6) Analyzing context-centric decomposition boundaries.

0 0
Explore
hexbee/hello-skills

agent-first-product-strategy

Reframe AI product and SaaS strategy from human-user assumptions to agent-first execution. Use when redefining product positioning, success metrics, API/docs priorities, go-to-market, or roadmap decisions for an AI-native market where agents are primary software users.

0 0
Explore
hexbee/hello-skills

debog-yourself

Help users identify and escape psychological traps that are holding them back. Use when user feels stuck, unable to progress, facing a deadlock, or experiencing decision paralysis. Provide diagnostic frameworks and specific strategies to help users understand which trap pattern they're in and find a path forward.

0 0
Explore
hexbee/hello-skills

china-model-selection-guide

China model selection and task-routing guide for Doubao-Seed-2.0-Code, GLM-5, MiniMax-M2.5, and Kimi-K2.5. Use when users need to choose the best-fit model by input type, task complexity, engineering constraints, and delivery goals, including staged multi-model workflows.

0 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results