twenty-nine-sentence-knowledge-extraction

twenty-nine-sentence-knowledge-extraction is a skill for Codex from SuperChason/ontology-driven-ai-data-management-skills. It costs 92 tokens per session (1,561 once invoked), scanned A, original, MIT.

A structured interview method for turning documents, data, procedures, and expert knowledge into information that can support an ontology. Its 29 question areas cover concepts, rules, processes, permissions, actions, and quality constraints.

In plain words
What is it for?
Use it to interview experts, extract rules and exceptions, unify terminology, record conflicts, and prepare material for ontology design.
Why use it?
It turns scattered or unstated business knowledge into traceable, confirmed input instead of treating guesses as rules.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to interview experts, extract rules and exceptions, unify terminology, record conflicts, and prepare material for ontology design.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SuperChason/ontology-driven-ai-data-management-skills --skill twenty-nine-sentence-knowledge-extraction
Clone the repo
git clone --depth 1 https://github.com/SuperChason/ontology-driven-ai-data-management-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for twenty-nine-sentence-knowledge-extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction/github.svg)](https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction)
Your own site
<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for twenty-nine-sentence-knowledge-extraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/twenty-nine-sentence-knowledge-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01561
Opus 5 $0.00046 $0.00781
Sonnet 5 $0.00018 $0.00312
Haiku 4.5 $0.00009 $0.00156

Measured 4d ago against content hash 80a5af95fe2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

twenty-nine-sentence-knowledge-extraction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/twenty-nine-sentence-knowledge-extraction/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

用“29句话”提取业务知识

方法骨架

  • 用一组固定问句把文档、数据和专家经验转成可建模的业务知识。
  • 问题覆盖对象、属性、关系、分类、标识、规则、流程、查询、权限、Action和质量约束。
  • 显性知识可从制度、流程、表结构和接口中抽取,隐性知识通过专家访谈补齐。
  • 每个答案都要保留来源、适用范围、例外和确认人,避免把口头经验直接固化。
  • 相近答案合并为统一术语,冲突答案进入待裁决清单。
  • 输出应能直接交给7+1映射和本体建模质量门。

执行完整提取或设计专家访谈时,先读取 29 类建模语句,按与当前场景相关的类别逐项作答。

触发场景

用户会在什么情境下需要这个 Skill

  1. 要从制度和业务资料提取本体知识
  2. 专家说得很散,需要结构化访谈
  3. 现有知识库只有文档,缺少规则、权限和行动语义

语言信号

  • “怎么访谈业务专家”
  • “用29句话提取知识”
  • “把制度整理成本体输入”
  • 英文信号:knowledge elicitation, expert interview, 29 sentences

与相邻 Skill 的区分

  • seven-plus-one-semantic-mapping:本 skill 负责采集和澄清自然语言知识;7+1负责将确认后的知识映射为语义构件。
  • ontology-model-multilayer-quality-gate:本 skill 检查输入知识是否齐备;多层质量门检查形式化模型是否正确。

执行步骤

按当前任务选择必要步骤;已有可靠成果直接复用:

  1. 盘点来源

    • 动作:列出制度、流程、表单、数据字典、接口、案例和专家,并标记权威级别与版本。
    • 完成标准:每类知识有来源负责人和适用时间。
  2. 按29类问题提取

    • 动作:依次追问对象属性、对象关系、分类约束、术语、规则、操作与服务、权限和七类查询更新语义。
    • 完成标准:每个相关问题都有答案、无答案原因或待确认责任人。
  3. 追问隐性判断

    • 动作:用真实案例、反例、边界条件和历史异常追问专家实际怎样判断。
    • 完成标准:模糊词被替换为阈值、条件、优先级或人工裁决点。
  4. 统一与裁决

    • 动作:合并同义词,标出同物异名、同名异义、规则冲突和跨域差异。
    • 完成标准:形成已确认词汇、冲突清单和待确认项。
  5. 交付建模输入

    • 动作:按来源、语义类别、自然语言描述、例外、确认状态组织输出。
    • 完成标准:输入满足清晰、正确、完整、最简四项要求。

固定输出

  • 知识来源与权威级别登记表:制度、流程、表单、数据字典、接口、案例和专家的版本、责任和适用范围
  • 29 类建模语句回答表:语句编号、当前场景是否适用、自然语言答案、来源、证据位置、适用范围、例外、状态、责任人和对应场景任务
  • 术语归一表:标准术语、同义词、同名异义、使用语境和裁决结果
  • 规则、权限、Action 和质量约束的边界、反例与例外清单
  • 知识冲突与待裁决表:冲突编号、差异来源、影响、裁决人、期限和状态
  • 无答案类别、不适用类别、资料缺口和专家访谈问题清单
  • 交付 7+1 映射与场景语义建模的输入包

与当前场景无关的类别记录不适用理由,不使用虚构答案填满表格。

使用边界

不要在以下情况使用

  • 把来源不明且未经业务确认的提取结果作为正式知识;可继续设计访谈和整理候选条目
  • 用户只需要普通会议纪要或文档摘要
  • 已经存在经过验证的结构化语义模型,仅需运行时调用

常见失败模式

  • 纯人工符号建模或纯神经生成走向单边极端:单一技术范式无法同时覆盖语义抽象效率、业务约束、泛化能力和可解释性。
  • 专家经验以模糊规则直接固化:隐含前提在结构化过程中丢失,Agent把宽泛条件解释为确定触发器并直接行动。

使用折扣与复核要求

  • 29类问句降低采集门槛,无法自动判断专家经验是否有效或仍然适用。
  • 大模型生成形式结构无法直接证明业务语义正确,生产使用需保留专家确认、工具校验、真实用例和审计记录。

相关 Skills

  • depends-onscenario-related-knowledge-structure;先确定材料、专家和证据范围。
  • feeds-intoscenario-related-semantic-modelingseven-plus-one-semantic-mapping;本 Skill 负责采集和澄清,后续完成正式语义定义和完整性检查。

Read the full file on GitHub · 107 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago Changed · +12 tokens per session 80a5af95fe2a
  2. 8d ago Changed · +10 lines b64f562d4ae2
  3. 12d ago First seen · 97 lines · 80 tokens per session scan A 6802b66447d9

Subscribe to this mod's changes

twenty-nine-sentence-knowledge-extraction is a skill published in the GitHub repository SuperChason/ontology-driven-ai-data-management-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 1,561 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

open-ontologies

AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…

fabio-rovai/open-ontologies · 110 tokens

mykg

Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…

SenolIsci/mykg · 175 tokens

ontology-ontology-architect

Design a domain ontology from evidence using layered modeling, stable concept definitions, explicit relations, SKOS-first structure, and selective OWL formalization with recorded modeling decisions.

Mokee04/ontology_research · 39 tokens

understand-explain

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.

Egonex-AI/Understand-Anything · 27 tokens

rwkv-architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

davila7/claude-code-templates · 72 tokens

graphify

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…

Graphify-Labs/graphify · 76 tokens