Updated 2w ago
by SuperChason
ontology-driven-ai-data-management-skills
16 cross-platform Agent Skills for enterprise ontology engineering, supporting Codex, Claude Code, and WorkBuddy.
21 GitHub stars (21)
+6 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | +1 |
| Oct 17 | +2 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | 0 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | +2 |
| Oct 31 | 0 |
| Nov 1 | 0 |
- 25 skills (25 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add SuperChason/ontology-driven-ai-data-management-skills
Asks which skills and agents to install. Just one: npx skills add SuperChason/ontology-driven-ai-data-management-skills --skill action-contract-execution-feedback-loop — add -g for every project.
Claude Code
git clone https://github.com/SuperChason/ontology-driven-ai-data-management-skillscp -r "ontology-driven-ai-data-management-skills/skills/action-contract-execution-feedback-loop" ~/.claude/skills/
Copies the action-contract-execution-feedback-loop skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add SuperChason/ontology-driven-ai-data-management-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
action-contract-execution-feedback-loop
用于需要把一个业务动作封装成Agent可调用工具、要设计动作执行前校验、重试和降级,用户出现“帮我定义Action契约”“这个动作失败后怎么办”或 action contract, pre-check, retry and fallback 等信号时调用。控制模式未定时可生成候选契约及模式选项,实际执行前落实授权与控制条件。
skills/action-contract-execution-feedback-loop/SKILL.md on GitHub (opens in a new tab) -
ai-training-inference-data-asset-governance
用于需要建设AI数据资产目录、训练数据、实时事实、规则和推理结果混在一起,用户出现“AI数据资产怎么分类”“训练和推理数据怎么分”或 AI data assets, training vs inference, provenance governance 等信号时调用。不适用于只需要普通数据仓库分层设计。
skills/ai-training-inference-data-asset-governance/SKILL.md on GitHub (opens in a new tab) -
business-scenario-deep-analysis
用于智能体作用已初步识别,需要把业务场景完整梳理成可建模、可开发和可验收的场景规格,用户出现“把这个场景完整详细梳理”“先把业务过程、判断和异常弄清楚”或 business scenario deep analysis, scenario specification 等信号时调用。不适用于只做本体适配初判或已经拥有完整场景规格。
skills/business-scenario-deep-analysis/SKILL.md on GitHub (opens in a new tab) -
data-to-ontology-mapping-and-instantiation
用于已有逻辑本体和数据语义(包括明确隔离的候选版本),需要说明数据记录如何对应本体类、字段如何对应属性、关联如何对应对象关系,并生成可追溯实例,用户出现“把数据映射到本体类和属性”“生成本体实例”或 data-to-ontology mapping, ontology instantiation 等信号时调用。不适用于首次寻找真实系统中的表、字段和接口。
skills/data-to-ontology-mapping-and-instantiation/SKILL.md on GitHub (opens in a new tab) -
fact-reason-action-business-loop
用于需要把模糊业务描述转成Agent可用模型、需要解释一个判断怎样落到系统动作,用户出现“帮我按事实事理行动拆解”“这个判断依据和动作怎么串起来”或 fact-reason-action, business loop, traceable action 等信号时调用。不适用于只需要解释术语或摘要文档。
skills/fact-reason-action-business-loop/SKILL.md on GitHub (opens in a new tab) -
fact-reason-goal-explainable-decision
用于需要解释Agent为什么得出某个业务判断、实时事实、业务规则和多个目标需要综合决策,用户出现“按事实事理目标分析”“这个决策依据是什么”或 fact-reason-goal, explainable decision, goal trade-off 等信号时调用。不适用于事实来源和任务目标均未明确。
skills/fact-reason-goal-explainable-decision/SKILL.md on GitHub (opens in a new tab) -
five-ring-ontology-engineering-lifecycle
用于需要规划企业本体建设项目、已有模型原型但缺少上线和运营路径,用户出现“按五环规划实施”“本体项目需要哪些阶段和产出”或 ontology lifecycle, five-ring, production readiness 等信号时调用。不适用于仅需制作一次性概念演示。
skills/five-ring-ontology-engineering-lifecycle/SKILL.md on GitHub (opens in a new tab) -
intent-driven-minimal-ontology-loading
用于Agent上下文过长或本体加载过多、同一问法可能对应不同业务意图,用户出现“只加载当前需要的本体”“这个意图该路由到哪个子本体”或 minimal ontology, intent routing, hybrid retrieval 等信号时调用。不适用于意图尚未澄清却直接静默路由。
skills/intent-driven-minimal-ontology-loading/SKILL.md on GitHub (opens in a new tab) -
ontology-ai-application-pattern-selection
用于场景已确认适合本体,需要选择应用架构、问答、审核、协同、决策和PDCA方案混在一起,用户出现“这个场景属于哪种应用模式”“六类模式怎么选”或 application pattern, ontology AI patterns, workflow vs PDCA 等信号时调用。适配证据不足时可比较候选模式与轻量替代方案,不据此启动正式建设。
skills/ontology-ai-application-pattern-selection/SKILL.md on GitHub (opens in a new tab) -
ontology-ai-scenario-fit-and-spike
用于准备为一个企业AI场景选择本体技术路线、项目范围很大,需要确定首个小切口,用户出现“这个场景适合做本体吗”“先做哪个小切口”或 ontology fit, vertical slice, go/no-go 等信号时调用。不适用于纯信息查询或单表统计,现有查询能力即可满足。
skills/ontology-ai-scenario-fit-and-spike/SKILL.md on GitHub (opens in a new tab) -
ontology-conceptual-model-design
用于场景语义已经形成,需要把术语、对象、关系、规则、状态、权限、动作和目标组织成业务专家可阅读审查的概念模型,用户出现“把语义清单画成概念模型”“给业务专家做本体模型评审”或 conceptual ontology model, business model views 等信号时调用。不适用于直接编写RDF/OWL文件或只定义单个术语。
skills/ontology-conceptual-model-design/SKILL.md on GitHub (opens in a new tab) -
ontology-constraint-and-knowledge-injection
用于要决定本体知识写进Prompt、走RAG还是微调、规则型任务需要提高可解释性和一致性,用户出现“Prompt RAG 微调怎么选”“本体怎么注入大模型”或 knowledge injection, prompt vs RAG vs fine-tuning, ontology constraint 等信号时调用。知识范围未定时先从当前任务提炼候选最小范围,再比较注入路径。
skills/ontology-constraint-and-knowledge-injection/SKILL.md on GitHub (opens in a new tab) -
ontology-golden-case-testing
用于需要验收本体能否回答真实业务问题、本体规则或版本变化后要做回归,用户出现“帮我设计本体测试用例”“怎么做黄金问题集”或 golden cases, ontology regression, test matrix 等信号时调用。不适用于只有形式化语法错误,需要先走模型质量门。
skills/ontology-golden-case-testing/SKILL.md on GitHub (opens in a new tab) -
ontology-logical-model-generation
用于已有概念模型或可明确列出假设的业务语义,需要生成机器可处理的类、属性、关系、词汇、约束、查询和动作接口,用户出现“生成逻辑本体模型”“把概念模型转成RDF OWL SHACL”或 logical ontology generation, TTL, SHACL shapes 等信号时调用。不适用于只需澄清业务语义或审查现有模型质量;未确认输入可生成候选逻辑模型。
skills/ontology-logical-model-generation/SKILL.md on GitHub (opens in a new tab) -
ontology-model-multilayer-quality-gate
用于大模型生成了本体,需要判断能否使用、准备评审本体模型质量和生产准入,用户出现“帮我做本体质量审查”“双模型怎么校验”或 ontology quality gate, dual-model audit, semantic review 等信号时调用。不适用于把同一个模型的自我反思当作独立审核。
skills/ontology-model-multilayer-quality-gate/SKILL.md on GitHub (opens in a new tab) -
ontology-runtime-service-and-version-operations
用于本体已建成,需要以服务方式供多个Agent调用、业务规则存在多版本并行和灰度发布,用户出现“怎么做本体即服务”“本体版本如何灰度和回滚”或 ontology as a service, semantic versioning, runtime governance 等信号时调用。草稿阶段可设计服务与发布方案;实际生产发布须通过质量与业务用例验收。
skills/ontology-runtime-service-and-version-operations/SKILL.md on GitHub (opens in a new tab) -
ontology-scenario-delivery
用于用户拿到一个企业业务场景,希望从本体适配、智能体作用、场景梳理、数据需求、知识结构和语义模型一路推进到逻辑本体、实例、验证与发布,用户出现“按这个场景生成完整本体建设包”“直接指导这个本体怎么落地”或 scenario-to-ontology delivery, ontology work package 等信号时调用。不适用于只询问某个本体术语或只需要单阶段专项产物。
skills/ontology-scenario-delivery/SKILL.md on GitHub (opens in a new tab) -
point-line-plane-ontology-scaling
用于首个本体场景验证成功,准备扩大范围、多个局部本体开始重复或冲突,用户出现“怎么从点扩到线和面”“这个本体怎么复用到其他场景”或 point-line-plane, ontology scaling, federated ontology 等信号时调用。不适用于首个场景尚未形成价值闭环。
skills/point-line-plane-ontology-scaling/SKILL.md on GitHub (opens in a new tab) -
risk-based-agent-action-modes
用于要决定Agent能否自动执行某个业务动作、需要设计人工审批或接管点,用户出现“这个动作能自动执行吗”“哪里需要人工介入”或 human in the loop, action autonomy, multi-agent mode 等信号时调用。不适用于只需描述具体API参数和错误码。
skills/risk-based-agent-action-modes/SKILL.md on GitHub (opens in a new tab) -
scenario-agent-role-design
用于业务场景已初步明确,需要判断智能体能帮助哪一部分、在场景中发挥什么作用,并划分Agent、确定性系统和人工职责,用户出现“这个场景智能体能做什么”“先识别Agent的作用”或 agent role in scenario, human-system-agent boundary 等信号时调用。不适用于已经确定Agent任务、只需设计具体Action契约。
skills/scenario-agent-role-design/SKILL.md on GitHub (opens in a new tab) -
scenario-data-requirements-readiness
用于场景和Agent任务已经梳理,需要判断业务、财务、IT等数据分别需要什么、来自哪些系统表字段、质量权限是否满足,用户出现“这个场景需要哪些数据”“业务财务IT三类数据怎么盘点”或 scenario data requirements, data readiness 等信号时调用。不适用于把已确认数据映射为本体类、属性和实例。
skills/scenario-data-requirements-readiness/SKILL.md on GitHub (opens in a new tab) -
scenario-related-knowledge-structure
用于场景范围和数据需求已经明确,需要盘点完成Agent任务所需的制度、文档、数据、案例、专家和已有知识资产,并建立来源、证据、责任和缺口结构,用户出现“梳理这个场景相关的知识结构”“这些知识从哪里来”或 scenario knowledge structure, evidence landscape 等信号时调用。不适用于定义对象、关系、约束和规则的正式业务语义。
skills/scenario-related-knowledge-structure/SKILL.md on GitHub (opens in a new tab) -
scenario-related-semantic-modeling
用于场景、数据需求和知识来源已经梳理,需要统一定义当前场景的术语、概念、业务对象、属性、分类、继承、关系、约束、规则、事件、状态、权限、动作、目标和评价,用户出现“建设场景相关的语义模型”“这些对象关系和约束怎么定义”或 scenario semantic model, business semantics 等信号时调用。不适用于只盘点知识来源或直接生成TTL文件。
skills/scenario-related-semantic-modeling/SKILL.md on GitHub (opens in a new tab) -
seven-plus-one-semantic-mapping
用于需要把业务描述映射为本体语义、要检查Agent知识、规则、权限和动作是否完整,用户出现“按7+1映射一下”“这个场景缺哪些语义”或 7+1 semantic mapping, ontology schema, action semantics 等信号时调用。不适用于输入知识仍处于自由讨论、没有来源和责任人。
skills/seven-plus-one-semantic-mapping/SKILL.md on GitHub (opens in a new tab) -
twenty-nine-sentence-knowledge-extraction
用于要从制度和业务资料提取本体知识、专家说得很散,需要结构化访谈,用户出现“怎么访谈业务专家”“用29句话提取知识”或 knowledge elicitation, expert interview, 29 sentences 等信号时调用。资料来源或专家尚缺时可形成访谈提纲与候选知识,不能声明为已确认事实。
skills/twenty-nine-sentence-knowledge-extraction/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.