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.
npx skills add SuperChason/ontology-driven-ai-data-management-skills --skill ai-training-inference-data-asset-governancegit clone --depth 1 https://github.com/SuperChason/ontology-driven-ai-data-management-skillsWrote 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.
[](https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/ai-training-inference-data-asset-governance)<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/ai-training-inference-data-asset-governance"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/ai-training-inference-data-asset-governance/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.
<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/ai-training-inference-data-asset-governance"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/ai-training-inference-data-asset-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.01345 |
| Opus 5 | $0.00040 | $0.00673 |
| Sonnet 5 | $0.00016 | $0.00269 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
ai-training-inference-data-asset-governance 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.
What it actually says
面向训练与推理的 AI 数据资产治理
方法骨架
- 按消费方式和责任边界区分作业、分析和AI数据资产。
- AI资产内部继续区分训练样本、运行时事实、事理模型、推理结果和过程日志。
- 事实尽量留在权威源系统，通过不可变标识、版本和动态引用参与推理。
- 事理资产保存规则、因果、流程、权限和适用范围。
- 推理结果必须连接输入事实、模型版本和过程日志，支持追溯和复现。
- 治理输出包括目录、来源、责任、质量、权限、生命周期和审计字段。
触发场景
用户会在什么情境下需要这个 Skill
- 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
- 要明确AI数据的来源、版本、责任和审计边界
语言信号
- “AI数据资产怎么分类”
- “训练和推理数据怎么分”
- “事实规则和推理结果怎么治理”
- 英文信号：AI data assets, training vs inference, provenance governance
与相邻 Skill 的区分
- 与
seven-plus-one-semantic-mapping：本 skill 管理资产类别和责任；7+1定义事理与Action的语义结构。 - 与
ontology-runtime-service-and-version-operations：资产治理管理可用资产；运行时服务负责向Agent安全供给本体资源。
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：
-
盘点消费场景
- 动作：列出作业、分析、训练、在线推理、审计和反馈的消费者与目标。
- 完成标准：每类资产有明确消费者和服务级别。
-
完成资产分类
- 动作：区分作业、分析、训练样本、事实、事理、推理结果和日志。
- 完成标准：同一对象可有多种资产形态，但责任与用途不混用。
-
登记来源与版本
- 动作：为不可变标识、源系统、时间、版本、适用范围和血缘建档。
- 完成标准：关键事实能回到权威源，推理结果能回到输入与模型版本。
-
配置质量与权限
- 动作：按资产类型设置完整性、时效、一致性、授权、脱敏和保留策略。
- 完成标准：训练和生产用途的授权分别确认。
-
建立审计闭环
- 动作：记录推理过程、结果、反馈、纠错和退役，定期检查混用与孤岛。
- 完成标准：形成目录、责任矩阵、质量规则和问题清单。
固定输出
- 资产消费场景与服务级别清单
- AI 数据资产目录：资产编号、名称、类别、消费方、权威来源、不可变标识、版本、责任和状态
- 训练样本、运行时事实、事理模型、推理结果与过程日志分类表
- 来源、血缘与版本追溯矩阵
- 质量、权限、脱敏、保留和退役规则表
- 推理结果—输入事实—模型版本—过程日志追溯表
- 资产冲突、质量缺口、责任缺口和整改清单
同一业务对象的不同资产形态分别登记用途、授权、时间和版本；训练可用不自动代表生产推理可用。
使用边界
不要在以下情况使用
- 只需要普通数据仓库分层设计
- 资产消费者和责任人尚未明确
- 复制事实数据会破坏源系统权威性
常见失败模式
- 数据集混用且缺少责任和来源治理：数据上下文和授权边界被抹平，错误、泄露或效果变化出现时无法定位责任和输入来源。
- 用错误本体生成训练数据并放大偏差：同一语义缺陷被重复采样，训练优化把局部错误提升为模型的稳定决策倾向。
使用折扣与复核要求
- 分类需映射现有数据治理体系，新增目录无法自动解决责任冲突和数据质量问题。
- 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
composes-with→seven-plus-one-semantic-mapping；本 skill 管理资产类别和责任；7+1定义事理与Action的语义结构。composes-with→ontology-runtime-service-and-version-operations；资产治理管理可用资产；运行时服务负责向Agent安全供给本体资源。
审计信息
- 历史验证：v0.1.0 路由测试 6/6；v0.4.0 已通过输出契约结构校验，跨平台行为继续按版本抽样
- 首次公开版本：2026-08-21
- 来源说明：方法框架受《本体驱动的 AI 数据管理》启发；仓库不包含原书正文。
What ships with it
3 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.
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.
- 4d ago Changed 811a68e243ff
- 8d ago Changed · +7 lines 3ce25cd2ae3b
- 12d ago First seen · 98 lines · 80 tokens per session scan A 858af6568ce9
ai-training-inference-data-asset-governance 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 80 tokens to every session and 1,345 once invoked, about $0.0004 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.
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…
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…
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.
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…
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.