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 seven-plus-one-semantic-mappinggit 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/seven-plus-one-semantic-mapping)<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/seven-plus-one-semantic-mapping"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/seven-plus-one-semantic-mapping/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/seven-plus-one-semantic-mapping"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/seven-plus-one-semantic-mapping.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 | $0.00097 | $0.01606 |
| Opus 5.5 | $0.00039 | $0.00642 |
| Sonnet 5.5 | $0.00019 | $0.00321 |
| Haiku 4.5 | $0.00010 | $0.00161 |
Grade A, and why
seven-plus-one-semantic-mapping 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用“7+1”规范映射业务语义
方法骨架
- 把业务知识按确认状态映射为七类语义能力和一类目标评估,候选与已确认条目保持隔离。
- 七类覆盖资源与关系、类层级与约束、统一术语、业务规则、流程服务、权限策略、查询与数据操作。
- 附加的一类把Agent任务目标、效果指标、判定依据和质量标准写清。
- 映射时同时保留自然语言、形式表达、来源、版本和责任人。
- 任何缺失项都要显式标记,尤其是权限、Action前置条件和评估规则。
- 结果是一张可审查、可测试且保留确认状态的语义映射表;进入运行时另满足适用准入条件。
需要完整维度、工程产物和技术选择时读取 7+1 语义维度。
触发场景
用户会在什么情境下需要这个 Skill
- 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
- 准备从自然语言规则生成RDF/OWL等模型
语言信号
- “按7+1映射一下”
- “这个场景缺哪些语义”
- “把业务规则转成机器可理解结构”
- 英文信号:7+1 semantic mapping, ontology schema, action semantics
与相邻 Skill 的区分
- 与
twenty-nine-sentence-knowledge-extraction:29句话负责提取自然语言知识;本 skill 负责分类映射和完整性检查。 - 与
fact-reason-action-business-loop:事实事理行动提供三层业务骨架;7+1细化到标准、权限、查询和目标评估。
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:
-
确认输入
- 动作:读取或补记来源、适用范围和确认状态;无法核验的条目保留原描述并标记假设、来源或责任缺口。
- 完成标准:未确认内容单列,不进入生产映射。
-
映射七类语义
- 动作:分别填写资源关系、层级约束、术语、规则、流程服务、权限、查询与数据操作。
- 完成标准:每条业务知识有唯一主类别,跨类别引用清晰。
-
补目标与评估
- 动作:定义场景业务目标、Agent任务目标、动作结果、完成条件、评价口径和责任主体。
- 完成标准:目标能够通过数据或有权角色验收。
-
检查闭环
- 动作:沿事实输入、规则推理、权限判断、Action执行、结果反馈逐段检查缺项。
- 完成标准:缺项、冲突和高风险项形成问题清单。
- 判停条件:若权限或行动前置条件缺失,停止进入生产建模。
-
输出映射表
- 动作:保留自然语言、语义类别、形式化建议、来源、版本、确认人和测试问题。
- 完成标准:映射表可被建模工程师与业务专家共同复核。
固定输出
- 输入知识准入表:知识编号、来源、证据、适用范围、确认状态、责任人和版本
- 7+1 语义映射表:条目编号、业务表达、语义主类别、跨类引用、形式化建议、来源、版本、责任与确认状态
- 资源关系、层级约束、统一术语、业务规则、流程服务、权限策略、查询数据操作和目标评价完整性矩阵
- 事实输入—规则推理—权限判断—Action 执行—结果反馈闭环检查表
- Agent 任务—语义条目—测试问题追溯表
- 术语、规则、权限、Action、目标与评价缺口清单
- 冲突、待确认项、生产阻断项与下一步清单
使用边界
不要在以下情况使用
- 将自由讨论、来源或责任未定的候选映射直接作为正式业务规则
- 只做概念科普,无需机器推理或行动
- 简单字段映射能够满足需求
常见失败模式
- 约束和权限落入过紧或过松两端:场景风险与控制策略未建立映射,Agent无法判断何时自主、何时申请授权、何时停止。
- 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。
- 目标模糊且行动原语契约残缺:Agent缺少可计算的成功条件及行动前后状态模型,只能猜测参数、条件和执行结果。
- 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
- W3C语法与业务正确性属于不同质量维度,规范映射完成后仍需专家和用例验证。
- 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-on→twenty-nine-sentence-knowledge-extraction;复用已有来源及状态清晰的知识条目,必要时补提取,不要求重做整套访谈。composes-with→scenario-related-semantic-modeling与fact-reason-action-business-loop;7+1用于完整性检查和形式化建议。
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.
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.
- 14d ago Changed · +9 tokens per session 1006238600e4
- 1mo ago Changed c5ca4f1d6fac
- 1mo ago Changed · +8 lines 16c791530d26
- 1mo ago First seen · 100 lines · 88 tokens per session scan A 6b799ef12876
seven-plus-one-semantic-mapping is a skill published in the GitHub repository SuperChason/ontology-driven-ai-data-management-skills (19 stars, last pushed 15d ago), licensed MIT. It adds 97 tokens to every session and 1,606 once invoked, about $0.0004 per session on Opus 5.5. 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
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.
open-ontologies
AI-native ontology engineering using 110 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…
report-generation
A workflow for generating data-analysis reports as interactive HTML with charts. It is intended for trend, statistics, monthly, weekly, and other reports, using database queries and ECharts, a web charting library.
competitor-deep-dive
A competitor-research workflow that combines competitor profiles, recent web research, and internal product facts into an HTML comparison dashboard. It can include charts for comparing products and prices.
market-daily-brief
A market-intelligence workflow that gathers recent industry, competitor, policy, and news information into an HTML briefing dashboard. HTML is the standard markup used to display pages in a web browser.
ontology-engineering
Build, validate, and govern RDF/OWL ontologies using the Open Ontologies MCP server. Use when the user asks to create, modify, query, or manage ontologies, knowledge graphs, or RDF data.