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 ontology-golden-case-testinggit 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/ontology-golden-case-testing)<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/ontology-golden-case-testing"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/ontology-golden-case-testing/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/ontology-golden-case-testing"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/ontology-golden-case-testing.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 | $0.00078 | $0.01566 |
| Opus 5 | $0.00039 | $0.00783 |
| Sonnet 5 | $0.00016 | $0.00313 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
ontology-golden-case-testing 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
本体“黄金用例—测试矩阵—结果回溯”验收
方法骨架
- 用业务专家定义的黄金用例建立本体验收基准,再让AI扩展边界和异常测试。
- 每个用例包含真实问题、输入事实、期望规则路径、期望答案或Action和判定标准。
- 测试矩阵覆盖正常、边界、缺失、冲突、越权、等价变异和压力场景。
- 失败结果要回溯到输入事实、模型规则、查询、Action或用例本身。
- 修复后执行全量回归,防止局部调整破坏既有业务逻辑。
- 测试集作为版本化资产,随业务规则和本体版本持续演进。
触发场景
用户会在什么情境下需要这个 Skill
- 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
- 准备设计边界、异常和越权测试
语言信号
- “帮我设计本体测试用例”
- “怎么做黄金问题集”
- “这次本体变更会不会影响原结论”
- 英文信号:golden cases, ontology regression, test matrix
与相邻 Skill 的区分
- 与
ontology-model-multilayer-quality-gate:质量门审查模型本身;本 skill 用真实问题验证业务结果和推理路径。 - 与
ontology-ai-scenario-fit-and-spike:穿刺验证决定技术路线是否可行;黄金用例形成可持续回归资产。
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:
-
确定验收范围
- 动作:列出核心意图、关键决策点、Action和不可接受错误。
- 完成标准:每项与业务目标和风险等级对应。
-
制作黄金用例
- 动作:为正常、边界、异常、缺失、冲突和越权场景定义输入、期望路径、期望结果。
- 完成标准:候选用例有明确的预期依据与样本状态;正式黄金基线需专家确认和稳定样本。
-
扩展测试矩阵
- 动作:基于黄金用例生成等价变异、组合、压力和回归用例。
- 完成标准:矩阵覆盖对象、规则、权限、查询和行动维度。
-
执行并回溯
- 动作:记录实际输出、模型与映射版本、实例来源、规则路径和差异,把失败归因到数据需求、知识来源、语义、概念模型、逻辑模型、映射、查询、Action或用例。
- 完成标准:每个失败项有唯一责任和修复建议。
-
修复与回归
- 动作:修复后重跑失败项及受影响的核心黄金用例;跨模块语义或公共规则变更时运行完整核心回归;更新版本记录。
- 完成标准:阻断用例100%通过,一般用例达到约定阈值且无新增回归。
固定输出
- 验收范围与版本锁定表:场景、任务、本体、数据映射、规则、查询和 Action 版本
- 黄金用例登记表:用例编号、业务问题、输入实例、前置条件、预期证据、推理路径、结果、专家确认人和优先级
- 正常、边界、异常、缺失、冲突和权限用例矩阵
- 测试执行结果表:预期与实际结果、通过状态、证据、运行时间和执行环境
- 失败归因与修复清单:数据、语义、逻辑、映射、权限、Action 或用例问题及责任人
- 回归测试报告:重跑范围、新增缺陷、阻断通过率、一般用例通过率和剩余风险
- 业务验收结论与发布建议
使用边界
不要在以下情况使用
- 只有形式化语法错误,需要先走模型质量门
- 将缺少稳定业务预期或专家确认的用例直接声明为正式黄金基线;可先设计候选用例并标记待确认预期
- 用少量样本直接宣称全量生产效果
常见失败模式
- 把语法通过当成业务语义正确:形式合法性与业务正确性处于不同验证层,语法工具无法判断领域含义、规则完整性及行动后果。
- 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。
- 行动前无校验且失败后无反馈策略:计划层假设与真实系统状态没有校验,执行结果也未反馈给决策层重新规划。
使用折扣与复核要求
- 黄金用例容易固化已知经验,应持续补充线上新异常和反事实边界。
- 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→ontology-model-multilayer-quality-gate;质量门审查模型本身;本 skill 用真实问题验证业务结果和推理路径。depends-on→data-to-ontology-mapping-and-instantiation;真实实例和映射版本属于用例输入。composes-with→ontology-ai-scenario-fit-and-spike;穿刺验证决定技术路线是否可行;黄金用例形成可持续回归资产。
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 1ae5d9d438fd
- 8d ago Changed · +6 lines 6dd8bb6f80db
- 12d ago First seen · 99 lines · 78 tokens per session scan A 3c3c96111bcd
ontology-golden-case-testing 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 78 tokens to every session and 1,566 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
ontology-shacl-validator
Validate ontology outputs through SHACL-oriented checks, structural issue reporting, and release-readiness notes tied to competency questions, evidence quality, and unresolved modeling risks.
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.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.
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…
code-review
Review diffs and change sets for bugs, regressions, risks, and missing tests.