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 ontology-of-everything/SemanticSkills --skill semantic-km-creatorgit clone --depth 1 https://github.com/ontology-of-everything/SemanticSkillsWrote 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/ontology-of-everything/semanticskills/semantic-km-creator)<a href="https://agentmods.dev/skills/ontology-of-everything/semanticskills/semantic-km-creator"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/semantic-km-creator/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/ontology-of-everything/semanticskills/semantic-km-creator"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/semantic-km-creator.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 | $0.00090 | $0.01076 |
| Opus 5 | $0.00045 | $0.00538 |
| Sonnet 5 | $0.00018 | $0.00215 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
semantic-km-creator 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 2d 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
Semantic KM Creator（企业知识 · 接口 → 语义层）
把接口契约（REST/OpenAPI、CLI、表/DDL）一次通过地建成受治理语义层。四个阶段严格串行，每阶段一个参考文件、一组退出条件——满足才前进，不满足不硬闯：
Phase 1 Ingest → Phase 2 Review → Phase 3 Emit → Phase 4 Verify
ingest.md review.md emit-okf.md verify.md
emit-yaml.md
唯一真源是接口。不臆造字段/粒度/枚举/取值；缺证据停下，一次一问。
Workflow
Phase 1 · Ingest（references/ingest.md）
接口归一成「操作清单」，每个 op 判定角色（fact / dimension-lookup）。 退出条件：清单完整，每个 op 有角色与读写标记。
Phase 2 · Review（references/review.md）
将对象拆为原子决策；显式展示目标、候选、证据、风险、依赖与权衡，并在
事实、维度、度量、路由分区提供固定 YAGNI 判断指导。生成 model JSON 注入
assets/review-template.html，由用户确认、选择、修正、补证或拒绝；反馈写入
amendments.md 后重出报告。
退出条件：收到 approved:true，且无未决或阻塞项。出报告后必须停下；
未批准禁止进入 Phase 3。
Phase 3 · Emit（references/emit-okf.md 默认 / references/emit-yaml.md 可选）
默认生成 Google OKF v0.1 bundle；用户明确要求时生成 repo-YAML（Kimball 星型）。字段语义两个目标共享（定义在 emit-yaml.md §2–§4）。≥2 个 bundle 时生成薄根索引。
退出条件：产物文件完整落盘。
Phase 4 · Verify（references/verify.md）
跑结构检查 + 语义 lint +（如导出 OKF）OKF 硬约束，逐条回报 pass/fail。 退出条件：全部 pass；不可机械修复的 fail → 回 Phase 2 One blocking ask，不静默通过。
Critical Rules
- Evidence-only — 字段/粒度/枚举/取值仅来自接口；缺证据写
TODO(verify)并列入待确认，不编造。 - Grain first — 未锁 grain 不挂维度、不写度量。
- One blocking ask — 仅在改变建模结果处停（一次一问，带候选），不连环问；批量确认走 HTML 评审。
- Layer split — 形态/路由/粒度归语义层；可键入或读取的取值（枚举、code、字段路径、命令）归契约层，语义层只指向。
- Stable names — 事实/维度名确认后不重命名（OKF 概念 ID = 文件路径，改名即断链）。
- Decision gate — 所有决定初始 pending，不得默认通过。Phase 2 出报告后
停下；仅用户回传
approved:true且无未决/阻塞项时进入 Phase 3。
Reference Index（按阶段加载）
| 阶段 | 文件 |
|---|---|
| Phase 1 物料归一 + 角色判定 | references/ingest.md |
| Phase 2 决策建模 + HTML 工作台 + amendments | references/review.md |
| Phase 3 默认目标 OKF 布局/映射 | references/emit-okf.md |
| Phase 3 可选目标 YAML + 共享字段语义 | references/emit-yaml.md |
| Phase 4 全部校验 + 升级回路 | references/verify.md |
| 端到端样例 | references/examples.md |
What ships with it
7 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.
- 2d ago First seen · 69 lines · 90 tokens per session scan A 5bf079505390
semantic-km-creator is a skill published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,076 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 2026-09-10.
Other skills, from other repositories
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
cwicr-data-loader
Load and parse DDC CWICR construction cost database from multiple formats: Parquet, Excel, CSV, Qdrant snapshots. Foundation for all CWICR operations.
laravel-vector-search
Use when implementing semantic/vector search in Laravel 13 with PostgreSQL + pgvector.
using-datavault4dbt
Builds Data Vault 2 models in dbt with the datavault4dbt package — staging, hubs, links, satellites, and business-vault entities — using the YAML-metadata macro pattern with correct hashkeys, hashdiffs, naming, and materializations. Use when creating or editing datavault4dbt models, setting up a raw vault, choosing…