data-knowledge-architect
/data-knowledge-architect
Builds semantic models from API, CLI, and database contracts with an HTML review and OKF/YAML export. Use when modeling enterprise knowledge, semantic layers, dimensional models, or ontology.
- Author
- ontology-of-everything ↗
- Repository
- concept-skills ↗
- Licence
- Apache-2.0
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 8
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Builds semantic models from API, CLI, and database contracts with an HTML review and OKF/YAML export. Use when modeling enterprise knowledge, semantic layers, dimensional models, or ontology.
Original author description
Builds semantic models from API, CLI, and database contracts with an HTML review and OKF/YAML export. Use when modeling enterprise knowledge, semantic layers, dimensional models, or ontology.
How it works
- Workflow
- Critical Rules
SKILL.md preview
---
name: data-knowledge-architect
description: >-
Builds semantic models from API, CLI, and database contracts with an HTML review and OKF/YAML export. Use when modeling enterprise knowledge, semantic layers, dimensional models, or ontology.
metadata:
language: en
translation_of: data-knowledge-architect-cn
version: "1.1.0"
openclaw:
homepage: https://github.com/ontology-of-everything/concept-skills/tree/main/skills/en/data-knowledge-architect
---
# Data Knowledge Architect — Model the Meaning Behind Your Data
Turn an interface contract—REST/OpenAPI, CLI, or table/DDL—into a governed semantic layer in four
strictly sequential phases. Advance only when the current phase meets its exit condition.
```text
Phase 1 Ingest → Phase 2 Review → Phase 3 Emit → Phase 4 Verify
ingest.md review.md emit-okf.md verify.md
emit-yaml.md
```
The interface is the sole source of truth. Never invent fields, grain, enums, or values. Stop on
missing evidence and ask one question at a time.
## Workflow
1. **Ingest** (`references/ingest.md`) — Normalize interfaces into a complete operation inventory
and classify each operation as fact or dimension lookup with read/write status. Exit when every
operation is classified.
2. **Review** (`references/review.md`) — Decompose the model into atomic decisions. Show objective,
options, evidence, risks, dependencies, and tradeoffs, with fixed YAGNI guidance for facts,
dimensions, measures, and routing. Inject model JSON into `assets/review-template.html`; record
feedback in `amendments.md` and regenerate. Stop after the report. Exit only on `approved:true`
with no open or blocked decisions.
3. **Emit** — Default to a Google OKF v0.1 bundle using `references/emit-okf.md`; use repository
YAML only when explicitly requested, following `references/emit-yaml.md`. Both targets share
field semantics. Generate a thin root index for two or more bundles. Exit when every artifact
exists.
4. **Verify** (`references/verify.md`) — Run structural checks, semantic lint, and OKF hard
constraints when applicable. Report every pass and failure. Return non-mechanical failures to
Phase 2 with one blocking question.
## Critical Rules
1. **Evidence only** — Unsupported fields, grain, enums, or values become `TODO(verify)` and an open
decision.
2. **Grain first** — Attach no dimensions or measures before grain is fixed.
3. **One blocking ask** — Stop only when an answer changes the model; ask one question with options.
Use the HTML review for bulk decisions.
4. **Layer split** — Shape, routing, and grain belong to the semantic layer. Values typed into
commands or read from responses—enums, codes, paths, and commands—belong to the contract layer;
the semantic layer only points to them.
5. **Stable names** — Do not rename confirmed fact or dimension names; OKF concept IDs derive from
paths.
6. **Decision gate** — Every decision starts pending. Phase 2 must stop after producing the report;
Phase 3 requires `approved:true` and no open or blocked item.
Load by phase: `ingest.md`, `review.md`, `emit-okf.md` or `emit-yaml.md`, then `verify.md`. Read
`references/examples.md` for an end-to-end example.
Files in this package (8)
- SKILL.md 3 KB
- assets/review-template.html 50 KB
- references/emit-okf.md 1 KB
- references/emit-yaml.md 1 KB
- references/examples.md 1 KB
- references/ingest.md 2 KB
- references/review.md 2 KB
- references/verify.md 1 KB
Versions
The database has no other skills named data-knowledge-architect.
Database snapshot: 13.11.2026 · package version 1377a590e344 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95okf-authoring
Author Open Knowledge Format (OKF) bundles — knowledge represented as a directory of markdown files with YAML frontmatter. Use when asked to create, write, generate, enrich, or validate an OKF bundle or OKF concept docs; to turn a data source (Glue database, API, database,… - 95okf-skill
Use the Open Knowledge Format (OKF) when storing, retrieving, or documenting knowledge. Produces and reads OKF bundles, portable markdown with YAML frontmatter. Use when the user asks to "document this in OKF", "create an OKF bundle", "read the knowledge base", or when working… - 100ontology
Author and maintain optional local ontology rules, reusable nested types, reference selectors, and semantic relationships. Use for local modeling, not OKF conformance; exact Attested Computation semantics remain built into OKF v0.2. - 100okf-wiki
Builds an Open Knowledge Format (OKF) knowledge base from existing docs, notes, or a repo. Use to scaffold an OKF wiki. - 95okf-visualize-bundle
OKF — Render an Open Knowledge Format (OKF) bundle as a single self-contained, interactive HTML graph (viz.html) of its concepts and links. Use when asked to visualize, graph, preview, or explore an OKF bundle. - 100ontology-modeling
Use when defining what business entities are and how they relate: an ontology, taxonomy or domain model beyond a glossary. Separates meaning from facts, models the business rather than the database, and keeps a YAML source of truth with classes, properties, links, axioms and a trust lifecycle.