ontology-bootstrap

Solid

Build a trustworthy first ontology from an empty or near-empty ontology-atlas vault using only Atlas MCP evidence. Use when the user asks to analyze a codebase, bootstrap/fill its ontology, extract product meaning from a repository, or when a requested ontology task finds only starter nodes. Separate observed implementation facts from proposed meanings, define and cite every domain/capability, answer competency questions, obtain independent source-hidden qualification and user approval, then write only the exact released plan with batch tools. Route mature vaults with 20+ curated nodes to ontology-sync instead; this is a workflow threshold, never a vault or project node limit.

AI & Automation 103 stars 15 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
67
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Bootstrap a trustworthy ontology Create a shared meaning model, not a labeled file tree. Treat repository structure as implementation evidence. Never promote a folder, package, README heading, or model-generated phrase into a business concept without a definition and source-backed justification. Use only ontology-atlas MCP tools for the core workflow. Do not depend on CodeGraph, another skill, shell search, or an AST index. Those may exist, but a plain agent connected only to Atlas must still succeed at the meaning model. The optional, bounded task-navigation enrichment below is the sole exception: after meaning selects a stable element, a source-aware builder may use an available local source reader to verify exact coordinates that Atlas then checks again. Navigation may remain unknown without blocking the core model. ## Meaning contract The normative five-kind discriminator, relation support matrix, direct `is_a` test, and inference/standards boundary live only in the [Atlas meta-model specification](../../../docs/ONTOLOGY-ATLAS-SPEC.md#2-the-five-authorable-node-kinds-and-reserved-reader-kind). This skill owns the bootstrap sequence and evidence/approval states; it does not redefine the model. If the linked file is unavailable, use the compact meta-model boundary supplied by the connected Atlas MCP instructions. Keep these epistemic states separate: - `observed`: directly present in a returned source excerpt, path, package, or import. - `proposed`: an interpretat...

Details

Author
wlsdks
Repository
wlsdks/ontology-atlas
Created
4 months ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Solid

ontology-sync

After a code change, sync the project's ontology vault — read what's already there, identify new capabilities / elements / domains introduced by the change, and write them back via the MCP server (or fall back to the CLI). Use this at the end of any task that introduces a new feature, refactors a module, or renames a unit. Skip when the change is purely a typo, style nudge, or test fixture tweak.

103 Updated today
wlsdks
AI & Automation Solid

ontology-field-trial

Measure Atlas ontology quality on an unfamiliar repository with a source-hidden handoff and four baseline measurements. Use for changes to meaning-construction rules or MCP read/write behavior that can change vault contents, or an explicit ontology-quality field trial. Skip UI work and wording-only clarifications that preserve the evidence, approval, and write contracts.

103 Updated today
wlsdks
Web & Frontend Listed

ontology-building

Builds, extends, reviews, or audits an ontology, domain model, conceptual/data model, taxonomy, or knowledge-graph/property-graph schema — deciding what entities, classes, relations, or aggregates should exist, how to shape a class or role hierarchy, how to scope with competency questions, and how to validate coherence (is-a correctness, anti-patterns, agent-actionability). Use when designing a data model, building a taxonomy, modeling a domain, defining a class hierarchy or knowledge-graph schema, or reviewing an existing ontology/domain model for coherence or AI-agent fitness. Skip for trained ML/statistical models, or routine schema tweaks with no structural decision.

2 Updated 1 weeks ago
mgillett43