agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/de-anthropocentric-research-engine/skills/build-domain-ontology/SKILL.md

build-domain-ontology

Skill505 starsChanged 51 days agoApache-2.0View on GitHub

Construct a tool-independent domain ontology: scope the domain, atomize concepts, type relations, build hierarchy, audit consistency, detect gaps, and refine confidence.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not perform called SOP operations inline.

    line 22
  2. Very specific:

    If the ontology is ready to express directed mechanisms, consider construct-causal-model as the next tactic.

    line 33
  3. Distinctive:

    Stop synthesis when a required object is absent, a precondition is violated, or a counterexample invalidates the proposed conclusion.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

build-domain-ontology

Purpose

Construct a tool-independent domain ontology: scope the domain, atomize concepts, type relations, build hierarchy, audit consistency, detect gaps, and refine confidence.

Input contract

required: [domain_scope, concept_records, relation_evidence]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]

Execution protocol

Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

  1. You MUST load skill scope-domain to freeze the domain question, inclusion boundary, granularity, and reopening trigger before extracting entities.
  2. You MUST load skill extract-concepts to capture source-defined concepts and relation candidates while retaining aliases, qualifiers, and unresolved meanings.
  3. You MUST load skill atomize-concept to split broad concepts into mechanism-, function-, level-, or context-specific facets.
  4. You MUST load skill type-relation to type each in-scope relation while preserving direction, rejected alternatives, and evidence.
  5. You MUST load skill construct-hierarchy to insert supported edges into an acyclic hierarchy and quarantine cycles, orphans, and missing levels.
  6. You MUST load skill audit-structure-consistency to check node and relation schemas with hierarchy, dependency, cardinality, and cycle constraints.
  7. You MUST load skill detect-coverage-gap to prioritize absent, thin, disconnected, or weak regions.
  8. You MUST load skill canonicalize-entity to merge only semantically identical aliases and near-duplicates while retaining rejected merges.
  9. You MUST load skill update-confidence-from-evidence to update confidence after identities and structure are stable. If the ontology is ready to express directed mechanisms, consider construct-causal-model as the next tactic.

Deviation: reorder only when a dependency is already satisfied or unavailable; record the reason and confidence effect.

Output contract

produces: [scoped_ontology, typed_relations, consistency_findings, coverage_gaps]
delta_fields: [findings, decisions]

Thresholds and quality gates

  • Each output is traceable to an input object, operation, and evidence reference.
  • Scope, assumptions, and unresolved alternatives remain explicit.
  • Retain $\alpha$ 0.05 and power 0.8 wherever the predeclared statistical design requires them.

Failure and counterexamples

Stop synthesis when a required object is absent, a precondition is violated, or a counterexample invalidates the proposed conclusion; return the partial delta with the failure recorded.

Provenance map

  • intermediate: knowledge-structuring/ontology-building [campaign]
  • resolved: domain-scoping
  • resolved: concept-extraction
  • resolved: relation-typing
  • resolved: taxonomy-validation
  • resolved: ontology-refinement
  • resolved: hierarchy-construction
  • intermediate: consistency-checking [tactic]

Preserved source criteria ledger

sourcecriteriontreatment
resolved v3 entries abovenode-specific criteriaretained and specialized to the v4 object contract
experiment-execution/statistical-testing$\alpha$ = 0.05fixed value retained where applicable
experiment-execution/sample-size-estimationpower = 0.8fixed value retained where applicable

Context checkpoint / Delta notes

Return the node-specific research-state delta and preserve findings, evidence updates, uncertainties, decisions, open questions, and recommended jumps as applicable.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free