本文へ移動
cccskills
無料GitHub で公開

fipa-00086-ontology-service

Plan and diagnose FIPA-style ontology-service interactions while keeping declared ontology relations, provider capability, and application authorization separate. NOT for treating an ontology mapping as provider authority or guaranteed interoperability.

インストール方法を見る

含まれるファイル(21)

  • SKILL.md6.9 KB
  • _book_identity.json3.9 KB
  • _raw_response.md100.3 KB
  • diagrams/01_flowchart_ontology_relationship_decision.md2.8 KB
  • diagrams/01-mapping-procedure.md1.2 KB
  • diagrams/02_sequenceDiagram_fipa_ontology_service_coordina.md2.1 KB
  • diagrams/02-layer-boundary.md1.0 KB
  • diagrams/03_erDiagram_three-layer_ontological_model_.md1.3 KB
  • diagrams/INDEX.md1.1 KB
  • historical-provenance.md1.1 KB
  • references/bottom-up-integration-fallacy.md1.7 KB
  • references/conceptualization-vs-ontology-for-coordination.md1.5 KB
  • references/explicit-vs-implicit-ontologies-tradeoffs.md1.4 KB
  • references/failure-modes-semantic-interoperability.md1.1 KB
  • references/INDEX.md702 B
  • references/okbc-knowledge-model-as-interlingua.md6.6 KB
  • references/ontology-agent-as-coordination-infrastructure.md1.6 KB
  • references/ontology-authoring-guidelines.md1.3 KB
  • references/ontology-relationship-as-action-constraint.md2.7 KB
  • references/source-access.md2.1 KB
  • references/translation-hierarchy-as-coordination-strategy.md1.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

FIPA ontology-service design

Use this skill when agents must select a shared ontology, query a declared ontology relation, or request an expression translation. It does not establish provider availability, application suitability, or shared conceptualization.

Source and version boundary

The accessible predecessor body is FIPA XC00086C, Experimental, 2000-06-15: https://www.fipa.org/specs/fipa00086/XC00086C.html. The catalog identifies XC00086D, Experimental, 2001-08-15: https://www.fipa.org/specs/fipa00086/index.html; D's body remains unread. A contemporaneous implementer paper reports no functional change between the then-latest experimental service specification and FIPA 98 Part 12; that supports using C to recover methods, not treating C and D as textually or normatively identical. See source access.

Working method

  1. Name source and target ontology identifiers exactly as they will appear on the message. Record source -> target; reverse direction is a separate claim.
  2. Separate four questions: does syntax parse; what vocabulary/axioms are declared; what intended model is relied on; and is an application effect authorized. A yes at one layer is not a yes at another.
  3. Discover an OA or translation service through the Directory Facilitator only when needed. Registration is advertisement, not validation.
  4. Ask for the declared relation or translation capability. Preserve who asserted it, names, version/revision identifiers if available, and the response or refusal.
  5. Before using translation, test a task-essential expression against a local fixture. Record unmapped terms, changed constraints, and result. This receipt is local practice, not a FIPA requirement.
  6. Apply explicit local policy to loss or possible inconsistency. FIPA does not supply a command-permission matrix, mandatory confirmation loop, or safety classification.
flowchart TD
    S([Need shared meaning]) --> I[Name source and target ontology]
    I --> R[Discover declared relation or translation capability]
    R --> Q{Capability returned?}
    Q -->|no or refusal| N[Keep mismatch; negotiate another shared ontology]
    Q -->|yes| D{Direction and task fixture acceptable?}
    D -->|no| N
    D -->|yes| T[Request translation]
    T --> Z{Translation result returned?}
    Z -->|no: nil/refuse/failure| N
    Z -->|yes| V{Task fixture validates?}
    V -->|no| N
    V -->|yes| G{Local authorization granted?}
    G -->|no| X[No effect; authority handling]
    G -->|yes| A[Authorized application effect]

Relationship facts are not a ladder

RelationC-body semanticsEngineering check
ExtensionDirectional preservation of base vocabulary and propertiesUse named shared vocabulary; do not infer reverse
IdenticalVocabulary, axiomatization, representation language physically identicalDoes not prove shared conceptualization
EquivalentSame vocabulary and logical axiomatization; representation may differServer deductions can differ by implementation
StrongTotal source vocabulary translation; source axioms hold; no loss/inconsistency in that directionTest exact direction
WeakTranslation can lose information but should not add inconsistencyCheck whether loss defeats task
ApproxWeak translation with possible inconsistencyTreat as candidate under local validation

Only these implications are stated: Strong => Weak => Approx; Equivalent implies Strong both directions; Identical implies Equivalent. Extension is not another rung. Relation determination can be difficult or undecidable, so record provenance and allow manual review.

Source-shaped interaction patterns

These are illustrative summaries of XC00086C, not wire captures. For assert, retract, and domain query-if/query-ref, ACL :ontology names the service ontology and affected domain ontology. For translate, ACL :ontology names the service ontology; the source and target ontologies are translation-description :from and :to.

(query-ref
  :ontology FIPA-Ontol-Service-Ontology
  :content (iota ?level (ontol-relationship source-ontology target-ontology ?level)))

(request
  :ontology FIPA-Ontol-Service-Ontology
  :content (action ontology-agent
    (translate source-expression
      (translation-description :from source-ontology :to target-ontology))))

In C §5.2.6, nil illustrates an OA unable to provide any translation between the two ontologies. It is not the generic result for unknown relationships or individual unmapped expressions. not-understood, failure, and refuse remain distinct conversational outcomes; READ-ONLY and INCONSISTENT are modification-refusal reasons. Preserve the actual response rather than relabeling every absence as semantic failure.

Shared-ontology routes (C §5.3)

Choose a route whose prerequisite is actually met: (1) request B's service under O1; not-understood shows B does not understand O1; (2) ask the DF for a provider supporting O1; (3) ask an OA for an ontol-relationship to a differently named Identical/Equivalent ontology or a usable sub-ontology; (4) ask the DF for a translation service and use that service as proxy. These are alternatives, not a mandatory protocol. See translation routing.

Hand checks

Positive: for task-essential terms covered by a declared Strongly-Translatable(source,target) relation, confirm the result satisfies a target-vocabulary fixture. This validates the fixture, not all expressions.

Negative: reverse the direction or add an extension-only term. If no relation/capability covers it, retain the unknown relation or unmapped term as a local unresolved outcome; do not silently make the relation bidirectional or drop the term. Record nil only when actually returned for the source-described no-translation-between-pair case.

Read next

Bundle navigation

diagrams index.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/port-daddy22026年10月12日 更新

curiositech のスキルをすべて見る

このスキルの問題を報告する