ontology

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/ontology/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and well-structured with real executable CLI examples, but it is held back by duplicated inline content, missing explicit validation feedback loops, and illustrative Python integration code that does not match the actual script API.

Suggestions

Remove the inline 'Core Types' and 'Constraints' YAML blocks from SKILL.md (they duplicate references/schema.md) and replace them with a one-line pointer, keeping only the minimal types needed to understand the CLI.

Turn the Workflows section into an explicit validate→fix→retry loop: after create/relate, run `python3 scripts/ontology.py validate`, show how to read the errors, fix them, and re-run before proceeding.

Make the 'Integration Patterns' Python examples executable or explicitly label them illustrative — `ontology.create()`/`ontology.query()` and the `Commitment` type do not exist in scripts/ontology.py.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference-style prose, but the inline 'Core Types' and 'Constraints' YAML blocks duplicate references/schema.md, and 'Quick Start' repeats commands already shown in 'Workflows'.	2 / 3
Actionability	Primary guidance is fully executable copy-paste CLI commands (create/query/relate/validate) backed by the real scripts/ontology.py, with concrete examples and flags.	3 / 3
Workflow Clarity	Operations are listed individually rather than sequenced into a validate→fix→retry loop, and the Planning section asserts validation/rollback without showing the recovery steps — a validation feedback gap that caps this dimension.	2 / 3
Progressive Disclosure	References to references/schema.md and references/queries.md are well-signaled and one level deep (both files exist), but large type/constraint blocks duplicated inline are content that should live in the reference files.	2 / 3
	Total	9 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: specific, concise, third-person, and explicit about both capabilities and trigger conditions. Its main weakness is overlap with general memory skills via generic trigger phrasing.

Suggestions

Sharpen the niche by leading with the typed-graph/entity-model framing and reserving 'remember'/'what do I know about' for graph-specific phrasing (e.g., 'remember as a typed entity', 'what entities link to X') to reduce overlap with a generic memory skill.

Add a negative boundary such as 'Not for free-form notes or untyped key-value memory — use when relationships and type constraints matter' to make it unlikely to trigger for the wrong skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, entity CRUD" — rather than vague language.	3 / 3
Completeness	Clearly answers both what ("Typed knowledge graph for structured agent memory and composable skills") and when with explicit triggers ("Use when…", "Trigger on…").	3 / 3
Trigger Term Quality	Includes natural phrases users would say — "remember", "what do I know about", "link X to Y", "show dependencies" — giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The graph/entity-typed niche is fairly clear, but "structured agent memory" combined with triggers like "remember" and "what do I know about" overlaps with a generic memory skill, so conflict risk remains.	2 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/ontology/SKILL.md
Commit: f618458

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.