CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A well-structured, highly actionable skill body with real executable commands, a working bundle script, and clearly signaled references. The main weaknesses are inline duplication of the schema reference content, a non-executable pseudo-API in the integration examples, and a meta-commentary section that adds tokens without guidance value.

Suggestions

Replace the inline Core Types and Constraints listings with a brief summary plus a pointer to references/schema.md, since that file already contains the full definitions — this would remove ~60 duplicated lines.

Rewrite the Integration Patterns Python snippets against the actual interface (e.g., subprocess calls to scripts/ontology.py) or explicitly label them as illustrative pseudocode.

Delete or drastically shorten the "Instruction Scope" section; its scope/limitations content is reviewer-facing meta-commentary rather than runtime guidance, and the validation caveats could fold into the Constraints section.

DimensionReasoningScore

Conciseness

The body is dense with tables and executable commands rather than prose, but the full Core Types and Constraints listings duplicate references/schema.md, and the closing "Instruction Scope" section ("this is within scope", "documentation-only unless implemented in code") is meta-commentary that could be trimmed. Not 5 because of this removable redundancy; not 3 since the padding is minor relative to the whole.

4 / 5

Actionability

Workflows and Quick Start give copy-paste-ready CLI commands ("python3 scripts/ontology.py create --type Person --props '{...}'") and the bundle script exists, but the Integration Patterns snippets use a pseudo-API ("ontology.create(\"Commitment\", {...})") that is not executable as written — minor gaps, so not 5.

4 / 5

Workflow Clarity

Quick Start sequences init → schema → create, and the planning section has an explicit checkpoint ("Each step is validated before execution. Rollback on constraint violation") plus a dedicated validate command. Not 5 because validation is described but not wired into the Quick Start sequence as an explicit step, and there is no fix-and-retry loop shown.

4 / 5

Progressive Disclosure

References section clearly signals the two real one-level-deep files ("references/schema.md — Full type definitions and constraint patterns", "references/queries.md — Query language and traversal examples") and the script bundle exists as listed. Not 5 because the ~30-line inline Core Types and Constraints sections duplicate content that already lives in references/schema.md, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

83%Weight 40%Scale 1-5

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 that clearly states what the skill does and when to use it, with genuinely natural trigger phrases and third-person voice. Slight abstractness in the graph-transformation framing and minor overlap risk with generic memory skills keep it just short of top marks.

DimensionReasoningScore

Specificity

Lists several concrete actions — "creating/querying entities (Person, Project, Task, Event, Document)", "linking related objects", "enforcing constraints" — but "planning multi-step actions as graph transformations" and "composable skills" lean abstract, leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both: the what is a "Typed knowledge graph for structured agent memory" with named operations, and the when is a full "Use when..." clause plus a "Trigger on..." list of concrete phrases. Not below 4 because the when-clause is fully explicit with concrete triggers.

5 / 5

Trigger Term Quality

Good natural-phrase coverage ("remember", "what do I know about", "link X to Y", "show dependencies") alongside technical triggers ("entity CRUD", "cross-skill data access"), though common variations like "tasks", "todos", or "who works on" are missing.

4 / 5

Distinctiveness Conflict Risk

The typed-graph/agent-memory niche is mostly distinct with specific entity-type triggers, but "remember" and "skills need to share state" could overlap with a generic memory or state-management skill — minor conflict risk, so not 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.