CtrlK
BlogDocsLog inGet started
Tessl Logo

ontology-core

操作 知识网络(BKN)— 构建知识网络、查询 Schema/实例、语义搜索、执行 Action。 操作数据源与数据视图 — 数据源连接与查询、原子/自定义视图浏览与 SQL 查询。 操作 Vega 可观测平台 — 查询 Catalog/资源/连接器类型、健康巡检。 当用户提到"知识网络"、"知识图谱"、"查询对象类"、"执行 Action"、 "数据源"、"数据视图"、"原子视图"、"Catalog"、"Vega"、 "健康检查"、"巡检"等意图时自动使用。

72

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, actionable skill body that leans on a clean reference split and concrete commands. Main weaknesses are mild internal repetition and a drift between the body's 'unavailable command groups' claim and content inside build-kn-from-db.md.

Suggestions

Consolidate the jq projection rules and the unavailable-command-group (auth/config/agent/skill/toolbox/dataflow/context-loader) list so each appears once; cross-reference instead of repeating.

Reconcile references/build-kn-from-db.md with the body: it documents `ontology agent` and `context-loader` flows that the body says are unavailable — either remove those sections or note they require a deployment the body excludes.

Surface an inline validation/confirmation checkpoint for destructive/batch operations (e.g. `bkn delete`, `action-type execute`, `ds delete`) in the body rather than relying solely on references.

DimensionReasoningScore

Conciseness

Largely lean and reference-style with dense tables, but the jq projection rules and the unavailable-command-group list each recur 2-3 times across sections, which could be consolidated.

4 / 5

Actionability

Provides concrete executable commands throughout — real `ontology` invocations, jq projections, and copy-paste-ready examples covering common cases like list/get/query/health.

5 / 5

Workflow Clarity

The body routes to sequenced workflows with validation (e.g. build-kn-from-db has numbered steps plus a '验证' checkpoint) and offers a '先裸跑 jq keys/type' pre-check, but validation for destructive/batch ops is mostly delegated to references rather than surfaced inline.

4 / 5

Progressive Disclosure

Clear overview with one-level-deep references signaled via a command-group table and inline links, well split across references/*.md; however references/build-kn-from-db.md documents `ontology agent`/`context-loader` that the body declares unavailable, a minor navigation inconsistency.

4 / 5

Total

17

/

20

Passed

Description

100%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 high-quality description: third-person voice, concrete actions across all three covered domains, and an explicit auto-use trigger clause with rich natural synonyms. No fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three domains — '构建知识网络、查询 Schema/实例、语义搜索、执行 Action', '数据源连接与查询…SQL 查询', '查询 Catalog/资源/连接器类型、健康巡检' — giving comprehensive coverage rather than vague verbs.

5 / 5

Completeness

Explicitly answers both 'what' (three domains of concrete actions) and 'when' via the clause '当用户提到…等意图时自动使用', with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonyms — '知识网络'/'知识图谱', '数据视图'/'原子视图', 'Catalog', 'Vega', '健康检查'/'巡检' — phrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (the ontology CLI over BKN/datasource/dataview/Vega) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

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.