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。

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is a well-structured, highly actionable overview with clear progressive disclosure to real reference files and solid validation guidance. Its main weakness is redundant repetition of the removed-command-group and --user-id reminders across several sections.

Suggestions

Consolidate the 'removed command groups' (auth/config/agent/skill/toolbox/dataflow) note into a single section — it currently appears in '常见 CLI 坑', '命令组总览', '操作指南', and '注意事项'.

State the --user-id requirement and bd_public default once in '调用约定' and reference it, instead of repeating the full rule in multiple sections.

Pull the key validation checkpoints (e.g. 'validate before push', 'probe jq structure first') from the build-KN reference into a short inline checklist so the main workflow is self-contained.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but the 'removed command groups' reminder (auth/config/agent/skill/toolbox/dataflow) is repeated across '常见 CLI 坑', '命令组总览', '操作指南', and '注意事项', and the --user-id / bd_public rules recur several times.

3 / 5

Actionability

Provides copy-paste-ready commands and jq projections (e.g. `ontology --user-id <accountId> bkn object-type list <kn-id> | jq '.entries[] | {id, name, comment, primary_keys, display_key}'`) plus concrete condition-structure tables covering the common cases.

5 / 5

Workflow Clarity

Clear sequencing with real checkpoints — the 'probe with jq keys/type before templating' feedback loop and 'confirm before Action' validation are explicit — but the build-KN workflow is an inline arrow chain whose detailed validation steps live in the reference file rather than the body.

4 / 5

Progressive Disclosure

Body acts as a well-signaled overview pointing one level deep to real reference files (bkn.md, ds.md, dataview.md, vega.md, call.md, build-kn-from-db.md) via a dedicated '详细参考' column and inline links, with detail appropriately split out.

5 / 5

Total

17

/

20

Passed

Description

92%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.

The description is strong: it states concrete capabilities across three domains and provides an explicit, synonym-rich trigger clause for when to activate. Minor room to add a few more colloquial trigger phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions per domain — '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', '查询 Catalog/资源/连接器类型、健康巡检' — giving comprehensive coverage rather than vague verbs.

5 / 5

Completeness

Clearly answers both 'what' (operate BKN / 数据源与数据视图 / Vega with named actions) and 'when' via the explicit trigger clause '当用户提到…等意图时自动使用'.

5 / 5

Trigger Term Quality

Good keyword coverage with explicit synonyms ('知识网络'/'知识图谱', '健康检查'/'巡检') and natural terms like '数据视图' and 'Catalog', though a few common phrasings (e.g. '建图', '导数据') are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (the ontology CLI for BKN/dataview/Vega) with distinct, domain-specific triggers, minimizing overlap with generic skills.

5 / 5

Total

19

/

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.