CtrlK
BlogDocsLog inGet started
Tessl Logo

bkn-modeling-advisor

指导业务知识网络(BKN)建模,输出符合 BKN 2.0.0 的对象类型、关系类型、操作类型、风险类型与概念分组定义。适用于用户提出本体设计、知识网络建模、实体关系梳理、Action 设计、Schema 评审、从文档提取初稿或扩展现有 BKN 的场景。

74

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

88%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 tight, well-sequenced advisory workflow with concrete field/enums guidance, explicit validation gates, and a quality-gate feedback loop. Its main weakness is that all detail is inlined in one file rather than split into progressive reference files, and a full worked example would lift actionability.

Suggestions

Add one complete worked example walking a sample business scenario through Phases 1–7 with the resulting BKN JSON, to make the guidance fully copy-paste ready.

Move the detailed per-phase field requirements and the bkn-creator 对接契约 into one-level-deep reference files (e.g., references/phases.md, references/bkn-creator-contract.md) and link to them from SKILL.md to improve progressive disclosure.

Split the per-round 质量门禁 checklist into a reusable self-check artifact or reference so the overview stays lighter.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven with no padding; it avoids explaining concepts Claude already knows and every section (phases, modeling heuristics, quality gates) earns its place through actionable decision criteria.

5 / 5

Actionability

It gives concrete field lists (network.id, data_properties[], keys.primary_keys[]), enums (add/modify/delete/query; risk low/medium/high), a naming rule ([a-z0-9_-]), and a copy-paste JSON skeleton, but lacks a complete end-to-end worked example tying the phases together.

4 / 5

Workflow Clarity

A clear 7-phase sequence with explicit mid-stream entry points for import/from_doc modes is backed by validation checkpoints (Phase 7 完整性审查), a per-round 质量门禁 checklist with a fix-then-output feedback loop, and explicit 结束标准 completion criteria.

5 / 5

Progressive Disclosure

Sections are well-organized and clearly signaled, but everything lives in a single ~210-line SKILL.md with no bundle files; the detailed phase specs and the bkn-creator contract could be split into one-level-deep reference files to ease navigation.

4 / 5

Total

18

/

20

Passed

Description

95%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 well-crafted: it states concrete deliverables tied to a specific versioned standard and pairs them with a rich set of natural-language trigger scenarios. The only minor gap is that the action verbs are somewhat concentrated (指导/输出) rather than enumerating a wider range of distinct operations.

DimensionReasoningScore

Specificity

Names the BKN modeling domain and lists several concrete deliverables ("对象类型、关系类型、操作类型、风险类型与概念分组定义") conforming to BKN 2.0.0, but the actions concentrate on guiding/outputting rather than enumerating a fuller set of distinct operations, leaving a minor coverage gap.

4 / 5

Completeness

It explicitly answers both "what" (指导 BKN 建模,输出符合 BKN 2.0.0 的各类定义) and "when" (适用于用户提出本体设计、知识网络建模等场景) with concrete trigger phrases.

5 / 5

Trigger Term Quality

The "适用于用户提出...的场景" clause covers a comprehensive set of natural trigger phrases users would say: 本体设计, 知识网络建模, 实体关系梳理, Action 设计, Schema 评审, 从文档提取初稿, and 扩展现有 BKN.

5 / 5

Distinctiveness Conflict Risk

It targets a clear niche (BKN 2.0.0 modeling) with distinct, specialized triggers that are unlikely to fire for unrelated skills, minimizing conflict risk.

5 / 5

Total

19

/

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.

Validation16 / 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.