smart-search-tables

找表/找数端到端编排：在元数据型知识网络下用 ontology bkn object-type query 检索表/视图实例，再在职责型知识网络下检索相关部门职责与治理边界，最后汇总为中文结论（候选表 + 职责要点 + 下一步）。当用户问「表在哪、哪个视图、数据资产归属、谁负责这类数据」时使用。所有 ontology CLI 执行均委托 ontology-core 完成；本 skill 不直接执行 CLI。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A strongly structured, actionable orchestration skill with a clear sequenced workflow and well-signaled one-level-deep references. The main weakness is repetitive delegation boilerplate across the body and reference files that inflates tokens without adding information.

Suggestions

State the 「委托 ontology-core 执行、本 skill 不直接执行 CLI」 delegation rule once in the 调用方式 section and drop the repeated 'Never/委托' restatements from 子技能依赖, 委托命令形态, 配置, and each reference file header.

Collapse the duplicate call-chain diagram and the step→subcommand table (步骤 1/2 already appear in both 主流程 and 委托给 ontology-core 的命令形态) into a single source of truth.

Move the condition-json field-name/isomorphism detail fully into metadata-search.md and keep only the pointer in SKILL.md, since the reference already owns that spec.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful tables and checklists, but the 「Never 由本 skill 直接执行 CLI / 委托 ontology-core」 delegation note is repeated in nearly every section and again in each reference, which is padding Claude already retains after the first statement.	2 / 3
Actionability	Provides concrete, copy-pasteable command forms (ontology --user-id <accountId> bkn object-type query <kn_id> <ot-id> '<condition-json>' [--limit n]), a step→subcommand table, and field-level guidance (technical_name/business_name, condition-json shape).	3 / 3
Workflow Clarity	Clear fixed sequence (步骤 1→2→3) with a checkbox checklist (复制进度), explicit ordering constraint (step 2 derives from step 1), and error-recovery branches (empty results → relax search/switch KN; no duty_kn_id → skip step 2 and note it).	3 / 3
Progressive Disclosure	SKILL.md is an overview with a 必读 references table pointing one level deep to real files (metadata-search.md, duty-search.md, tool-examples.md), each clearly scoped to a step; no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 well-crafted, third-person description that states concrete capabilities, gives natural Chinese trigger phrasing, and covers both what and when. Slightly jargon-heavy (ontology bkn object-type query) but the user-facing trigger clause keeps it grounded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 「检索表/视图实例」「检索相关部门职责与治理边界」「汇总为中文结论」 — and names the specific subcommand form (ontology bkn object-type query), rather than vague language.	3 / 3
Completeness	Answers both what (find tables/views → retrieve duties → summarize) and when, via an explicit 「当用户问…时使用」 trigger clause equivalent to 'Use when…'.	3 / 3
Trigger Term Quality	「当用户问『表在哪、哪个视图、数据资产归属、谁负责这类数据』时使用」 gives natural phrasing a user would actually say, covering the common variants for this domain.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (locating tables/data-asset ownership) with distinct triggers, unlikely to fire for the sibling metrics/SQL skill (smart-ask-data).	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 7 suspicious	Warning

	Total	14 / 16 Passed

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

Reviewed: about 12 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.