smart-data-analysis

数据分析员工（Data Analyst Agent）的唯一总入口：凡与数据资产、取数、指标、表/视图、治理职责、知识网络、统计或分析相关的问题，必须先经本 skill 做编排与路由，再进入找表或问数等子流程。负责 kn 分域、上下文注入（accountId / date）、多候选 KN 时的 LLM 决策、问数分支的 SQL 生成；与 smart-search-tables / smart-ask-data / ontology-core 的交接。当用户提出任何数据类自然语言任务、或需在多条业务 KN 间切换时使用；所有 ontology CLI 执行均委托 ontology-core 完成，本 skill 不直接执行 CLI。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

A well-structured orchestration skill with strong workflow sequencing, validation checkpoints, and concrete contracts/JSON examples. Its main weaknesses are repetition-driven verbosity and a lack of internal progressive disclosure (no own bundle files), plus a missing SQL-generation example for its headline deliverable.

Suggestions

Consolidate the repeated 'Never 直接执行 ontology CLI' and '禁止交叉兜底' rules into one stated-once section that other sections reference, to cut verbosity.

Add at least one concrete SELECT/WITH SQL example in the 问数分支 since SQL generation is declared a 硬责任 but currently has no template.

Move the long 知识网络声明 / 交接契约 / 职能矩阵 reference material into a references/ file to give SKILL.md a leaner overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient policy text but padded with repetition — 'Never 直接执行 ontology CLI' appears 4+ times and '禁止交叉兜底' is restated across 总入口原则, 路由识别, and 分支走不通 sections; could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready artifacts: JSON condition-wrapping bodies, step checklists, and explicit 交接契约 field tables with missing-value handling — actionable instruction guidance despite the SQL-generation step lacking an example.	3 / 3
Workflow Clarity	Clear sequenced workflows with validation checkpoints: '编排总流程（必须按序）', per-branch checklists, and explicit stop conditions ('占位仍为 <填入…> → 告知用户并停止') plus error-recovery guidance.	3 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist for this skill, so the ~250-line orchestration body is monolithic and inline; sibling-skill links are clearly signaled, but detail that could live in this skill's own references is not split out.	2 / 3
	Total	10 / 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 strong description: third-person voice, explicit trigger guidance, specific concrete actions, and clear delineation from sibling skills. Voice and trigger-clause requirements are both met.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'kn 分域、上下文注入（accountId / date）、多候选 KN 时的 LLM 决策、问数分支的 SQL 生成' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('负责 kn 分域、上下文注入…SQL 生成') and when ('当用户提出任何数据类自然语言任务、或需在多条业务 KN 间切换时使用'), with an explicit 'Use when…' clause.	3 / 3
Trigger Term Quality	Covers natural analyst terms users would say — '数据资产、取数、指标、表/视图、治理职责、统计或分析' — though it mixes in some jargon (KN, ontology CLI), the natural coverage is strong.	3 / 3
Distinctiveness Conflict Risk	Positions itself as the '唯一总入口' and explicitly names sibling skills (smart-search-tables / smart-ask-data / ontology-core) with delegation boundaries, giving it a clear niche unlikely to conflict.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 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: 16 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/ontology/smart-data-analysis/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.