tushare-data

面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/tushare-data/SKILL.md

Quality

Content

56%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 thorough, well-structured skill body with strong interface coverage, concrete rules, and clear sequenced workflows, but it is long and repetitive, supplies little executable code, and fails to surface its own bundle scripts. Tightening repetition and wiring up the scripts/reference files would lift the weaker dimensions.

Suggestions

Consolidate the repeated trigger-phrase lists across 'When to use', 'Natural-language trigger guide', and 'Quick rule' into one section to cut length and repetition.

Add a small inline executable Tushare example (init pro_api + a daily call) and link to scripts/stock_data_demo.py and scripts/fund_data_demo.py so actionability and progressive disclosure both improve.

Make the validate→fix→retry loop explicit in at least one workflow template (e.g., Data retrieval rules) to push workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	Content is structured and actionable, but at 822 lines it repeats trigger phrases across 'When to use', 'Natural-language trigger guide', 'Intent taxonomy', 'Workflow templates', 'Examples' and 'Quick rule', and restates meta-principles Claude already knows; could be tightened without losing clarity.	3 / 5
Actionability	Names concrete interfaces (daily, pro_bar, fina_indicator) and rules (YYYYMMDD dates, 600519.SH codes, file naming, output contract), but provides almost no executable code — only one bash export snippet — and never points to the ready-made scripts/fund_data_demo.py and stock_data_demo.py, leaving copy-paste execution unmet for a code/data skill.	3 / 5
Workflow Clarity	Nine workflow templates are clearly sequenced with numbered steps and validation is present (environment check, schema/empty-result checks, 分段合并去重, 部分成功原则), satisfying the batch-operation guidance; held at 4 because explicit validate→fix→retry feedback loops are implied rather than spelled out.	4 / 5
Progressive Disclosure	It correctly offloads the full interface catalog to references/数据接口.md (a real one-level-deep file) and keeps a minimal set inline, but the two scripts/ demo files are never referenced or signaled from the body, and large inlined trigger/example blocks could themselves live in reference files.	3 / 5
	Total	13 / 20 Passed

Description

86%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 strong, third-person description that pairs concrete data-workflow actions with rich natural-language trigger phrases and a clear, distinctive niche. It could be nudged to perfect by adding an explicit "Use when..." trigger clause alongside the existing 适用于 scenarios.

Suggestions

Add an explicit "Use when..." trigger sentence to anchor the "when" as directly as the "what", pushing completeness to a clear 5.

List the concrete actions as distinct verbs (获取、清洗、对比、筛选、导出、分析) rather than a comma category to maximize specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions (数据获取、清洗、对比、筛选、导出与简要分析) plus enumerated research scenarios, but stops short of the fully comprehensive concrete-verb list of a 5.	4 / 5
Completeness	Explicitly answers "what" (turns NL requests into executable data workflows) and conveys "when" through trigger phrases and an 适用于 scenarios clause; falls just short of a clean explicit "Use when..." directive.	4 / 5
Trigger Term Quality	Embeds multiple natural phrases users actually say ("看看这只股票最近怎么样", "帮我查财报趋势", "北向资金在买什么", "给我导出一份行情数据") with strong synonym/variation coverage.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Chinese NL → Tushare/A股 financial data) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (823 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: agentscope-ai/ReMe
Path: skills/tushare-data/SKILL.md
Commit: 0eba6ea

Reviewed: 4 days 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.