tushare

tushare是一个财经数据接口包，拥有丰富的数据内容，如股票、基金、期货、数字货币等行情数据，公司财务、基金经理等基本面数据。该模块通过标准化API方式统一了数据资产的对外服务方式，以帮助有需要的技术用户更实时、简洁、轻量的使用相关数据。

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/tushare/SKILL.md

Quality

Content

72%

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

The body is well-structured for progressive disclosure and highly actionable in its quick-start, with real bundle files backing the references. Its main weaknesses are the redundant verbatim overview and the lack of error/validation guidance around rate-limited API calls.

Suggestions

Remove the '概述' section (or shorten it to one line), since it duplicates the frontmatter description token-for-token.

Add a brief error-handling note for the quick start, e.g. check the returned DataFrame is empty, retry on rate-limit/500 errors, and paginate using start_date/end_date when hitting the per-request row cap.

Consider moving the 229-row interface catalog into a references/index.md and keeping only category groupings in SKILL.md to reduce the inline token load.

Dimension	Reasoning	Score
Conciseness	The '概述' section duplicates the frontmatter description verbatim, adding redundant tokens, and the 229-row interface table is heavy; the quick-start and parameter sections are lean, so it is mostly efficient but could be tightened.	2 / 3
Actionability	Quick start provides executable commands ('pip install tushare -i ...', 'export TUSHARE_TOKEN=...') and a complete runnable Python snippet (pro.stock_basic with fields), plus links to real example scripts and concrete parameter formats (YYYYMMDD, ts_code), making it copy-paste ready.	3 / 3
Workflow Clarity	Quick start is sequenced (install → register token → find interface in docs → write code), but there are no validation/error checkpoints or feedback guidance despite the table noting rate limits ('每次请求最多返回200条记录'), so checkpoints are missing for batch-prone API calls.	2 / 3
Progressive Disclosure	Structure is well split: overview and quick start inline, per-interface detail one level deep under references/<category>/, and executable examples in scripts/, with the interface table serving as a clearly signaled navigation index to those reference files.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 clearly identifies tushare as a financial-data interface package and enumerates its data domains, but it reads as a product blurb rather than skill-trigger guidance and omits any 'Use when...' clause. It is competent but generic, landing at the middle anchor across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs Chinese financial/market data (stocks, funds, futures, bonds, macro indicators) via the Tushare API.'

Reframe capabilities as concrete actions ('Fetch stock daily bars', 'Query fund NAV', 'Pull macro indicators') instead of describing the product's service model.

Include natural trigger variations users would actually say, such as 'A股行情', '基金净值', '期货行情', '宏观经济数据', 'tushare token'.

Dimension	Reasoning	Score
Specificity	Quotes '财经数据接口包' and lists data domains ('股票、基金、期货、数字货币等行情数据，公司财务、基金经理等基本面数据'), naming the domain and content, but it describes the product ('标准化API方式统一了数据资产的对外服务方式') rather than concrete skill actions like fetch/extract/query, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It clearly answers 'what' (a financial data interface package with the listed data), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Natural domain keywords are present ('股票', '基金', '期货', '数字货币', '行情数据', '基本面', '财务') that a Chinese user would say, but common variations and explicit trigger phrasing are missing, so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	The financial-data niche ('财经数据接口包') is reasonably specific, but without distinct explicit triggers it could still overlap with other finance/data skills, so it does not reach the 'clear niche with distinct triggers' anchor.	2 / 3
	Total	8 / 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: 33 missing, 229 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	13 / 16 Passed

Repository: charliedream1/ai_quant_trade
Path: a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/tushare/SKILL.md
Commit: 3dba332

Reviewed: 3 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.