akshare

AKShare financial data aggregator (18k+ stars). Free, no API key. Covers A-shares, US, HK, futures, macro, forex. Primary fallback for tushare and yfinance.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/akshare/SKILL.md

Quality

Content

85%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.

An efficient, highly actionable reference body: executable quick-start code, exact symbol/date conventions, and a genuinely useful Chinese column-name translation table. The main defect is the closing reference pointer, which names a `references/` subdirectory that is not present in the bundle, leaving navigation to less common interfaces broken.

Suggestions

Fix the dangling reference: either create the `references/` directory with per-market interface docs and cite them by exact filename (e.g. 'See [references/advanced_interfaces.md](references/advanced_interfaces.md)'), or remove the pointer and inline the handful of interfaces that matter.

Remove the volatile '18k+ stars' figure from the body (it also appears in the description) — star counts go stale, and it adds no actionability.

Trim the Overview paragraph, which repeats the frontmatter description ('free, no API key'), and keep only the GitHub URL and install command.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — tables of function signatures, symbol formats, and a Chinese-to-English column-name map that Claude genuinely would not know. Minor penalty for the time-sensitive '18k+ stars' figure in the Overview and slight repetition of the frontmatter's 'free, no API key' claim, so it sits just below anchor 5's 'every token earns its place'.	4 / 5
Actionability	The Quick Start is copy-paste-ready executable code for all three markets with realistic symbols, dates, and adjust flags, and the tables give exact function names and key params. The symbol-format and date-format sections cover exactly the details that would otherwise cause silent failures, matching anchor 5.	5 / 5
Workflow Clarity	This is a single-action skill (fetch market data) and the action is unambiguous with executable examples for every market; per the simple-skill guideline that warrants 5. There are no destructive or batch operations requiring validation checkpoints, and the fallback behavior (runner falls back to AKShare when tushare/yfinance are unavailable) is explicitly documented.	5 / 5
Progressive Disclosure	Sections are well-organized and the body appropriately keeps only the top-10 interfaces inline, but the pointer 'see the `references/` subdirectory' is vaguely signaled and the referenced directory does not exist in the bundle — a dangling reference. Structure is good but the navigation pointer is broken/unclear, matching anchor 3 rather than 4.	3 / 5
	Total	17 / 20 Passed

Description

65%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 distinct, information-dense description for a well-defined niche, weakened by the absence of any explicit 'Use when...' trigger clause and by a lack of action verbs describing what the skill actually does. Adding trigger guidance would lift completeness from 3 to 5.

Suggestions

Add an explicit trigger clause, e.g. 'Use when fetching A-share/Chinese market data without an API key, or when tushare or yfinance are unavailable or rate-limited.'

State concrete actions in third person, e.g. 'Fetches daily OHLCV, real-time quotes, and macro/forex/futures data for A-shares, US, and HK markets', instead of a noun-phrase coverage list.

Include natural synonyms users would say — 'China stock data', 'Chinese A-shares', 'HK stocks' — to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("financial data aggregator") and enumerates concrete coverage areas ("A-shares, US, HK, futures, macro, forex"), but states no concrete actions — it is noun phrases rather than 'fetch/retrieve X' verbs, matching anchor 3's level of specific-but-not-comprehensive rather than anchor 4's list of several specific actions.	3 / 5
Completeness	The 'what' is clear (free, no-API-key financial data aggregator across named markets), but there is no 'Use when...' clause — 'Primary fallback for tushare and yfinance' only weakly implies when to use it. Per the guideline, a missing explicit 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage: "AKShare", "A-shares", "futures", "macro", "forex", and sibling-library names "tushare" and "yfinance" users would plausibly say. A few common variations are missing (e.g., 'China stock data', 'Chinese markets', 'HK stocks'), so it falls short of anchor 5's comprehensive synonym coverage but is noticeably above anchor 3.	4 / 5
Distinctiveness Conflict Risk	The named library plus explicit positioning ('Free, no API key... Primary fallback for tushare and yfinance') carves out a clear niche with distinct triggers; overlap with sibling skills is explicitly resolved rather than ambiguous, matching anchor 5.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/akshare/SKILL.md
Commit: 251b094

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.