data-routing

Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source.

Quality

75%

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 ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/data-routing/SKILL.md

Quality

Content

78%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 lean, highly actionable routing skill: every section carries non-obvious operational knowledge (source priorities, token requirements, symbol formats, fallback behavior) with no padding. It correctly delegates API detail to per-source skills, and only minor tightening and a couple of edge-case gaps keep it from top marks.

Suggestions

Merge or trim the "Fallback Chain (Runner Layer)" section, which re-explains the automatic fallback already stated in the Backtest Scenario, and drop the filler line "This is transparent to the user — they just see results".

Add a two-line example config.json snippet showing `source: "auto"` in context, and a concrete fallback instruction for when every source in a market fails.

Dimension	Reasoning	Score
Conciseness	The body is lean and factual — tables of auth tokens, network requirements, and symbol formats that Claude cannot infer, with no padding or concept explanations. Not 5 because the "Fallback Chain (Runner Layer)" trace partially duplicates the Backtest Scenario's "falls back to alternative sources" statement, and "This is transparent to the user — they just see results" is filler.	4 / 5
Actionability	Guidance is directly executable: exact per-market priority chains, the TUSHARE_TOKEN environment variable check, `load_skill("akshare")`, `source: "auto"`, and copy-paste-ready symbol examples. Not 5 due to minor gaps — no example config.json snippet and no concrete command to test network availability for the free sources.	4 / 5
Workflow Clarity	Both scenarios are clearly sequenced (identify market → pick source by priority → load the source skill) with explicit checkpoints (availability checks, connection-timeout fallback). Not 5 because there is no guidance for the case where all sources fail, and the network availability check is stated but not concretely testable.	4 / 5
Progressive Disclosure	The ~64-line body is well organized under clear headers and correctly delegates all API detail to per-source skills via the Skill column and `load_skill(...)`, rather than inlining it — textbook one-level-deep reference behavior with no bundle files needed.	5 / 5
	Total	17 / 20 Passed

Description

62%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.

The description clearly and explicitly states both what the skill does and when to load it, with a genuinely distinct niche (data source routing). It is held back by thin capability specificity and limited trigger vocabulary for a domain where users would naturally mention many specific data needs.

Suggestions

Add one or two concrete capabilities or scope markers to the "what" clause, e.g., "Selects among tushare, akshare, yfinance, okx, and ccxt by market and availability" instead of the abstract "decision tree" phrase.

Expand trigger vocabulary with natural user phrasings such as "market data", "price data", "stock/crypto/forex data", or "fetching historical data for a backtest".

Mirror the body's coverage (markets: A-shares, US, HK, crypto, futures, macro, forex) so the description signals scope without loading the full skill.

Dimension	Reasoning	Score
Specificity	"Data source selection decision tree" and "choose the best available data source" name the domain plus one concrete action, but the description does not list several specific actions (no markets, sources, or fallback behaviors). It is above anchor 2 because a concrete action is stated, but below anchor 4 because coverage is not comprehensive.	3 / 5
Completeness	Both parts are present: the "what" ("Data source selection decision tree... choose the best available data source") and an explicit "when" ("Load this skill BEFORE any backtest or data-fetching task"). Not 5 because the "what" is terse ("decision tree" does not say what sources are chosen among) and the trigger phrasing could include concrete variations.	4 / 5
Trigger Term Quality	"backtest" and "data-fetching task" are natural user terms, but common variations are missing (e.g., "market data", "price data", "stock data", "crypto data", or any source names). Coverage is relevant but incomplete, matching anchor 3 rather than anchor 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	A routing/selection meta-skill occupies a distinct niche, and triggers like "data source selection" are distinctive. Not 5 because "backtest" could naturally also trigger a backtest-execution skill, creating minor overlap risk with closely related skills.	4 / 5
	Total	14 / 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: charliedream1/ai_quant_trade
Path: a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/data-routing/SKILL.md
Commit: b612402

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.