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

68%

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

75%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.

The body is a tight, well-structured routing skill with concrete priority chains and a sensible fallback mechanism. It could improve by tightening the narrative example and making validation checkpoints more explicit.

Suggestions

Tighten the trailing fallback-chain narrative block; the prose ('transparent to the user', 'zero config required') adds little over the flow diagram.

Make the availability check an explicit validation checkpoint in the workflow (e.g., a numbered 'verify source is reachable before proceeding' step).

If API-detail references are intended, consider signaling them as one-level-deep references with explicit pointers rather than only inline `load_skill()` calls.

Dimension	Reasoning	Score
Conciseness	Lean tables and tight priority lists with minimal padding; only mild over-explanation in the trailing fallback-chain narrative ('zero config required', 'transparent to the user'). Not 5 because a few explanatory lines could be trimmed.	4 / 5
Actionability	Provides concrete, actionable guidance: `source: "auto"`, per-market priority chains, `load_skill("akshare")`, and `TUSHARE_TOKEN` checks. Not 5 because the fallback-chain example is illustrative flow rather than copy-paste executable code.	4 / 5
Workflow Clarity	Clear sequence (identify market -> pick source by priority -> load skill) with an availability-check checkpoint and an error-recovery fallback on 'connection timeout'. Not 5 because checkpoints are implicit rather than formal validation steps.	4 / 5
Progressive Disclosure	Well-organized into clear sections (overview, decision tree, availability, symbol formats, fallback chain) and defers API details to other skills via one-level-deep `load_skill()` routing. Not 5 because the body exceeds the under-50-line simple-skill exception, so structure is good rather than maximally split.	4 / 5
	Total	16 / 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 states both purpose and a specific load-time trigger, and occupies a distinct niche. It could be strengthened by listing more concrete capabilities and a broader set of natural trigger terms.

Suggestions

Add a couple more concrete capability phrases (e.g., 'routes symbols to the right market data source by priority and availability') to raise specificity.

Broaden trigger terms to include natural synonyms users say, such as 'historical data', 'market data', or 'stock data'.

Optionally add an explicit 'Use when...' clause listing concrete trigger conditions to push completeness toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('data source selection') and one concrete action ('decision tree' to 'choose the best available data source'), but does not enumerate several distinct capabilities. Not 4 because only ~2 actions are stated rather than several.	3 / 5
Completeness	Both 'what' ('Data source selection decision tree... choose the best available data source') and 'when' ('Load this skill BEFORE any backtest or data-fetching task') are present and explicit. Not 5 because the trigger phrasing is narrower than a comprehensive list of concrete trigger conditions.	4 / 5
Trigger Term Quality	'backtest' and 'data-fetching task' are relevant natural triggers for the domain, but common synonyms like 'historical data', 'market data', or 'stock data' are absent. Not 4 because keyword coverage is limited rather than good with few gaps.	3 / 5
Distinctiveness Conflict Risk	Tied to a distinct niche (data-source routing before backtest/data-fetching) with clear triggers, giving low overlap risk. Not 5 because the broad 'data-fetching' framing could marginally overlap with general data 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: 6565e03

Reviewed: 8 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.