minute-analysis

Minute-level data analysis and backtesting. Retrieves minute candlesticks through OKX/Tushare/yfinance and can be used both for analysis and as input to the backtest engine.

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 ./agent/src/skills/minute-analysis/SKILL.md

Quality

Content

80%

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

The content is lean, executable, and free of concept over-explanation, with strong concrete code and config examples. Its weaknesses are the absence of an explicit validation/verification checkpoint for the batch backtest workflow and a single inline structure that does not progressively disclose deeper reference material.

Suggestions

Add an explicit validation step before backtesting, e.g. 'Verify the loaded DataFrame is non-empty (especially for Tushare, which returns empty data when score < 2000) before running the backtest.'

Move the full OKX candlestick API example and/or indicator templates into a references file linked from the body, keeping SKILL.md as a tighter overview to improve progressive disclosure.

Clarify the backtest run sequence as numbered steps with a checkpoint after data retrieval.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it does not explain what candlesticks, VWAP, or pandas are, and every section (config JSON, API example, indicator templates, pitfalls) is actionable rather than padded.	3 / 3
Actionability	It provides fully executable, copy-paste-ready code (OKX candles request, VWAP/TWAP/volume templates), a concrete config.json snippet, and a specific pip install command.	3 / 3
Workflow Clarity	The flow (set interval in config.json, run the backtest tool) is present, but minute-level backtesting is a batch operation with no explicit validation checkpoint (e.g. verifying data loaded or Tushare non-empty before running), so it is capped at 2.	2 / 3
Progressive Disclosure	The file is well-sectioned but ~96 lines with no bundle references, and content that could be split out (full OKX API example, indicator templates) is kept entirely inline, so structure is only partially optimized.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 is third-person, specific to a clear niche, and states concrete capabilities, but it lacks an explicit "Use when..." trigger clause and omits some common trigger variations. Adding trigger guidance would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs intraday minute-bar data (1m/5m/15m) or wants to run minute-level backtests.'

Include common trigger variations such as 'intraday', '1m/5m bars', or 'minute candlesticks' alongside the existing terms.

Tighten 'can be used both for analysis and as input to the backtest engine' into more concrete named actions to improve specificity.

Dimension	Reasoning	Score
Specificity	"Retrieves minute candlesticks through OKX/Tushare/yfinance" names a concrete action and domain, but "can be used both for analysis and as input to the backtest engine" is only partially specific, so it names some actions without being comprehensive.	2 / 3
Completeness	It clearly states what the skill does, but there is no explicit "Use when..." trigger clause, so the "when" guidance is only implied and completeness is capped at 2 per the rubric.	2 / 3
Trigger Term Quality	Terms like "minute-level data", "backtesting", and "candlesticks" are natural, but common variations such as "intraday" or granularity terms (1m/5m) are missing.	2 / 3
Distinctiveness Conflict Risk	The minute-level granularity combined with named sources (OKX/Tushare/yfinance) and backtesting gives it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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/minute-analysis/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.