CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-trading

Professional finance research toolkit — backtesting (8 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 88 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 23 market-data sources (tushare, yfinance, okx, binance, akshare, baostock, tencent, mootdx, ccxt, futu, mt5, local, eastmoney, sina, stooq, yahoo, india_broker, qveris, longbridge, plus optional-key finnhub/alphavantage/tiingo/fmp).

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 and offers concrete entry points (install, MCP config, connector commands, example prompts), but it is verbose and repetitive and keeps large reference material inline rather than pushing it to bundled files. Workflows are sequenced but lack explicit validation checkpoints.

Suggestions

Move the full 54-tool catalog and per-zoo Alpha Zoo detail into separate reference files, leaving the SKILL.md body a concise overview that links to them.

Add explicit validation/verification checkpoints to the Shadow Account and backtest workflows (e.g. confirm data coverage, check for lookahead bias, verify report rendered).

Deduplicate the Alpha Zoo, tool-count, and data-source content that currently repeats across the intro, dedicated sections, tool table, and Quick Start.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no basic-concept explanations), but it is padded with redundancy — the Alpha Zoo, tool counts, and data sources are repeated across the intro, dedicated sections, the 54-row tool table, and Quick Start — so it could be tightened considerably.

2 / 3

Actionability

It provides some concrete executable guidance (pip install, MCP config JSON, connector CLI commands, example prompts), but the example workflows are largely prose prompts and the 54-tool table gives one-line descriptions without runnable signatures, leaving key usage details incomplete.

2 / 3

Workflow Clarity

Multi-step processes like the Shadow Account loop and the backtesting example are clearly sequenced with tool names, but there are no explicit validation or verification checkpoints for batch/risky operations such as backtests or report rendering.

2 / 3

Progressive Disclosure

The body has clear section structure, but large content blocks that could live in separate files — the full 54-tool catalog and the per-zoo Alpha Zoo detail — are inlined, and the bundle scripts/ directory is never referenced or signaled from the body.

2 / 3

Total

8

/

12

Passed

Description

60%

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 highly specific about capabilities and clearly scoped to finance research, but it is overloaded with internal jargon and enumeration. It states what the skill does but omits explicit 'when to use it' guidance and natural trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when backtesting a strategy, analyzing a trade journal, or benchmarking quantitative alphas').

Trim internal jargon (qlib158/alpha101/gtja191, the full 23-source list) from the description; surface those details in the body instead.

Reduce the enumeration of counts (88 skills, 30 teams, 462 alphas) in favor of the few concrete actions a user would ask for.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions and capabilities — 'backtesting (8 engines + benchmark comparison panel), factor analysis, ... options pricing ... Trade Journal analyzer, and Shadow Account (extract → backtest → render)' — rather than vague abstractions.

3 / 3

Completeness

It answers 'what does this do' thoroughly but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some user-relevant terms (backtesting, options pricing, trade journal) but leans heavily on technical jargon (qlib158/alpha101/gtja191, 'Alpha Zoo', 'swarm teams', 23 data-source names) that a user would rarely say verbatim, and lacks common natural variations.

2 / 3

Distinctiveness Conflict Risk

The finance-research/quant niche is fairly distinct, but the dense feature-listing style ('88 finance skills, 30 multi-agent swarm teams') could still overlap with adjacent quant or data-tool skills rather than carving a single clear trigger surface.

2 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
HKUDS/Vibe-Trading
Reviewed

Table of Contents

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.