CtrlK
BlogDocsLog inGet started
Tessl Logo

pair-trading

Pair trading strategy. Trades mean reversion using the spread/ratio Z-score of two correlated instruments. Requires at least two instruments.

58

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/pair-trading/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is concise, well-organized, and clearly sequenced with an explicit pitfalls/verification checklist and executable config examples. Its main weakness is actionability: the signal logic is described as formulas and steps rather than a complete executable code block.

Suggestions

Provide one complete, copy-paste-ready Python snippet implementing the signal logic (compute ratio, rolling mean/std, Z-score, opposite A/B signals, NaN-fill) so actionability reaches anchor 3.

Consider folding the two most critical Common Pitfalls (date alignment via inner join, NaN-fill to 0) inline as explicit checkpoints within the numbered Signal Logic sequence.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives formulas, a parameter table, and config examples without explaining what a Z-score or mean reversion is, so every token earns its place.

3 / 3

Actionability

It provides concrete formulas and fully executable config.json examples, but the core signal-generation logic is expressed as inline expressions and steps (e.g. "ratio = close_A / close_B", "Z < -entry_z -> long A, short B") rather than a complete, copy-paste-ready code implementation, leaving it at anchor 2.

2 / 3

Workflow Clarity

The Signal Logic is a clearly numbered 4-step sequence (compute ratio, rolling mean/std, Z-score, signal generation), and the Common Pitfalls section functions as an explicit verification checklist (align dates via inner join, fill NaN signals with 0, never emit same-direction signals), satisfying the checklist criterion for this single-process skill.

3 / 3

Progressive Disclosure

The skill is a single self-contained ~75-line file with no bundle files and no nested external references, organized into clearly labeled sections (Purpose, Signal Logic, Parameters, Common Pitfalls, etc.); it has no need for external references, so well-organized sections earn anchor 3.

3 / 3

Total

11

/

12

Passed

Description

50%

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 conveys a clear, specific niche and technique but is missing any "Use when..." trigger guidance and lacks natural keyword variations, which collectively cap every dimension at the mid-level. Adding explicit trigger phrasing would lift completeness and trigger_term_quality.

Suggestions

Add a "Use when..." clause, e.g. "Use when the user wants a pair trading / statistical arbitrage strategy on two correlated instruments."

Broaden trigger keywords to include natural variations users say: "statistical arbitrage", "cointegration", "correlation trading", "long-short hedge", "spread trading".

Optionally enumerate concrete actions (e.g., "computes the price-ratio Z-score, generates opposite long/short signals, and exits on mean reversion") to reach multiple concrete actions for specificity anchor 3.

DimensionReasoningScore

Specificity

It names the domain and a concrete technique — "Trades mean reversion using the spread/ratio Z-score of two correlated instruments" — but describes essentially one action rather than listing multiple specific concrete actions, so it falls short of anchor 3.

2 / 3

Completeness

The description answers "what" (trades mean reversion via spread/ratio Z-score) but provides no "when" — there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

"Pair trading" and "mean reversion" are relevant natural keywords, but common variations a user might actually say (e.g., statistical arbitrage, cointegration, correlation trading, long-short hedge) are absent and the Z-score phrasing leans technical.

2 / 3

Distinctiveness Conflict Risk

"Pair trading strategy" is a recognizable niche unlikely to conflict with unrelated skills, but it has no distinct explicit triggers and could overlap with other mean-reversion or strategy skills, so it does not reach the clear-distinct-trigger bar of anchor 3.

2 / 3

Total

8

/

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.