CtrlK
BlogDocsLog inGet started
Tessl Logo

market-microstructure

Market microstructure: bid-ask spread analysis, order-flow toxicity metrics (VPIN / Kyle lambda), liquidity measures (Amihud / Roll), price-impact models, limit-order-book analysis, and China A-share call auction / block trade mechanics.

57

Quality

66%

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/market-microstructure/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 well-organized, actionable reference with concrete formulas, thresholds, worked examples, and an output template, but it is a long monolith that re-explains known theory and lacks an explicit end-to-end workflow with validation checkpoints.

Suggestions

Trim textbook re-explanation Claude already knows (spread decomposition drivers, flash-crash characteristics, LOB depth definitions), keeping only the domain-specific thresholds and China A-share specifics.

Split the monolith into reference files (e.g. china-ashare.md, price-impact.md) and reduce SKILL.md to a concise overview with clearly signaled one-level-deep links.

Add an explicit end-to-end analysis workflow with validation checkpoints (data check -> liquidity -> toxicity -> cost estimate -> report) instead of leaving the sequence implied by the output template.

DimensionReasoningScore

Conciseness

Mostly useful reference material with concrete thresholds and China A-share specifics, but padded with textbook re-explanation Claude already knows (spread decomposition drivers, flash-crash definition, LOB depth meaning), matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than lean-and-efficient.

2 / 3

Actionability

Provides concrete formulas, numeric thresholds (VPIN<0.3, Amihud<0.5), a worked impact calculation with real numbers, decision rules, and a copy-paste output template — highly actionable guidance, and per the instruction-only scoring note absence of executable code is not penalized when guidance is this concrete.

3 / 3

Workflow Clarity

Sub-procedures are sequenced (VPIN steps 1-4, Kyle estimation 1-3, flash-crash measures 1-5) and the output template implies a flow, but there is no unified end-to-end analysis workflow and no validation checkpoints, matching the 'steps present but checkpoints missing or implicit' anchor.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is a ~290-line monolithic document with well-organized sections but content that could be split into reference files; it exceeds the 'under 50 lines, no external references needed' exception, so it lands at the 'some structure but content that should be separate is inline' anchor rather than a clear overview with one-level-deep references.

2 / 3

Total

9

/

12

Passed

Description

67%

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 specific and highly distinctive, naming concrete microstructure analyses and a clear China A-share niche. Its weakness is the absence of an explicit 'Use when...' trigger clause and reliance on jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause naming user scenarios, e.g. 'Use when estimating trading costs, measuring liquidity, detecting order-flow toxicity, or optimizing China A-share execution.'

Pair jargon terms with plain-language variations users would say (e.g. 'bid-ask spread / trading costs', 'price impact / execution slippage') to broaden trigger matching.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'bid-ask spread analysis', 'order-flow toxicity metrics (VPIN / Kyle lambda)', 'liquidity measures (Amihud / Roll)', 'price-impact models', 'limit-order-book analysis', 'China A-share call auction / block trade mechanics' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill covers but provides no explicit 'when' guidance — there is no 'Use when...' clause, so per the judging guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

Contains relevant domain keywords (bid-ask spread, VPIN, Kyle lambda, Amihud, Roll) but leans on specialized jargon and omits common plain-language variations a user might say (trading costs, slippage, execution), matching the 'some relevant keywords but missing common variations' anchor rather than full natural-term coverage.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (market microstructure with China A-share specifics) with distinct triggers unlikely to overlap with other skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

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.