behavioral-finance

Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/behavioral-finance/SKILL.md

Quality

Content

65%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.

A dense, highly actionable body packed with concrete quantitative thresholds, market-specific evidence, and a clear output template. Weaknesses are the absence of an explicit sequenced workflow with validation checkpoints, undefined helpers in the code snippet, and a monolithic single-file structure with no progressive disclosure.

Suggestions

Add an explicit numbered analysis workflow (data prep → sentiment diagnosis → bias detection → signal generation → out-of-sample validation) with a validation checkpoint, since the frameworks are currently parallel rather than sequenced.

Make the composite sentiment snippet executable or explicitly justify the pseudocode by defining normalize() and weighted_sum().

Move the bias tables and sentiment-cycle detail into a references/ file (e.g. BIAS-CHECKLISTS.md), keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Dense, data-rich tables and thresholds with almost no padding, assuming domain knowledge (SUE, CGO, chip-distribution) without explaining basics. A few reference-weight sections (the two bias tables, the sentiment-cycle ASCII chart) could be trimmed or split, keeping it below the lean 5 anchor.	4 / 5
Actionability	Concrete thresholds throughout ('RSI(5) < 15', 'CGO > 0.2', 'abnormal turnover > 3x average'), a component-weighted sentiment spec, checklists, and an output template. However, the Python snippet depends on undefined helpers (normalize(), weighted_sum()) and most signals are pseudo-specs rather than copy-paste code, so not fully executable.	4 / 5
Workflow Clarity	The four analysis frameworks and output template are well structured but presented in parallel; there is no explicit step sequence with validation checkpoints, and out-of-sample validation appears only as a caution in Notes. Checkpoints are missing/implicit rather than minor gaps.	3 / 5
Progressive Disclosure	Good section structure with clear headers, but the ~200-line body is a monolith with no bundle files; the bias tables and sentiment-indicator spec are inline content that could live in reference files. Fits the 3 anchor ('some structure but could be better organized') better than the 2 anchor, since structure is solid and no references exist to be buried.	3 / 5
	Total	14 / 20 Passed

Description

66%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.

A specific, well-keyeded description covering the domain's main capabilities with strong natural keywords. Its main weakness is the absence of any 'when to use' trigger clause, and slight overlap risk with general quant momentum skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing momentum/reversal strategies, extreme market sentiment, or checking trading decisions for cognitive bias.'

Lead with action verbs ('Applies', 'Diagnoses', 'Detects') to sharpen the capability framing.

Add one or two colloquial trigger phrases (e.g. 'market overreaction', 'sentiment extremes') to widen natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('behavioral explanations for momentum and reversal', 'investor sentiment cycles', 'cognitive-bias checklists, and debiasing quantitative strategies'), though framed as topic nouns rather than actions, leaving minor gaps versus the comprehensive 5 anchor.	4 / 5
Completeness	The 'what' is clear and multi-part, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric says caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage ('momentum', 'reversal', 'investor sentiment', 'cognitive-bias', 'debiasing', 'overreaction and underreaction') but missing natural user phrasings like 'market overreacting' or 'sentiment extremes', placing it between the 3 and 5 anchors, above midpoint.	4 / 5
Distinctiveness Conflict Risk	Behavioral finance is a clear niche with distinct triggers, but it overlaps with generic momentum/reversal quant strategy skills — mostly distinct with minor overlap risk rather than the minimal-conflict 5 anchor.	4 / 5
	Total	15 / 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: HKUDS/Vibe-Trading
Path: agent/src/skills/behavioral-finance/SKILL.md
Commit: 251b094

Reviewed: 3 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.