factor-research

Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.

Quality

66%

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/factor-research/SKILL.md

Quality

Content

75%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.

The content is a well-structured, actionable reference with concrete tables, thresholds, and executable code, all efficiently written. The main gaps are the absence of an explicit validation feedback loop and the inlining of detailed subsections that could live in separate reference files.

Suggestions

Add an explicit validate→fix→retry loop for the batch analysis (e.g., 'if IC mean > 0.10 or group curves are non-monotonic, re-check for look-ahead bias and rerun').

Show a concrete factor_analysis tool invocation example (parameters filled in) rather than only the parameter table.

Move the detailed Factor Combination methods and Common Pitfalls into one-level-deep reference files (e.g., COMBINATION.md, PITFALLS.md) with clearly signaled links from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient — parameter tables, threshold tables, and code blocks earn their tokens — with only minor explanatory asides ('A larger spread means stronger selection power') that could be trimmed.	4 / 5
Actionability	It provides executable Python (Registry example), a pip command, concrete parameter/output tables, and IC/IR thresholds, but the factor_analysis tool invocation and the combination formulas are shown as description/math rather than copy-paste call examples.	4 / 5
Workflow Clarity	The five numbered steps are clearly sequenced with interpretation standards and pitfalls serving as validation checkpoints, though there is no explicit validate→fix→retry feedback loop for the batch cross-sectional analysis.	4 / 5
Progressive Disclosure	The body is well-organized into clearly headed sections with cross-links to sibling skills, but several lengthy sections (Factor Combination methods, Common Pitfalls) are inlined rather than split into one-level-deep reference files.	4 / 5
	Total	16 / 20 Passed

Description

58%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.

The description is specific and well-targeted to a niche quant audience, but it lacks an explicit 'Use when...' trigger clause and natural-language synonyms, leaving the 'when' only weakly implied. Adding concrete trigger phrases would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when evaluating single-factor predictive power, tuning multi-factor weights, or diagnosing factor decay').

Include natural-language synonyms and file/term variants users might say (e.g., 'factor analysis', 'alpha evaluation', 'IC/IR', '.csv factor panels').

Clarify the boundary with the multi-factor skill so 'factor combination' does not ambiguously trigger either skill.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'IC/IR analysis, quantile backtesting, and factor combination' — giving solid coverage of the factor-research domain, though it stops short of a fully comprehensive action list.	4 / 5
Completeness	It clearly states the 'what' (a factor research framework with named techniques) but the 'when' is only weakly implied by 'Suitable for cross-sectional factor evaluation' with no explicit 'Use when...' trigger clause, capping it at 3.	3 / 5
Trigger Term Quality	Relevant domain terms ('factor research', 'IC/IR analysis', 'quantile backtesting') are present but there are no synonyms, file extensions, or layperson variations a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	The quant factor-research niche is clearly distinct with specialized triggers, but 'factor combination' creates minor overlap risk with a related multi-factor skill.	4 / 5
	Total	14 / 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/factor-research/SKILL.md
Commit: d71ed8d

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.