CtrlK
BlogDocsLog inGet started
Tessl Logo

factor-research

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

62

Quality

73%

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 ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/factor-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is a well-organized, domain-dense reference with concrete thresholds and formulas, but the batch workflow lacks an explicit validation/feedback loop and the main tool invocation has no concrete code example. Splitting the longer sections into reference files would improve progressive disclosure.

Suggestions

Add a concrete factor_analysis tool invocation example (command or code snippet) showing the parameter values in use.

Insert an explicit validation/verification step in the workflow (e.g., check output files exist and IC values are non-NaN before interpreting) to provide a feedback loop for this batch operation.

Move the detailed factor-combination methods and/or common-pitfalls sections into separate reference files linked from SKILL.md to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Dense and well-organized, mostly tables and concrete criteria, assuming domain knowledge (IR, Z-score, Schmidt orthogonalization) without generic padding; only minor rationale sentences in the pitfalls section could be trimmed.

4 / 5

Actionability

Provides concrete parameter tables, output-file tables, IC/IR thresholds, and executable combination formulas, but lacks a concrete tool-invocation example or full code for the core factor_analysis call.

4 / 5

Workflow Clarity

The 5-step workflow is clearly sequenced with interpretation criteria as implicit checkpoints, but this batch operation has no explicit validation/verification gate or error-recovery feedback loop, which caps the score at 3 per the batch-operations guidance.

3 / 5

Progressive Disclosure

Well-structured with clear section headers and tables in a single ~135-line file; however some content (detailed combination methods, extensive pitfalls) is inlined that could be split into one-level-deep reference files.

4 / 5

Total

15

/

20

Passed

Description

78%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, domain-appropriate, and clearly distinguishable, covering both what the skill does and a suitability scenario. It could be improved by adding an explicit 'Use when...' trigger and a few more natural synonyms.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions ('IC/IR analysis, quantile backtesting, and factor combination', 'cross-sectional factor evaluation'), but coverage is not exhaustive enough for a 5.

4 / 5

Completeness

Clearly states 'what' (factor research framework with the listed analyses) and a 'when' clause ('Suitable for cross-sectional factor evaluation across multiple instruments'), though the when is softer than an explicit 'Use when...' trigger.

4 / 5

Trigger Term Quality

Includes domain-natural terms ('factor research', 'IC/IR', 'quantile backtesting', 'factor combination') a quant user would say, but lacks synonyms or file extensions keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear, specialized quant niche with distinctive terminology (IC/IR, quantile backtesting) and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

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
charliedream1/ai_quant_trade
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.