alpha-zoo

Browse and bench the bundled alpha zoos — prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French / Carhart). Use when the user asks "which alphas exist", wants metadata on a named alpha, or wants to run IC/IR on a whole zoo over a universe.

Quality

80%

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

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 tight, actionable orientation with concrete tool calls and useful constraints/pitfalls. Its main weakness is the absence of an explicit validation feedback loop for the batch bench operation, and its external references point to non-bundled paths.

Suggestions

Add an explicit validation checkpoint before/after a whole-zoo bench (e.g. run 'alpha_zoo action=health' first, and interpret empty/failed registry before invoking 'alpha_bench') so the batch workflow has a feedback loop.

Wrap the decision-tree tool invocations in fenced code blocks or a clearer call syntax so they are unambiguously copy-pasteable.

Clarify that the Reference paths (docs/alpha-zoo/spec.md, src/factors/*.py) are repo-internal pointers outside the skill bundle, or move truly needed detail into bundled reference files.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no beginner-concept padding, each section earning its place; the brief Purpose restatement of the description is a minor instance of over-explanation that keeps it just below the lean anchor.	4 / 5
Actionability	Concrete executable tool invocations in the decision tree (e.g. 'alpha_bench' with 'zoo=gtja191, universe=csi300, period=2020-2024') and specific operator rules, with only minor gaps (no literal code-block formatting of calls).	4 / 5
Workflow Clarity	The decision tree maps intents to tool+params and pitfalls add some guards, but the batch 'alpha_bench' over a whole zoo lacks an explicit validate-checkpoint/feedback loop, which caps it at 3 per the batch-operations guidance.	3 / 5
Progressive Disclosure	Well-organized with clearly labeled sections and a Reference section signaling one-level-deep pointers, though the referenced docs/src paths are not present in any bundled references/ directory, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

92%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, complete, and distinct: it names concrete actions and explicit trigger phrases tied to a clearly bounded niche. It is written in third-person imperative voice and avoids fluff. Its only slight gap is trigger-term coverage skewing toward specialist phrasing over lay synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Browse and bench', metadata on a named alpha, run IC/IR) covering the skill comprehensively, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	Explicitly states what it does (browse/bench prebuilt cross-sectional factor libraries) and when to use it with concrete trigger phrases, matching the anchor for clearly answering both what and when.	5 / 5
Trigger Term Quality	Strong natural triggers ('which alphas exist', 'metadata on a named alpha', 'run IC/IR on a whole zoo') plus named zoos, but slightly specialist-leaning with a few lay synonyms missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Highly niche scope (alpha zoos, specific named factor libraries) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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/alpha-zoo/SKILL.md
Commit: d71ed8d

Reviewed: 4 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.