etf-analysis

ETF分析：产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。

Quality

62%

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/etf-analysis/SKILL.md

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 content is highly actionable with extensive executable code and concrete China-market ETF reference data, but it is a long monolithic document that mixes some conceptual explanation Claude already knows and lacks explicit validation checkpoints and external reference splitting.

Suggestions

Trim concept explanations Claude already knows (e.g., the definition of ETFs, basic volatility-decay primer) and keep only the non-obvious China-market specifics.

Split large reference blocks into one-level-deep files (e.g., references/data-analysis.md for the section 7 code templates, references/etf-catalog.md for the product tables) and link them from the overview.

Add explicit validation/feedback steps to the analytical workflows (e.g., after computing tracking error, validate against the 优秀/合格/较差 thresholds before ranking ETFs) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with genuinely useful reference material (ETF codes, fee tables, QDII premium thresholds, tax rules) and executable code, but at ~870 lines it includes conceptual padding Claude already knows (e.g., "ETF（交易所交易基金）是被动投资与资产配置的核心工具") and could be tightened, matching the score-2 anchor of mostly efficient with some unnecessary explanation.	2 / 3
Actionability	It provides numerous complete, executable Python functions with docstrings (etf_score, fee_drag_analysis, sector_momentum_rotation, calc_tracking_error, calc_premium_discount, tushare data fetchers) plus concrete ETF codes, fee percentages, and decision thresholds, matching the score-3 anchor of fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (e.g., the Step 1–5 ETF selection framework in 3.1, rebalancing triggers in 4.1, scenario templates in section 8), but there are no explicit validation checkpoints or feedback loops for verifying intermediate results, matching the score-2 anchor of steps listed with missing/implicit checkpoints.	2 / 3
Progressive Disclosure	The body is internally well-organized into nine numbered sections with tables and code, but it is monolithic — no bundle files exist and substantial content that would benefit from being split (the section 7 code templates, section 1 product catalog, section 8 prompt templates) is all inline with no one-level-deep references, matching the score-2 anchor of content that should be separate being inline.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 lists several concrete ETF-analysis capabilities, but it omits any explicit "when to use" trigger guidance and relies on a capability list rather than natural trigger phrasing, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to screen, compare, or analyze China-market ETFs, or to build ETF-based portfolios').

Include natural trigger variations users would actually say, such as 'ETF推荐', 'ETF对比', '指数基金筛选', alongside the capability terms.

Sharpen distinctiveness by foregrounding the China-market/quant-allocation framing early so it is less likely to conflict with a general fund-analysis skill.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete analytical actions — "产品筛选、费率对比、跟踪误差、流动性评估、策略应用" (product screening, fee comparison, tracking error, liquidity assessment, strategy application) — matching the score-3 anchor of listing several specific concrete actions.	3 / 3
Completeness	The "what" is clearly stated (ETF analysis capabilities and a quant allocation framework), but there is no "Use when..." or equivalent explicit trigger guidance for when Claude should invoke the skill, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It surfaces relevant ETF keywords ("ETF分析", "费率对比", "跟踪误差") a finance user might say, but offers few natural variations (no "ETF推荐", "指数基金", "ETF对比") and reads more as a capability list than natural trigger phrasing, matching the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The China-market ETF framing ("中国市场ETF量化配置框架") gives it a reasonably clear niche, but trigger terms like fee comparison and tracking error could still overlap with a more general fund/asset-allocation analysis skill, matching the score-2 anchor of somewhat specific but potentially overlapping.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (871 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/etf-analysis/SKILL.md
Commit: 8643fcd

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.