broker-research-analyst

券商研报分析助手，聚焦"研报获取→结构化提取→多机构观点对比→风险识别→决策辅助"。使用时机：汇总个股券商研报、追踪行业研报、对比多机构观点、识别卖方利益冲突、验证研报时效性。默认数据源为东方财富研报中心公开接口（无需 API Key）。

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./egs_skill/broker-research-analyst/SKILL.md

Quality

Content

71%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.

Highly actionable with concrete commands and a clear orchestration sequence, but weakened by padded PDF-parser prose and incomplete progressive disclosure: real bundle references are not signaled from the body and one referenced file does not exist.

Suggestions

Trim the PDF-parser section: drop vendor/promotional descriptors ("微软出品", "OpenDataLab 出品", "准确率 98.7%") and keep only the chain order, config knobs, and invocation flags.

Link the existing bundle files from the body — e.g. replace the inline 机构白名单 summary with "见 [references/机构白名单.md](references/机构白名单.md)" and link [assets/研报分析模板.md](assets/研报分析模板.md) and [references/评级体系说明.md](references/评级体系说明.md).

Fix or remove the dangling [PDF_IMAGE_RESEARCH.md](../PDF_IMAGE_RESEARCH.md) link, since that file is not present in the bundle.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and commands, but the PDF-parser section includes promotional/background prose Claude doesn't need ("微软出品", "OpenDataLab 出品", "准确率 98.7%", "专为中文 PDF 优化") that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready commands covering common cases (stock/industry/list, with and without --download) plus a concrete config/settings.json example, matching fully executable guidance.	5 / 5
Workflow Clarity	The Team-First pipeline is a clear numbered sequence with a quality-gate validation checkpoint, but no explicit validate→fix→retry feedback loop is described, so it stays below 5.	4 / 5
Progressive Disclosure	Structure exists (script table, agent table), but existing reference files (机构白名单.md, 评级体系说明.md) and the report template asset are not linked from the body, the long PDF-parsing detail is inlined, and the body references a non-existent ../PDF_IMAGE_RESEARCH.md.	3 / 5
	Total	15 / 20 Passed

Description

87%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 strong, specific description that clearly states both capability and trigger conditions in third person with concrete use-case phrases. Minor synonym coverage gaps in trigger terms and one slightly abstract action keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists a concrete action pipeline ("研报获取→结构化提取→多机构观点对比→风险识别→决策辅助") plus specific use-case actions, but "决策辅助" is mildly abstract, leaving a minor coverage gap short of a 5.	4 / 5
Completeness	Explicitly answers both what (the chained analysis pipeline) and when ("使用时机：..." with concrete trigger scenarios), matching the anchor for clear what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Natural user phrases like "汇总个股券商研报", "追踪行业研报", "对比多机构观点" are present, but common synonyms/triggers such as 评级、目标价、盈利预测 are missing, so it falls short of comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (券商研报 / 东方财富研报中心) with domain-specific triggers, making conflict with other skills minimal.	5 / 5
	Total	18 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: charliedream1/ai_quant_trade
Path: egs_skill/broker-research-analyst/SKILL.md
Commit: 6565e03

Reviewed: 8 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.