CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

finance-research

金融研究技能。用于上市公司/行业研究、财报解读、行情数据分析、估值框架、投资主题调研。核心原则:数据必须标注来源与日期、区分事实与观点、明确披露不确定性。触发场景:分析公司、读财报、行业研究、投资主题调研。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 body is a compact, well-structured instruction-only skill: authoritative data sources with URLs, three concrete analysis frameworks, a copy-ready report template, and enforced discipline rules with validation-like checkpoints. It stays lean and assumes Claude's competence throughout. Remaining gaps are the vague market-data source, checkpoints not inlined into the workflow, and some repetition of the sourcing rules.

Suggestions

Name one or two concrete free market-data endpoints (or an example EDGAR API query with the required User-Agent header) instead of the vague "公开行情接口(稳定性有限)".

Inline the validation checkpoints into the workflow itself — e.g., after data acquisition add an explicit "verify each key number has source + date before analysis" step, rather than keeping all checks in the separate 纪律性守则 section.

Consolidate the repeated source/date-disclosure rules (sections 1.2, 2.3, template header, and 4) into one authoritative statement to save tokens, and give the research-protocol dependency a clear path or link.

DimensionReasoningScore

Conciseness

The body is dense and efficient — tables of named sources, numbered framework steps, and a template, with no explanation of concepts Claude already knows (DCF and PE/PB/PS are only named, not taught). Not 5 because the source/date-disclosure rule is repeated in section 1.2, section 2.3, the template header, and section 4, and the disclaimer appears in both the header blockquote and the template.

4 / 5

Actionability

Mostly concrete and executable: a specific SEC EDGAR URL with the User-Agent caveat, named data sources (cninfo, 国家统计局, 央行), specific metrics (毛利率/净利率, CR3/CR5, PEST/波特五力), and a copy-ready report template. Not 5 because "实时行情:公开行情接口(稳定性有限)" is vague with no named API, and there is no example EDGAR query despite the URL being given.

4 / 5

Workflow Clarity

A clear numbered sequence (数据获取 → 分析框架 → 输出报告 → 纪律守则) with real checkpoints present: failed-data handling ("拿不到就明说'该数据未能获取'"), mandatory source verification, and the adversarial 逆向检查 rule. Not 5 because these checkpoints live in a separate rules section instead of being woven into the workflow steps as inline validation points; not 3 because validation is clearly present, not absent.

4 / 5

Progressive Disclosure

A well-organized single file (~82 lines) with numbered sections and subsections; nothing inlined clearly belongs in a separate file, and there are no nested references. Not 5 because the body exceeds the under-50-lines simple-skill case and the research-protocol dependency is only mentioned in a top blockquote without a path or link, making navigation to it unclear.

4 / 5

Total

16

/

20

Passed

Description

83%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 description that clearly states the skill's domain, several concrete capability areas, core principles, and an explicit trigger-scenario clause. Trigger terms are natural and finance-specific, keeping conflict risk low. The only gaps are a few missing synonyms (估值, 股票, 基本面) and slightly generic action verbs.

DimensionReasoningScore

Specificity

Lists several concrete capability areas ("财报解读", "行情数据分析", "估值框架", "投资主题调研") beyond just naming the finance domain. Not 5 because the actions stay at domain level (research/analyze) rather than fully concrete operations, and not 3 since more than 1-2 specific actions are named.

4 / 5

Completeness

Explicitly answers both what ("用于上市公司/行业研究、财报解读、行情数据分析、估值框架、投资主题调研") and when ("触发场景:分析公司、读财报、行业研究、投资主题调研") with concrete trigger phrases. The explicit trigger-scenario clause satisfies the completeness requirement fully, so it is not capped at 3 or reduced to 4.

5 / 5

Trigger Term Quality

Trigger phrases "分析公司、读财报、行业研究、投资主题调研" are natural terms a user would say when needing this skill. Not 5 because common variations like 估值、股票、基本面、股价 are missing from the triggers.

4 / 5

Distinctiveness Conflict Risk

Clear finance-research niche with distinct triggers (financial reports, valuation, industry research) giving minimal conflict risk with unrelated skills. Not 5 because it overlaps slightly with a generic research skill on broad requests like "研究一下这家公司", and its relationship to research-protocol blurs the boundary.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

arwei944/research-bench

Path

.pi/skills/finance-research/SKILL.md

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.