CtrlK
BlogDocsLog inGet started
Tessl Logo

fundamental-filter

Fundamental factor screening — filter stocks by PE/PB/ROE, financial statement fields, and other metrics for value or growth selection. Supports A-shares (via tushare extra_fields or fundamental_fields) and HK/US stocks (via yfinance Ticker info).

58

Quality

67%

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 ./agent/src/skills/fundamental-filter/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 content is dense, executable, and well-structured, with strong concrete examples for both A-share and HK/US paths. Its main weakness is the absence of an explicit validation feedback loop in the screening workflow and no use of reference files to offload detail.

Suggestions

Add an explicit validation checkpoint for batch screening (e.g., assert no NaN in signal columns, verify ROE unit consistency, re-check after fillna) to form a validate->fix->retry loop.

Provide a complete executable A-share value-filter signal function rather than only numbered prose steps, to match the actionability of the HK/US example.

Move the full yfinance screening function and the statement column-mapping table into a reference file referenced one level deep from SKILL.md.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes competence (no basic explanations of PE/PB/ROE); the two A-share config examples are slightly redundant but each demonstrates a distinct mechanism, so minor trimming is possible.

4 / 5

Actionability

It provides a fully executable screen_us_stocks function, concrete config.json blocks, a column-mapping table, and an executable pre-filter snippet; the core A-share value-filter signal logic stays as numbered prose rather than a complete executable function, a minor gap.

4 / 5

Workflow Clarity

Signal logic is given as clear numbered steps and Common Pitfalls offers implicit validation guidance (NaN handling, PIT-safety, ROE units), but there is no explicit validate->fix->retry checkpoint, and batch screening caps this at 3.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections and tables and is navigable, but with no bundle files all ~170 lines are inline; the full yfinance function and statement-mapping detail could be offloaded to one-level-deep references.

4 / 5

Total

15

/

20

Passed

Description

66%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 and uses natural trigger terms within a clear niche, but it omits an explicit 'when to use' clause, which caps its completeness. Adding a 'Use when ...' sentence would raise the score meaningfully.

Suggestions

Add an explicit 'Use when ...' clause naming trigger phrases such as 'screening stocks by fundamentals', 'value/growth factor selection', or 'PE/PB/ROE filtering'.

Replace 'and other metrics' with a concrete example or omit it to remove the vague gap in specificity.

Include common synonyms like 'valuation' or 'factor investing' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('filter stocks by PE/PB/ROE', 'financial statement fields', 'value or growth selection') plus specific mechanisms (tushare extra_fields/fundamental_fields, yfinance Ticker info); the vague 'and other metrics' keeps it just below comprehensive.

4 / 5

Completeness

It clearly answers 'what' (fundamental factor screening by PE/PB/ROE and statement fields) but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Natural keywords a quant user would say are present ('PE/PB/ROE', 'value or growth', 'filter stocks', 'fundamental factor screening'), but common synonyms like 'valuation' or 'factor investing' are missing.

4 / 5

Distinctiveness Conflict Risk

Fundamental factor screening is a clear niche with distinct triggers (PE/PB/ROE, fundamental fields), with only minor overlap risk against sibling technical-backtest or stock-screening skills.

4 / 5

Total

15

/

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
HKUDS/Vibe-Trading
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.