finviz-screener

Build and open FinViz screener URLs from natural language requests. Use when user wants to screen stocks, find stocks matching criteria, filter by fundamentals or technicals, or asks to open FinViz with specific conditions. Supports both Japanese and English input (e.g., "高配当で成長している小型株を探したい", "Find oversold large caps with high ROE").

Quality

83%

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

77%

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 a clear, checkpointed workflow and real bundle references, but it is denser than an overview should be: large lookup tables and recipes inline duplicate the reference file. Tightening the body and offloading detail to references would raise both conciseness and progressive disclosure.

Suggestions

Move the full Common Concept Mapping table and most recipes into references/finviz_screener_filters.md, keeping only a short representative subset plus a pointer in SKILL.md.

Replace the six verbose recipe blocks with one canonical example plus a one-line pointer to a Recipes section in the reference file to cut inline token weight.

Add a brief validate-or-confirm loop note around Step 4 (e.g., verify the constructed URL opens the expected screener before reporting) to make the existing checkpoint explicit at execution time.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material (FinViz filter codes Claude does not know), but the large inline Common Concept Mapping table and six full recipes duplicate content that the 77KB references file already holds and could be trimmed or moved.	2 / 3
Actionability	Concrete executable `python3 scripts/open_finviz_screener.py` invocations with full argument lists, exact filter-code tokens, and copy-paste-ready recipe blocks provide fully actionable guidance.	3 / 3
Workflow Clarity	A clear five-step sequence (load reference, interpret, present for confirmation, execute, report) includes an explicit user-confirmation checkpoint in Step 3, and the script performs strict filter validation.	3 / 3
Progressive Disclosure	Bundle files exist and are signaled (Step 1 `cat references/...` and a Resources section), but substantial inline content (the ~50-row mapping table and six recipes) that belongs in the reference file is kept in SKILL.md, leaving structure present but not cleanly split.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 well-constructed: it states a concrete capability, provides explicit bilingual triggers covering both what and when, and occupies a distinct niche. Its only minor weakness is a slightly narrow action list, which keeps specificity at the second anchor rather than the top.

Dimension	Reasoning	Score
Specificity	"Build and open FinViz screener URLs from natural language requests" names two concrete actions but stops short of a comprehensive list of capabilities, matching the level-2 anchor rather than the multi-action level-3 example.	2 / 3
Completeness	It explicitly states what it does ("Build and open FinViz screener URLs") and when to use it ("Use when user wants to screen stocks..."), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Phrases like "screen stocks", "find stocks matching criteria", "filter by fundamentals or technicals", and bilingual example utterances ("高配当で成長している小型株を探したい", "Find oversold large caps with high ROE") give good coverage of natural terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The FinViz-specific niche and concrete triggers (screening, filter by fundamentals/technicals) make it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/finviz-screener/SKILL.md
Commit: 62a1635

Reviewed: 5 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.