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

90%

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

82%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.

A well-built skill body: fully executable script invocations that match the real bundle, a clearly sequenced workflow with a user-confirmation checkpoint, and appropriate one-level-deep externalization of the 142+ code reference. The main improvement opportunities are trimming the recipe tables' redundant per-filter explanations and adding a brief error-recovery note for invalid filter codes.

Suggestions

Compress the recipe sections: drop the per-filter 'Purpose' tables (each filter's meaning is already in the concept-mapping table or the external reference) and keep just the filter string, view, and the refinement tip.

Add one line to Step 4 covering the script's validation failure path (e.g., what the error output looks like and to re-check codes against references/finviz_screener_filters.md), which would close the workflow-clarity gap.

Dimension	Reasoning	Score
Conciseness	The body is dense with FinViz-specific knowledge (filter codes, NL mappings) Claude does not already know, and it never explains generic concepts, but the 6 recipe tables restate per-filter purposes already implied by the mapping table and could be trimmed — matching 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean 5.	4 / 5
Actionability	Commands are copy-paste ready and verified against the actual script — 'python3 scripts/open_finviz_screener.py --filters "..." --view overview' plus theme-only and combined variants — with every argument documented (matching the script's argparse) and the {from}to{to} range syntax explicitly demonstrated; this matches the fully-executable top anchor.	5 / 5
Workflow Clarity	The 5-step workflow (load reference → interpret → present filters → execute → report) is clearly sequenced with an explicit user-confirmation checkpoint in Step 3, but there is no guidance for recovering from a rejected/invalid filter code (the script's validation failure path), which keeps it at 'clear sequence with most checkpoints present; minor validation gaps' instead of 5.	4 / 5
Progressive Disclosure	Structure follows the anchor-4 pattern of 'a few key examples inline, bulk in separate file': the ~50-row common mapping table lives inline as the quick reference while the full 1988-line filter list is correctly externalized one level deep in references/finviz_screener_filters.md, and the script is in scripts/; both referenced files exist. Not 5 because the inline 50-row table is substantial enough that it sits on the boundary of content that could itself be externalized.	4 / 5
	Total	17 / 20 Passed

Description

95%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: concrete third-person actions, an explicit 'Use when...' clause with natural trigger terms, and concrete example utterances in both Japanese and English. The only weakness is that the 'what' side stops at build/open and does not mention validation or view/sort selection, leaving a minor specificity gap.

Dimension	Reasoning	Score
Specificity	Concrete actions are stated — "Build and open FinViz screener URLs from natural language requests" plus filtering "by fundamentals or technicals" — but coverage of what the skill does (translation, validation, view/sort selection) is incomplete, matching the anchor 'several specific actions; minor gaps in coverage' rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both what ("Build and open FinViz screener URLs from natural language requests") and when ("Use when user wants to screen stocks... or asks to open FinViz with specific conditions") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural phrases users would actually say are covered with synonyms in two languages — "screen stocks", "find stocks matching criteria", "filter by fundamentals or technicals", "open FinViz", plus concrete example utterances like "Find oversold large caps with high ROE" — which matches the comprehensive-synonyms anchor; not 4 because no common variation is missing.	5 / 5
Distinctiveness Conflict Risk	FinViz is a named, specific tool with distinct triggers (stock screening via FinViz), giving it a clear niche with minimal conflict risk against generic analysis or charting skills; the bilingual examples further narrow the trigger surface.	5 / 5
	Total	19 / 20 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: eab8d5c

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.