Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

finviz-screener

skill · tradermonty/claude-trading-skillsMIT licenceAudited 13 Nov 2026 · source 3241f6fce388

★ 3,821pushed today
✓SAFEGrade B · 89/100 · 13 Nov 2026 · 3241f6f
3,821repo stars · whole tradermonty/claude-trading-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 3241f6fce388 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 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…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “finviz-screener (tradermonty/claude-trading-skills)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/tradermonty/finviz-screener

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN1
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

MEDIUMInformation disclosuredisclose.log_secret · scripts/open_finviz_screener.py:164
F-12 Information disclosureCWE-209 · CWE-532Layer L1
print(f"Warning: Unknown filter prefix '…' in '…'.", file=sys.stderr)
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 3241f6fce388 · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishertradermonty GitHub userOwner of the repository this skill is read from
  • Source foldertradermonty/claude-trading-skills/skills/finviz-screenerThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict3241f6fce388A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 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…

---
name: finviz-screener
description: 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").
---

# FinViz Screener

## Overview

Translate natural-language stock screening requests into FinViz screener filter codes, build the URL, and open it in Chrome. No API key required for public screener; FINVIZ Elite is auto-detected from `$FINVIZ_API_KEY` for enhanced functionality.

**Key Features:**
- Natural language → filter code mapping (Japanese + English)
- URL construction with view type and sort order selection
- Elite/Public auto-detection (environment variable or explicit flag)
- Chrome-first browser opening with OS-appropriate fallbacks
- Strict filter validation to prevent URL injection

---

## When to Use This Skill

**Explicit Triggers:**
- "高配当で成長している小型株を探したい"
- "Find oversold large caps near 52-week lows"
- "テクノロジーセクターの割安株をスクリーニングしたい"
- "Screen for stocks with insider buying"
- "FinVizでブレイクアウト候補を表示して"
- "Show me high-growth small caps on FinViz"
- "配当利回り5%以上でROE15%以上の銘柄を探して"

**Implicit Triggers:**
- User describes stock screening criteria using fundamental or technical terms
- User mentions FinViz screener or stock filtering
- User asks to find stocks matching specific financial characteristics

**When NOT to Use:**
- Deep fundamental analysis of a specific stock (use us-stock-analysis)
- Portfolio review with holdings (use portfolio-manager)
- Chart pattern analysis on images (use technical-analyst)
- Earnings-based screening (use earnings-trade-analyzer or pead-screener)

---

## Prerequisites

- **FINVIZ Elite API key:** Optional. The public screener works without a key. Set `FINVIZ_API_KEY` to enable Elite mode, or pass `--elite` to force it.
- **Other API keys:** None used.
- **Python:** 3.9+ with the standard library only (see `requirements.txt`).
- **Browser:** Chrome is used first to open the screener URL. Use `--url-only` to print the URL instead.

---

## Workflow

### Step 1: Load Filter Reference

Read the filter knowledge base:

```bash
cat references/finviz_screener_filters.md
```

### Step 2: Interpret User Request

Map the user's natural-language request to FinViz filter codes. Use the Common Concept Mapping table below for quick translation, and reference the full filter list for precise code selection.

**Note:** For range criteria (e.g., "dividend 3-8%", "P/E between 10 and 20"), use the `{from}to{to}` range syntax as a single filter token (e.g., `fa_div_3to8`, `fa_pe_10to20`) instead of combining separate `_o` and `_u` filters.

**Common Concept Mapping:**

| User Concept (EN) | User Concept (JP) | Filter Codes |
|---|---|---|
| High dividend | 高配当 | `fa_div_o3` or `fa_div_o5` |
| Small cap | 小型株 | `cap_small` |
| Mid cap | 中型株 | `cap_mid` |
| Large cap | 大型株 | `cap_large` |
| Mega cap | 超大型株 | `cap_mega` |
| Value / cheap | 割安 | `fa_pe_u20,fa_pb_u2` |
| Growth stock | 成長株 | `fa_epsqoq_o25,fa_salesqoq_o15` |
| Oversold | 売られすぎ | `ta_rsi_os30` |
| Overbought | 買われすぎ | `ta_rsi_ob70` |
| Near 52W high | 52週高値付近 | `ta_highlow52w_b0to5h` |
| Near 52W low | 52週安値付近 | `ta_highlow52w_a0to5l` |
| Breakout | ブレイクアウト | `ta_highlow52w_b0to5h,sh_relvol_o1.5` |
| Technology | テクノロジー | `sec_technology` |
| Healthcare | ヘルスケア | `sec_healthcare` |
| Energy | エネルギー | `sec_energy` |
| Financial | 金融 | `sec_financial` |
| Semiconductors | 半導体 | `ind_semiconductors` |
| Biotechnology | バイオテク | `ind_biotechnology` |
| US stocks | 米国株 | `geo_usa` |
| Profitable | 黒字 | `fa_pe_profitable` |
| High ROE | 高ROE | `fa_roe_o15` or `fa_roe_o20` |
| Low debt | 低負債 | `fa_debteq_u0.5` |
| Insider buying | インサイダー買い | `sh_insidertrans_verypos` |
| Short squeeze | ショートスクイーズ | `sh_short_o20,sh_relvol_o2` |
| Dividend growth | 増配 | `fa_divgrowth_3yo10` |
| Deep value | ディープバリュー | `fa_pb_u1,fa_pe_u10` |
| Momentum | モメンタム | `ta_perf_13wup,ta_sma50_pa,ta_sma200_pa` |
| Defensive | ディフェンシブ | `ta_beta_u0.5` or `sec_utilities,sec_consumerdefensive` |
| Liquid / high volume | 高出来高 | `sh_avgvol_o500` or `sh_avgvol_o1000` |
| Pullback from high | 高値からの押し目 | `ta_highlow52w_10to30-bhx` |
| Near 52W low reversal | 安値圏リバーサル | `ta_highlow52w_10to30-alx` |
| Fallen angel | 急落後反発 | `ta_highlow52w_b20to30h,ta_rsi_os40` |
| AI theme | AIテーマ | `--themes "artificialintelligence"` |
| Cybersecurity theme | サイバーセキュリティ | `--themes "cybersecurity"` |
| AI + Cybersecurity | AI&サイバーセキュリティ | `--themes "artificialintelligence,cybersecurity"` |
| AI Cloud sub-theme | AIクラウド | `--subthemes "aicloud"` |
| AI Compute sub-theme | AI半導体 | `--subthemes "aicompute"` |
| Yield 3-8% (trap excluded) | 配当3-8%(トラップ除外)| `fa_div_3to8` |
| Mid-range P/E | 適正PER帯 | `fa_pe_10to20` |
| EV undervalued | EV割安 | `fa_evebitda_u10` |
| Earnings next week | 来週決算 | `earningsdate_nextweek` |
| IPO recent | 直近IPO | `ipodate_thismonth` |
| Target price above | 目標株価以上 | `targetprice_a20` |
| Recent news | 最新ニュースあり | `news_date_today` |
| High institutional | 機関保有率高 | `sh_instown_o60` |
| Low float | 浮動株少 | `sh_float_u20` |
| Near all-time high | 史上最高値付近 | `ta_alltime_b0to5h` |
| High ATR | 高ボラティリティ | `ta_averagetruerange_o1.5` |

### Step 3: Present Filter Selection

Before executing, present the selected filters in a table for user confirmation:

```markdown
| Type | Value | Meaning |
|---|---|---|
| Theme | artificialintelligence | Artificial Intelligence |
| Sub-theme | aicloud | AI - Cloud & Infrastructure |
| Filter | cap_small | Small Cap ($300M–$2B) |
| Filter | fa_div_o3 | Dividend Yield > 3% |
| Filter | fa_pe_u20 | P/E < 20 |
| Filter | geo_usa | USA |

View: Overview (v=111)
Mode: Public / Elite (auto-detected)
```

Ask the user to confirm or adjust before proceeding.

### Step 4: Execute Script

Run the screener script to build the URL and open Chrome:

```bash
p

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 3241f6f

Download folder ↗
git clone https://github.com/tradermonty/claude-trading-skills
git -C claude-trading-skills checkout 3241f6fce388

The author documents no install command, so this uses the repository directly. Our verdict covers commit 3241f6fce388 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 3241f6fce388

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/tradermonty/finviz-screener/badge.svg)](https://modelsatlas.com/skills/tradermonty/finviz-screener/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/tradermonty/finviz-screener/badge.svg)](https://modelsatlas.com/skills/tradermonty/finviz-screener/)

Questions about finviz-screener

What does the finviz-screener skill do?
Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.
Is finviz-screener safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can finviz-screener access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (3241f6fce388), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.