Text Classifier

Classify text or CSV files into preset or custom categories with optional confidence scores and batch processing, using AI-powered classification.

Security Scan

The skill mostly implements a plausible text-classifier that uses your supplied OpenAI API key and an external billing endpoint, but there are mismatches between the documentation and the code (especially about what billing data is sent) and a few undocumented environment/behavior details you should understand before installing.

Purpose & Capability

The code implements an AI text classifier that calls OpenAI and performs per-call billing to skillpay.me, which is consistent with the skill's stated purpose. Required billing environment variables (SKILL_BILLING_API_KEY, SKILL_BILLING_SKILL_ID) are used in the billing module as documented. Minor mismatch: SKILL.md claims Feishu Open ID is transmitted for billing, but the code transmits the provided license token/user_id (the validate_token() function passes the license token to charge_user()).

Instruction Scope

SKILL.md instructs users to run the web app/CLI and provide an OpenAI API key and license token; the code does exactly that and sends text to api.openai.com (expected). However SKILL.md asserts "No other data is transmitted to third parties", while the billing module posts the user_id (license token) and billing info to skillpay.me. The doc specifically says a Feishu Open ID is sent for billing, but the code sends whatever token string the user supplies — this is an inconsistency and a privacy concern if you assume only a benign identifier is shared.

Install Mechanism

There is no packaged install spec; the repo includes requirements.txt and Python scripts and expects the user to pip install dependencies and run the app. This is a normal, low-risk install pattern (no remote arbitrary binary downloads). Requirements include openai, requests, pandas, flask and related libs — typical for this functionality.

Credentials

Declared required env vars (SKILL_BILLING_API_KEY and SKILL_BILLING_SKILL_ID) match the billing module. The web app also reads SECRET_KEY from the environment (used for Flask config) but SKILL.md doesn't document it — undocumented env var. The skill does not request unrelated cloud credentials. Users must supply an OpenAI API key at runtime (via CLI or web form), which is expected for an OpenAI-backed classifier.

Persistence & Privilege

The skill does not request permanent or global privileges (always:false). It writes history to /tmp/text-classifier/ per config, which matches SKILL.md's claim about local history storage. It does not modify other skills or system settings.

What to consider before installing

This skill largely does what it claims (it classifies text using OpenAI and can bill per-call via skillpay.me), but there are a few issues to consider before installing: - Data exfiltration: Classification text is sent to OpenAI (you provide the API key). Additionally, billing calls are made to https://skillpay.me; the code sends the user identifier you provide (the license token string) to that endpoint. SKILL.md's statement that only a Feishu Open ID is sent is inaccurate; treat any token you enter as potentially transmitted. - Undocumented env var: The Flask SECRET_KEY is read from the environment but not listed in SKILL.md; set this explicitly if you run the web app to avoid default secrets. - Billing behavior: If SKILL_BILLING_API_KEY/SKILL_BILLING_SKILL_ID are unset the code runs in "dev mode" (no billing). The billing call also treats exceptions as success (fallback to FREE), so network failures may silently bypass billing. - If you will classify sensitive or regulated data, avoid using this skill until you confirm its privacy guarantees: either do offline testing, review the code locally, or run it on an isolated machine/network where outgoing connections are controlled. If you decide to use it, avoid entering highly sensitive tokens/identifiers into the license field unless you trust skillpay.me and understand what exactly is being transmitted. - To reduce risk: run the code locally, inspect/modify billing.charge_user() if you want different behavior, and set a custom SECRET_KEY. Monitor outbound connections (to api.openai.com and skillpay.me) during use. Given the documentation/code inconsistencies around what billing identifies are shared and the undocumented SECRET_KEY usage, I rate this skill as suspicious (not clearly malicious, but not fully coherent).

SKILL.md - Text Classifier

Upload text or CSV — AI automatically classifies content and returns structured labels with confidence scores.

Slug: text-classifier

Tiered Features

Feature	FREE	PRO
Text input	✅	✅
File upload (TXT/CSV)	❌	✅
Preset classifiers	3	Unlimited
Custom labels	❌	✅
Confidence score	❌	✅
Batch processing	❌	✅ (up to 5,000)
History retention	❌	✅ (365 days)
Daily classifications	20	Unlimited

Pricing

Per-call: $0.01 USDT per classification

No monthly subscription. Pay only for what you use.

Usage

Web Interface (Recommended)

cd text-classifier
pip install -r requirements.txt
python scripts/web_app.py
# Open http://localhost:5000

CLI

# Single text classification
python -m scripts.classifier --text "This product is great" --classifier "Sentiment Classification" --api-key "sk-..."

# Batch CSV classification
python -m scripts.classifier --file data.csv --classifier "Sentiment Classification" --api-key "sk-..." --output csv --output-path results.csv

# Custom labels
python -m scripts.classifier --text "Urgent issue" --custom-labels "High,Medium,Low" --custom-prompt "Classify priority" --api-key "sk-..."

Python API

from scripts.classifier import classify_text, validate_token

# Token validation
tier = validate_token("PRO-xxxx")
print(f"Tier: {tier}")

# Single classification
result = classify_text(
    text="This product is excellent",
    classifier_name="Sentiment Classification",
    api_key="sk-...",
    show_confidence=True
)
print(result)
# {'label': 'Positive', 'confidence': 0.85, 'raw': 'Positive', ...}

Preset Classifiers

• Intent Classification: Inquiry / Complaint / Refund / Cooperation
• Sentiment Classification: Positive / Neutral / Negative
• Industry Classification: Finance / Healthcare / Education / Retail / Manufacturing
• Risk Classification: Compliant / Violation / Suspicious
• Priority Classification: High / Medium / Low
• Content Classification: News / Advertisement / UGC / Spam

Required Environment Variables

SKILL_BILLING_API_KEY   # Your SkillPay Builder API Key
SKILL_BILLING_SKILL_ID  # Skill slug: text-classifier

Set these in your runtime environment. Without them, the tool runs in Dev Mode (FREE tier, no billing).

Billing

This skill uses SkillPay (skillpay.me) for per-call billing at $0.01 USDT per classification.

• Your Feishu User ID (Open ID) is transmitted to skillpay.me exclusively for billing purposes
• No other data is transmitted to third parties
• Billing occurs at the start of each classification (after API key validation)
• Dev Mode (SKILL_BILLING_API_KEY not set): FULL FREE USAGE — no API key required, no billing

Security Notes

• LLM Execution: All AI classification runs via OpenAI API you configure
• Data Isolation: Classification history is stored locally in /tmp/text-classifier/ — no data leaves your environment
• SQL Safety: Not applicable (no database queries in this skill)
• Path Isolation: All writes go to /tmp/ — no home directory access

Dependencies

requests>=2.28.0
pandas>=2.0.0
openpyxl>=3.0.0
flask>=3.0.0