← Back to list
pandas-ta Checked
Technical analysis with 130+ indicators using pandas-ta for crypto market data
8.2Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "pandas-ta" skill by following the instructions at https://skill123.me/install/pandas-ta.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/pandas-ta.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 24 KBAbout this skill
Overview
Technical analysis with 130+ indicators using pandas-ta for crypto market data
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/pandas-ta
Score breakdown
Trigger
5.5
Description states What (130+ indicators, pandas-ta, crypto) with good topic keywords but no Use-when, no boundary, no trigger-phrase variants.
Structure
8.7
292-line SKILL.md with three well-scoped references and two scripts, correctly classified and annotated; minor duplication between SKILL.md indicator tables and indicator_guide.md.
Workflow
8.4
Strong task design: copy-runnable indicator calls, missing-data handling code, named Strategy patterns, timeframe selection table, and pitfalls reference covering warmup NaN, look-ahead, and wash-trading traps; scripts offer demo mode (verification without network) and live mode; error paths in fetch (HTTPStatusError/RequestError handling).
Content
9.0
Concise imperative style; every snippet has concrete parameters; consistent tables.
Engineering
10.0
Frontmatter valid; shebangs present; dependencies and env vars (BIRDEYE_API_KEY, TOKEN_MINT) documented in script headers; all paths exist.
Security
9.0
6.0 manifest — network destination: https://public-api.birdeye.so only (official public market-data API, declared in usage); sends only API key header and token mint query (auth, not local data); no file writes, no credential-file reads, no persistence. Capabilities match declared scope. API key read from env, never hardcoded. Minor: no not-financial-advice disclaimer.
Well-executed tool-wrapper skill for pandas-ta technical analysis on crypto OHLCV data: indicator catalog with calls and signal thresholds, crypto-specific parameter adjustments, named strategy patterns, and an excellent common-pitfalls reference. Scripts default to synthetic demo mode with opt-in --live fetching from the official Birdeye API. Deductions: thin description (no When/When-Not); no financial disclaimer for signal-generating guidance.