← Back to list
ohlcv-processing Checked
Market data preparation including OHLCV resampling, gap handling, anomaly detection, normalizatio…
8.5Overall 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 "ohlcv-processing" skill by following the instructions at https://skill123.me/install/ohlcv-processing.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/ohlcv-processing.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 · 22 KBAbout this skill
Overview
Market data preparation including OHLCV resampling, gap handling, anomaly detection, normalization, and multi-source merging
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/ohlcv-processing
Score breakdown
Trigger
6.0
Description enumerates pipeline stages with good keyword coverage (resampling, gap handling, anomaly detection, normalization, merging); no Use-when or boundary statement, no trigger variants.
Structure
8.0
Two well-scoped references (data quality taxonomy, resampling guide) plus two scripts; 388-line SKILL.md carries many inline function definitions duplicating script content; Files section annotates contents.
Workflow
8.8
Excellent pipeline design with ordered stages, explicit guards (missing-column ValueError, max_gap fill limit, impossible-candle constraints), and a quality_report verification loop; --demo mode generates synthetic data with intentional anomalies to test the detector — a genuine self-verification design.
Content
9.0
Code-forward, imperative, every function copy-runnable with typed args and docstrings.
Engineering
10.0
Frontmatter valid; shebangs, dependencies, and env vars documented; all referenced paths exist.
Security
10.0
6.0 manifest: sole network destination is https://public-api.birdeye.so (official public market-data API, declared in script header, opt-in via --token); BIRDEYE_API_KEY from env only; no file writes beyond stdout, no credentials, no persistence. Capabilities match declared scope. No advice content, so no disclaimer needed.
Complete market-data preparation pipeline: validation (impossible-candle checks), gap handling with fill limits, composite anomaly flagging, correct OHLCV resample rules, normalization, and multi-source merging with conflict resolution. Scripts default to synthetic demo data containing intentional anomalies for self-testing. Deductions: description lacks When/When-Not; SKILL.md duplicates many function bodies that also live in scripts.