Data

AI Data Engineering builds data infrastructure for AI and ML systems, including RAG pipelines, embeddings, feature stores, and orchestration. Use it when preparing data for retrieval, semantic search, or production model serving.

Creating Dashboards builds analytics interfaces with KPI cards, charts, tables, filters, and real-time updates. Use it for business intelligence, monitoring, or reporting screens with coordinated data displays.

Data Architecture guides decisions for modern data platforms, including storage patterns, modeling approaches, lakehouse formats, data mesh, medallion layers, and governance. Use it when designing or modernizing analytics platforms and choosing architecture tradeoffs.

Feature Prioritization applies RICE, MoSCoW, Kano, and related scoring frameworks to rank features and initiatives. Use it when deciding what to build, defer, or document for a roadmap.

Fig Mirror mirrors the visual style of a reference paper figure onto the user's own data. It preprocesses a screenshot, runs a Drawer/Reviewer loop, and outputs a camera-ready PDF plus an editable matplotlib script.

FigMirror transfers the visual style of a reference paper figure onto your own data and outputs matplotlib code, PNG, and PDF. Use it when you want a chart to match a paper’s aesthetic rather than just plotting data.

ArXiv Search retrieves paper metadata from arXiv keyword queries and writes normalized results to JSONL. Use it to build an initial paper set for ranking, taxonomy, or citation workflows, or to import and enrich offline exports.

Dedupe Rank turns a broad paper candidate pool into a deduped JSONL and a stable core set. Use it when retrieval output needs deterministic deduplication, ranking, and repeatable paper IDs.

Leaderboard shows this repo's context-cost table of the files that have pulled the most tokens into context. Use it to identify the biggest re-read offenders and suggest a fix for each.

Receipts shows a personal model-quality trend card for recent Claude Code sessions. Use it to review failure rate, edit churn, and tokens per task by model version and call out any shifts.

Analyzes self-media content data (individual pieces, series, weekly or monthly) to produce actionable reviews. Helps creators attribute performance to topics, titles, covers, openings, and structure, and decide on content strategy adjustments.

Covariance Scoring scores covariance estimates with precise's assessor panel. Use it to compare estimators out of sample or against truth, especially in high dimensions where held-out likelihood can mislead.