Claude Skills by vamseeachanta

"Post-processing pipeline for document extraction \u2014 tables to CSV,\

'Repeatable workflow for domain documentation research WRKs: search for

"Orchestrate the 7-phase document indexing pipeline (A\u2192G) for the 1M+ document corpus. Use when running\

Scan and catalog document collections with metadata extraction, categorization,

Build complete document knowledge bases with PDF text extraction, OCR

Comprehensive Word document toolkit for reading, creating, and editing

Build searchable knowledge bases from document collections (PDFs, Word,

Convert Markdown documents with YAML frontmatter into styled, print-ready PDFs using Chrome headless.

"Comprehensive PDF manipulation toolkit. For batch/bulk extraction (1K+\

Memory-efficient PDF processing library for large files exceeding 100MB and 1000 pages

Sub-skill of pdf: pdftotext (Poppler) (+2).

"Extract text from PDF files with intelligent chunking and metadata preservation.\

Sub-skill of pdf-text-extractor: Readability Classification.

Read, extract, edit, and manipulate PDF documents including table extraction, page manipulation, fillable forms, and comments.

PowerPoint presentation toolkit for creating new presentations, editing

Build Retrieval-Augmented Generation (RAG) Q&A systems with Claude or

Setup vector embeddings and semantic search for document collections.

Excel spreadsheet toolkit for creating, reading, and manipulating .xlsx

"Surface SPECIFIC FILES on the shared drives (/mnt/ace, /mnt/dde) relevant

Proactively surface what DATA the ecosystem already has for an engineering domain — before starting analysis, points to the consolidated data-source catalog, any latent ACE_SHARE project precedent, and the domain-database issue that curates it. Use when work touches an engineering domain (riser, mooring, pipeline, structural/FFS, naval-arch/hydro, metocean, materials, production, geotech, drilling, CAD/sim, or financial/asset), when someone asks 'do we have data for X', 'where do we get X dat...

Analyze drilling performance and metrics using API 12-digit well numbering

Extract and process BSEE (Bureau of Safety and Environmental Enforcement)

Perform advanced economic sensitivity analysis for oil & gas investments

Interactive visualization for oil and gas production data analysis using Plotly dashboards

Perform offshore field development economic analysis with NPV, MIRR,

Deepwater field-specific analysis for major Gulf of Mexico developments

Analyze BSEE HSE (Health, Safety, Environment) incident data for risk

Collect, analyze, and report marine safety incident data from 7 global

Metocean data workflows — fetching, statistics, and visualization

Fetch real-time and historical metocean data from NDBC, CO-OPS, Open-Meteo,

Statistical analysis of metocean data including extreme value analysis,

Create interactive metocean visualizations including time series plots,

Perform NPV analysis and economic evaluation for oil & gas assets. Use

Forecast oil & gas well production using decline curve analysis. Use

Extract and process Norwegian Petroleum Directorate field and production

Web scraping workflows for energy data collection from BSEE and BOEM

Create interactive well production dashboards with real-time monitoring,

Convert OrcaFlex .dat binary model files to enriched YAML fixtures using worldenergydata public databases (vessel fleet, riser components, pipe schedules). All stages run on licensed-win-1. Output committed to digitalmodel as test fixtures.

Convert engineering Excel workbooks to Python code using Claude Desktop cowork on Windows. Benchmarked superior output with 24 vs 7 functions and 81 vs 53 tests for Ballymore jumper.

Convert engineering Excel workbooks to Python code using Claude Desktop cowork on Windows. Proven superior quality vs Linux openpyxl extraction (24 vs 7 functions, 81 vs 53 tests). Validated on Ballymore jumper installation analysis.

Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private ro...

Workflow for maintaining workspace-hub knowledge and learning pipelines

Port legacy MATLAB engineering code to Python through the legal deny-list gate — extract example data, audit branded names, build regression tests, and commit to nested repo correctly.

Template-based Word document generation using Jinja2 syntax. Create reports,

Automate Microsoft Office and PDF document workflows including generation,

Create and manipulate Microsoft Excel workbooks programmatically. Build

Manipulate PDF documents programmatically. Merge, split, rotate, and

Create and manipulate Microsoft Word documents programmatically. Build

Create and manipulate PowerPoint presentations programmatically. Build

"Convert Excel calculation spreadsheets to Python code \u2014 extract\