Personal skill collection with 23 specialized skills for PhD research, finance, real estate, AI/ML, and Python development. Features progressive disclosure architecture for optimized token usage.
**Arguments:** $ARGUMENTS
> Reference for: Common Ground
> Reference for: Common Ground
> Reference for: Common Ground
Two-phase context guidance audit — read skill, audit with subagents, remediate, delete review folder
Build discounted cash flow (DCF) valuation models in Excel specifically for commercial real estate (CRE). Use when creating CRE acquisition underwriting models, property-level DCF workbooks, NOI projections, rent roll buildouts, debt schedules, or IRR/equity-multiple return analyses in Excel or ExcelJS. Covers all CRE property types: office, retail, industrial, multifamily, mixed-use, hotel. Trigger on: 'CRE excel model', 'build underwriting model', 'property DCF excel', 'NOI projection spreadsheet', 'rent roll model', 'IRR excel', 'acquisition model', 'CRE waterfall', 'cap rate model'.
Use when analyzing commercial properties, creating investment memorandums, performing DCF/IRR analysis, evaluating REIT investments, or developing CRE business plans with institutional-grade underwriting standards.
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis.
Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke for async SQLAlchemy, JWT authentication, WebSockets, OpenAPI documentation.
Use when the user asks to create, draft, save, revise, or improve a Codex Goal, GOAL.md, goal file, persistent objective, completion contract, or long-running Codex work objective. This skill must be used before inventing or saving any goal for Codex.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub agentic-assets/agent-skillsBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
🎯 23 Skills • 🚀 9 Workflows • 🧠 Context Engineering • 📖 Progressive Disclosure
This is a personal collection of specialized Claude Code skills organized around PhD research, finance, real estate, and AI/ML development:
# Copy skills to Claude Code directory
cp -r ./skills/* ~/.claude/skills/
Skills activate automatically based on your requests:
# Python API Development
"Build a FastAPI endpoint with async SQLAlchemy"
→ Activates: fastapi-expert
# Data Analysis
"Clean this DataFrame and create summary statistics"
→ Activates: pandas-pro
# Research
"Generate LaTeX tables from PyFixest models"
→ Activates: pyfixest-latex
# Debugging
"Help me debug this stack trace"
→ Activates: debugging-wizard
# Context Engineering
"Run a two-phase context guidance audit on this repo"
→ Activates: context-guidance-audit
# Context Engineering
"Audit my CLAUDE.md and agent context setup"
→ Activates: context-engineering
23 specialized skills organized by domain:
Literature review and idea-screening starter kit for Claude Code, powered by the Corbis MCP. Bundles the repo's six research skills — literature review, positioning, landscape figures, idea generation, idea screening, and citation verification — alongside six slash commands and a paper-reader subagent.
Literature review and idea-screening starter kit for Claude Code, powered by the Corbis MCP. Bundles the repo's six research skills — literature review, positioning, landscape figures, idea generation, idea screening, and citation verification — alongside six slash commands and a paper-reader subagent.
Self-documenting, self-improving framework for analytical repositories
Autonomous research loops with 10 commands. Generalizes Karpathy's autoresearch loop to any domain with mechanical evaluation, overnight persistence, and zero dependencies.
🔬 Data Scientist — Data Scientist + Machine Learning Specialist
Structured deep research methodology for Claude Code — query decomposition, parallel web research with source verification, hallucination prevention, and synthesis into well-sourced documents
Oh My Paper research harness: memory system, Codex delegation, and pipeline commands for academic research projects.