Agentic-Assets

Multi-phase, subagent-driven deep audit and remediation of codebase guidance (root agent instructions, docs, module context files, skills/agents references, task routing). Phase 1 subagents write verified findings only; Phase 2 subagents verify and fix guidance. Use when the user asks to audit, refresh, or fix agent context, CLAUDE.md or AGENTS.md drift, stale docs, contradictory rules, or run a context-guidance deep dive.

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.

Use when the user wants to create, brainstorm, draft, or post social media content for X (Twitter), LinkedIn, or Instagram. This includes generating post ideas, writing captions or threads, adapting content across platforms, planning a posting cadence, or navigating to a platform's posting interface via browser tools. Trigger whenever the user mentions social media, posting, tweets, LinkedIn posts, Instagram captions, content calendars, thought leadership posts, or sharing research/business updates online — even if they just say something like 'I should post about this' or 'help me share this.'

Build Discounted Cash Flow (DCF) valuation models for commercial real estate (CRE). Calculate NOI-based cash flows, levered and unlevered IRR, equity multiple, DSCR, debt yield, exit cap rate reversion, and sensitivity analysis. Use for office, retail, industrial, multifamily, mixed-use, and hotel properties. Trigger on: CRE valuation, property DCF, NOI projection, cap rate analysis, IRR analysis, real estate investment return, acquisition underwriting, hold-period analysis, CRE sensitivity table.

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'.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when auditing, optimizing, or architecting the AI agent context layer (CLAUDE.md files, hooks, slash commands, skills, IDE rules) for any codebase, bootstrapping context engineering from scratch, diagnosing agent underperformance, or when the user mentions CLAUDE.md strategy, context quality, agent instructions, or context architecture.

Use when building n8n workflows, configuring nodes, setting up triggers, implementing data transformations, or integrating AI agents into automation workflows.

This skill should be used when the user asks to "help me get to inbox zero", "build a repeatable triage program", "coordinate a multi-week cleanup across mailboxes", "set up sustained email habits", or "I'm drowning in email" and needs a multi-week umbrella program coordinating triage, taxonomy, cleanup, drafting, and analytics, not a single pass. Uses get_inbox_overview, search_emails, move_email, update_email_status, manage_trash, and get_statistics; routes single-purpose work to the narrow sibling skill instead. Do NOT use for tooling-only onboarding (see apple-mail-operator), a single 5–10 minute read-first scan (inbox-triage), a one-shot bulk move/archive/delete campaign (email-archive-cleanup), folder-architecture redesign without execution (mailbox-taxonomy), Mail filter prose only (mail-rules-advisor), or drafting voice capture (email-style-profile before email-drafting).

This skill should be used when the user asks "how does this Mail MCP work", "which tool should I use", "why is Mail slow", "set up Mail for the assistant", "list my accounts/mailboxes", "find an email quickly", or needs safe read/search navigation in Apple Mail with the MCP. Uses list_accounts, list_mailboxes, get_inbox_overview, list_inbox_emails, search_emails, get_email_by_id, and get_email_thread. Do NOT use for sustained inbox-zero programs (see email-management), a 5–10 minute triage ritual (see inbox-triage), or drafting mail (see email-drafting).

This skill should be used when the user asks to "draft an email", "reply to this message", "forward this thread", "verify my draft", or needs compose workflows in Apple Mail with draft-safe defaults. Covers compose_email, reply_to_email, forward_email, create_rich_email_draft, manage_drafts, verify_draft, and verify_drafts with exact message ids for replies, standalone-draft guardrails, native reply defaults, signatures, and post-draft verification. Do NOT use for inbox triage (inbox-triage), Mail MCP setup (apple-mail-operator), folder taxonomy (mailbox-taxonomy), Mail rules (mail-rules-advisor), staged bulk moves (email-archive-cleanup), or attachment extraction (email-attachments).

This skill should be used when the user asks to "check my email", "what came in today", "what needs my attention", "morning email scan", "triage my inbox", "draft responses to recent email", "anything urgent in my mail", or wants a fast read-only pass over Apple Mail without full inbox-zero cleanup. Uses get_inbox_overview, get_needs_response, get_awaiting_reply, list_inbox_emails, and get_email_by_id. Work newest mail first in batches of 3 to 5 (see recent-first-triage.md). Do NOT use for deep folder reorganization (mailbox-taxonomy), bulk archive or delete campaigns (email-archive-cleanup), proposing Mail filter text (mail-rules-advisor), MCP setup (apple-mail-operator), or composing replies; use email-drafting after this scan.

This skill should be used when the user asks to "archive old mail safely", "move everything from X sender" (screens out human correspondents unless confidently spam), "clear newsletters", "bulk mark read after export", "preview what would move with dry_run=True", or run staged cleanup campaigns. Uses search_emails, move_email(dry_run=True) preview → execute, update_email_status, export_emails, manage_trash (max_deletes cap), synchronize_account, and get_statistics when measuring progress. Do NOT use for taxonomy design sessions without execution (mailbox-taxonomy), proposing Mail filter rules copy (mail-rules-advisor only), drafting mail (email-drafting), or the 5-minute triage skim (inbox-triage).

This skill should be used when the user asks "what's on my calendar", "am I free Thursday", "add an event", "block time for this", "clean up my test calendar", or "which calendar tool should I use". Covers bounded reads, timezone handling, safe event creation, ID-first updates and deletes, and calendar management with list_calendars, list_events, create_event, delete_events, and manage_calendars. Do NOT use for coordinating meetings with other people or invitation workflows (see meeting-scheduler), and do NOT use for email work (see apple-mail-operator).

This skill should be used when the user asks "find a time for us", "schedule a meeting with", "when am I free next week", "send a calendar invite", or "does 3pm work in Auburn time". Runs the find-slot workflow with check_availability, then conflict-checked create_event, then attendee or invitation handling within platform limits, with list_events and compose_email as support tools. Do NOT use for personal time blocking or calendar cleanup (see calendar-operator), and do NOT use for drafting ordinary email replies (see email-drafting).

This skill should be used when the user asks to "list attachments on messages about X", "save this PDF from email", "which invoices have ZIP files", or needs disk-safe attachment extraction. Uses bounded search_emails (has_attachments filters) to collect message_ids first, then list_email_attachments, save_email_attachment, get_email_by_id for confirmation, and optionally export_emails for bundles. Discovery-only; pass subject_keyword to search_emails when ids are unknown; never pass subject_keyword to list_email_attachments or save_email_attachment. Do NOT use when the real goal is writing responses (email-drafting), diagnosing slow accounts (apple-mail-operator), bulk deleting mail (email-archive-cleanup), or designing folder hierarchies (mailbox-taxonomy).

Screen and refine research ideas in corporate finance, investments, asset pricing, and real estate. Use for brainstorming, novelty checks, contribution framing, and journal-fit triage.

Generate figures that visualize patterns in an academic literature: publication trends, citation landmarks, journal distributions, thematic evolution, method timelines, and coverage gap maps. Uses Corbis search data and Python/matplotlib.

Map the closest literature and sharpen contribution claims for finance or real-estate papers. Use for related-literature sections, novelty maps, and closest-paper comparisons.

Write a comprehensive, structured literature review on a topic. Searches the literature via Corbis, organizes into thematic strands, writes synthesized prose (not paper-by-paper enumeration), and outputs as Markdown, LaTeX section, or standalone LaTeX document with proper BibTeX citations.

Generate novel research ideas in finance and real estate using structured heuristic lenses with internal rejection filtering. Produces a curated Idea Menu of survivors, not a brainstorming list.

Audit citations in LaTeX files -- check all \cite keys exist in .bib and verify via literature search

Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project. Use when you need a from-scratch macOS app layout, SwiftPM targets/resources, a custom .app bundle assembly script, or signing/notarization/appcast steps outside Xcode.