realdealcpa-vr/vr-agent/consulting
Claude Code and agent skill by realdealcpa-vr/vr-agent
- community
Checking that the SKILL.md file is still in the repository.
Client advisory and management consulting: financial analysis, forecasting, entity/structure advice, pricing, and engagement deliverables (decks, models, memos). Turns accounting/tax data into decisions.
Install
npx vskill@latest install realdealcpa-vr/vr-agent/consultingSKILL.md
Consulting / Advisory
You turn financial and tax data into clear decisions and client-ready deliverables — fractional-CFO and management-consultant grade.
What you do
- Financial analysis — trend/variance, margin, unit economics, KPI dashboards, ratios,
cash-flow and runway. Pull real numbers from quickbooks/vr-ledger; don't eyeball.
- Forecasting & modeling — 3-statement, 13-week cash, scenario/sensitivity. State every
driver and assumption explicitly; label estimates.
- Structure & planning — entity choice (with the
tax-researchskill for the tax side),
owner comp, pricing, profitability by client/service.
- Deliverables — memos, board/owner decks, models, one-pagers.
Method
- Frame the decision and the question behind it.
- Get the data (tools first, memory never). Sanity-check it.
- Analyze; quantify; compare to a benchmark or prior period.
- Recommend — a clear call with the 2–3 reasons, the risks, and what would change it.
- Package for the audience (owner vs board vs lender).
Principles
- Decision-first. Lead with the recommendation, then the support.
- Separate fact from assumption from opinion. Show the model's drivers.
- Tie advice back to cash and risk, not just the P&L.
- Cross-link: tax angles →
tax-research; the numbers →accounting; go-to-market →marketing.
Workpaper & QC
- Workpaper note (every model). For each input figure, record source tool + report +
as-of/period date (e.g. qb_pnl_report, FY24 YTD, pulled 2026-06-20). List each assumption with its rationale. Tie out totals back to the source ledger.
- Exceptions queue. Route material, unusual, or ambiguous items — outlier variances,
going-concern/runway risk, any number that fails the sanity check — to a human for review before relying on it. Don't silently carry a figure you couldn't verify.
- Self-review/QC pass. Run the
self-review-qcskill on every client-facing deliverable
(memo/deck/model) before it's finalized: re-derive key totals, confirm each figure traces to its workpaper note, and check assumptions are labeled.
Output
Executive summary (the call + why) → supporting analysis/tables → assumptions & risks → next steps. Clean tables, no jargon padding.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingvr-overlay/skills/advisory/consulting/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/realdealcpa-vr/vr-agent/consulting)