What does this skill do, and when should you use it?
This skill merges Perplexity Computer's 7 finance skills plus investment research with Claude Code's data science, data engineering, financial analysis, and invoice management skills into a single SKILL.md. It covers GAAP statement templates, journal entries, reconciliation, close management, variance analysis, SOX audit support, market data, DCF valuation, ETL pipelines, and ML revenue forecasting. It is essentially a large reference manual and workflow template collection rather than an executable program. The market-data sections depend on Perplexity Computer's finance_* connector tools and need replacement on other platforms. Best suited to teams wanting end-to-end finance and accounting support.
Provides fill-in-ready GAAP income statement, balance sheet, and cash flow templates; six journal-entry templates (accruals, prepaids, depreciation, payroll, ASC 606 revenue recognition, intercompany elimination) plus a month-end accrual checklist; bank and GL-to-subledger reconciliation templates; a 15-business-day close calendar with task tracker and dependency map; budget-vs-actual variance decomposition (price/volume/mix) with waterfall narrative templates; a SOX 404 control-testing workflow with PCAOB sample-size guidance and a Python sampling script; ratio benchmarks, a six-step DCF workflow, and industry-specific KPIs; the markets section calls list_external_tools / call_external_tool Perplexity connectors for live quotes, financials, and analyst estimates.
- A financial analyst organizing month-end close who needs a close calendar, JE checklists, and reconciliation templates
- An accountant preparing SOX 404 testing who needs control workpapers and PCAOB-aligned sampling methodology
- An FP&A analyst explaining budget variances to the CFO with price/volume/mix decomposition and waterfall narratives
- An investment researcher pulling company quotes, financials, peers, and analyst estimates, then building a DCF or investment thesis
- A data engineer building finance ETL pipelines using dbt/Airflow patterns from the skill's later sections
- An accounting team parsing invoice PDFs in bulk and exporting categorized CSVs
How do you install this skill?
- This is a static reference-template skill only; claimed capabilities such as 'market data', 'ML forecasting' and 'ETL pipelines' are not implemented in the visible content, so expectations should be lowered accordingly.
- All content assumes US GAAP and USD conventions; Chinese users must adapt for CAS and local tax rules.
- Merged sources (Perplexity Computer, Claude Code skills) are unverifiable; verify license compliance before use.
- Invoice and payroll templates involve sensitive financial data; sanitize inputs when using them.
- Network access
Place the repo's SKILL.md into your Claude Code skills directory, or upload it to Perplexity Computer user settings as the README describes. No one-click installer or dependency script is provided; installation on other platforms is undocumented.
git clone --depth 1 https://github.com/get-zeked/finance-super-skill.git ~/.claude/skills/finance-super-skillGenerated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Prepare the March bank reconciliation
- Draft a SOX control test workpaper
- Build a DCF for Apple
Trigger conversationally, e.g.: "Prepare the March bank reconciliation", "Draft a SOX control test workpaper", or "Build a DCF for Apple". Market-data features invoke connector tools such as finance_quotes and finance_financials; the skill explicitly forbids using web search for financial data and maps reference dates to fiscal quarters. Note: on platforms without Perplexity's finance_* tools, the markets chapters cannot execute.
What are this skill's strengths and limitations?
- Extremely broad coverage: journal entries through close, audit, valuation, data engineering, and ML forecasting in one file
- Templates are immediately usable, with complete table structures and worked example calculations
- Includes a Python audit sampling script and a clear SOX deficiency classification framework
- Explicit market-data guidance: structured finance tools over stale web search
- Market-data chapters depend on Perplexity Computer's proprietary finance_* connector tools, unavailable in Claude Code or elsewhere without substituting a data source
- No test suite and no standalone executable scripts (only example code embedded in the document)
- Repo shows no GitHub license label, while SKILL.md and README both claim MIT — an inconsistency
- Very large content footprint may consume substantial context; truncated portions of SKILL.md are unverified
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Finance & Accounting Super-Skill this page | 46 · Use with care | ★ 26 | 7mo ago | — |
| Month-End Variance Commentary ✓ Anthropic · Official | 42 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Period-End Accrual Planner ✓ Anthropic · Official | 48 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Financial Analysis Skill | 35 · Not recommended | ★ 7.3k | 11d ago | Apache-2.0 |
| Value Investing Agent | 55 · Use with care | ★ 23 | 8mo ago | MIT |
How did FollowSkills review this skill?
Pure reference-text skill (GAAP templates, journal entries, reconciliation, close calendars); no scripts, external calls, or permission requests; no red-line risk observed. But lacks data-flow disclosure, sensitive-financial-data (invoice, payroll) handling guidance, and rollback mechanisms, so full marks not awarded.
Static reference content, internally consistent (debits/credits logic in templates coherent), but no scripts, tests, or failure-feedback design; static calibration caps this below 10 and key paths lack reproduction evidence.
Scenarios clearly listed (statements, close, audit, valuation), but no declared capability boundaries or non-fit ranges; all content is US GAAP and English-only with no Chinese support, and merged-source claims exceed what visible text delivers, limiting trigger precision.
MIT license, author and version declared; well-layered structure with sectioned 'When to Use' guidance. However merged sources (Perplexity Computer, alirezarezvani) are unverifiable, no changelog, no ownership/update path, and README says 7 skills while the body says 8 — an inconsistency.
Genuinely useful as finance reference material (JE templates, ratio tables, DCF workflow, close calendar) directly usable; but no executable outputs verified, and claims like 'market data' and 'ML forecasting' are not delivered in visible text; static calibration caps below 7.
Only author claims and asserted source merges; no third-party execution evidence, no tests, no representative outputs, and source attribution lacks checkable links; static review caps below 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →