Data & Analysis ✓ Anthropic · Official financial-reconciliationnavprivate-equitylp-statementsfund-accountingmcp

LP NAV Tie-Out Auditor

Recompute an LP capital account from the NAV pack and flag statement mismatches before distribution.

FollowSkills review · FSRS-2.0
Not recommended
47/ 100 5-point scale 2.4 / 5
Trust16 / 25 · 3.2/5

The skill identifies the NAV pack as the source of truth and explicitly limits output to line-by-line comparisons and flags without editing the statement, keeping external effects and permissions relatively narrow. It does not specify MCP permissions, handling of sensitive LP/fund data, user confirmation, data flow, recovery, or dependency security, so 9 points are deducted.

Reliability7 / 20 · 1.8/5

The formula, input sources, tolerance, additional checks, and flagging requirements are coherent and support repeatable static reasoning. However, there is no handling or diagnostic guidance for MCP outages, missing fields, malformed data, valuation-policy differences, or rounding conflicts, and no key-path tests, so 13 points are deducted.

Adaptability8 / 15 · 2.7/5

The target scenario, timing, main inputs, and output are reasonably clear for pre-distribution LP statement review. Boundaries for non-fit cases, NAV MCP environment requirements, Chinese-language use, mainland-China reachability, and adaptation to differing fund accounting policies are not stated, so 7 points are deducted.

Convention6 / 15 · 2.0/5

The document is concise and includes a name, description, workflow, checks, and output requirements. The repository provides an Apache-2.0 license and plugin-validation CI, but the skill lacks its own version, changelog, maintenance owner, installation notes, examples, and troubleshooting guidance, so 9 points are deducted.

Effectiveness6 / 15 · 2.0/5

It directly covers the core task of recomputing capital accounts, comparing lines, and producing discrepancy flags. There are no representative outputs or execution evidence, and complex allocation and valuation conventions are underspecified, leaving material professional review, so 9 points are deducted.

Verifiability4 / 10 · 2.0/5

The skill supplies auditable formulas, input categories, and a tolerance, while the repository includes plugin-validation and secret-scanning workflows. It provides no skill-specific key-path tests, third-party execution evidence, or corroborating sources, so 6 points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 4aa51ed3d379
Before you use it
  • The skill depends on a NAV MCP connection but does not document required tools, permissions, authentication, outage behavior, or reachability.
  • Fund accounting policies, timing of contribution and distribution recognition, in-kind valuation, carry crystallization, and rounding rules are underspecified; an automated pass should not authorize final distribution.
  • The deploying institution should add access controls, confidentiality requirements, audit logging, and human sign-off for LP and fund financial data.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

This skill performs a NAV tie-out before LP statements are distributed. It treats the generated statement as the item under test and the NAV pack as the source of truth. It independently recomputes the LP capital account from beginning capital, contributions, distributions, allocated profit or loss, and crystallized carried interest. It then compares each statement line using a 0.01 tolerance and reports pass/fail results, values, and flags.

Reads a generated LP statement and the period NAV pack supplied through the nav MCP; pulls the LP commitment percentage, fund-level P&L components, fee and expense totals, and waterfall outputs; recomputes ending capital; compares each statement line with the recomputed value using a 0.01 tolerance; checks beginning and ending capital across periods, the sum of LP ending capitals against fund NAV, and commitment, unfunded, and recallable figures against the commitment register; produces pass/fail results, recomputed values, statement values, and flags without editing the statement.

  1. A fund administrator validates quarterly LP statements against the period NAV pack before distribution.
  2. A private-equity operations team investigates an allocated-P&L difference after an ownership transfer.
  3. A finance team reviews a mismatch between the current statement's ending capital and the next period's draft beginning capital.
  4. A fund accountant checks whether all LP ending capitals sum to fund NAV within rounding.
  5. A statement publisher routes flagged discrepancies for qualified human review before release.

Pros & cons

Pros
  • Uses the NAV pack as the stated source of truth and independently recomputes the LP capital account.
  • Defines a concrete 0.01 tolerance and asks for the input driving each mismatch.
  • Includes cross-period capital checks, a fund-NAV aggregation check, and commitment-register checks.
  • Produces review flags without directly changing the statement.
Limitations
  • Requires the nav MCP, a generated LP statement, a period NAV pack, and commitment-register inputs.
  • The source does not document the nav MCP interface, permission setup, or error-handling behavior.
  • The source provides no test suite, sample output, or independent platform validation details.
  • It identifies and flags discrepancies but does not correct statements or approve distribution.

How to install

The skill is located at plugins/agent-plugins/statement-auditor/skills/nav-tieout/SKILL.md and is distributed within the financial-services repository's plugin collection. The README documents installing the collection in Cowork by opening Settings → Plugins → Add plugin, pasting https://github.com/anthropics/financial-services, and selecting the required agent or vertical. It also documents uploading a zip of a directory under plugins/. The source does not document a standalone installation command for this skill.

How to use

Provide the generated LP statement and the period NAV pack, with access to the data through the nav MCP. Example prompt: Tie out this generated LP statement to the period NAV pack, recompute the LP capital account line by line, apply a 0.01 tolerance, and return pass/fail results, recomputed values, statement values, and flags. Do not ask it to edit the statement; the source specifies that the publisher acts on the flags after review.

FAQ

Does the skill edit LP statements automatically?
No. It returns line-level results and flags; the publisher acts on them after review.
What data does it need?
It needs the generated LP statement, the period NAV pack, relevant capital, P&L, fee, expense, waterfall, and commitment inputs, and access through the nav MCP.
How are mismatches determined?
Each statement line is compared with the independently recomputed value using a 0.01 tolerance, with the driving input identified where possible.
Is this accounting or investment advice?
The README states that the repository does not constitute investment, legal, tax, or accounting advice and that outputs require review by a qualified professional.

More skills from this repository

All from anthropics/financial-services

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Builder

Populate and validate linked income statement, balance sheet, and cash flow models with formulas.

Data & Analysis ✓ Anthropic · Official

Spreadsheet Auditor

Checks spreadsheet formulas, errors, and financial-model integrity.

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Builder

Complete existing three-statement templates with linked formulas, projections, scenarios, and audit checks.

Data & Analysis ✓ Anthropic · Official

Comparable Company Valuation

Build institutional-grade peer valuation analyses with operating metrics, trading multiples, and statistical benchmarks in spreadsheets.

Data & Analysis ✓ Anthropic · Official

Competitive Landscape Analyst

Turn competitive research into an approved, comparable market landscape deck.

Data & Analysis ✓ Anthropic · Official

Earnings Update Researcher

Turn quarterly results into an institutional-style update focused on beats, estimate changes, valuation, and thesis impact.

Data & Analysis ✓ Anthropic · Official

Sector Landscape Research

Structure industry dynamics, competition, valuation, and investment themes in one research workflow.

Productivity & Collaboration ✓ Anthropic · Official

PE Investment Committee Memo Writer

Turns diligence, financial analysis, and deal terms into a structured memo for private equity investment committee approval.

Data & Analysis ✓ Anthropic · Official

Excel Data Cleaning Assistant

Clean inconsistent spreadsheets before analysis.

Data & Analysis ✓ Anthropic · Official

Financial Deck Refresh

Update financial figures across an existing presentation while preserving its formatting and structure.

Writing & Content ✓ Anthropic · Official

IC Memo Drafting

Turns diligence and financial inputs into a structured IC memo.

Data & Analysis ✓ Anthropic · Official

Financial Model Auditor

Find spreadsheet formula errors and test financial-model integrity before review.

Automation & Ops ✓ Anthropic · Official

Reconciliation Break Tracer

Trace ledger breaks to source entries and state the operational root cause.

Automation & Ops ✓ Anthropic · Official

KYC Intake Parser

Turn onboarding packets into structured KYC data ready for screening.

Data & Analysis ✓ Anthropic · Official

Audit XLS: Spreadsheet Model Review

Systematically checks spreadsheet formulas, errors, and financial-model integrity issues.

Data & Analysis ✓ Anthropic · Official

General Ledger Roll-Forward

Connects a balance-sheet account’s opening balance to its period-end GL balance for close packages and audit support.

Data & Analysis ✓ Anthropic · Official

Investment Banking Pitch Deck Filler

Populate existing investment banking PowerPoint templates with validated data from Excel, CSV, and other source files.

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Filler

Complete and validate integrated three-statement templates with formulas, linkages, and audit checks.

Data & Analysis ✓ Anthropic · Official

Financial Model Audit

Systematically checks spreadsheet formulas and model integrity.

Data & Analysis ✓ Anthropic · Official

GL–Subledger Reconciliation

Reconcile general ledger and subledger data, expose breaks, and suggest likely causes for investigation.

Related skills