Data & Analysis ✓ Anthropic · Official nav-reconciliationfund-accountinglp-reportingprivate-equitycapital-accountmcp

LP NAV Tie-Out

Reconcile LP statements to fund NAV data and flag line-level capital account breaks.

FollowSkills review · FSRS-2.0
Not recommended
46/ 100 5-point scale 2.3 / 5
Trust15 / 25 · 3.0/5

The skill identifies the NAV pack as the source of truth and instructs the agent to compare and flag rather than edit the statement, indicating limited authority and low external effect. It does not specify sensitive financial-data handling, access confirmation, data-flow disclosure, isolation, or recovery controls, so points are deducted.

Reliability8 / 20 · 2.0/5

The recomputation formula, line-by-line comparison, tolerance, and additional checks make the happy path understandable. However, the nav MCP dependency is unspecified, and missing inputs, abnormal data, accounting-basis differences, and failure feedback are not handled; no skill-specific tests are provided, so the static ceiling and uncertainty reduce the score.

Adaptability8 / 15 · 2.7/5

The audience, timing, scenario, and requested output are clear. Boundaries, precise trigger conditions, input prerequisites, Chinese-language support, and nav MCP reachability are not documented, so points are deducted.

Convention6 / 15 · 2.0/5

The document is concise and layered into purpose, recomputation, comparison, checks, and output. Repository-level evidence supplies an Apache-2.0 license, contribution process, and maintenance-oriented CI, but the skill lacks versioning, changelog, dependency installation notes, examples, FAQs, known limitations, and explicit ownership, so points are deducted.

Effectiveness6 / 15 · 2.0/5

It directly covers capital-account recomputation, line-level reconciliation, and actionable flags, producing an output suitable for human review. Representative outputs, complex fund-accounting cases, and comparative benefit over manual review are not evidenced, and professional review remains necessary, so points are deducted.

Verifiability3 / 10 · 1.5/5

The source contains auditable formulas, a tolerance, and explicit checks, while repository CI provides general plugin validation and secret scanning. There are no skill-specific tests, execution records, independent reproductions, or corroborating evidence, so only limited credit is justified.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 4aa51ed3d379
Before you use it
  • The nav MCP service, permissions, authentication, and availability are unspecified; confirm that it can reliably provide complete, version-consistent NAV data before deployment.
  • The formula does not define treatment for valuation dates, transaction timing, fee bases, in-kind distributions, transfers, FX, rounding, or waterfall edge cases, creating risk of false positives or missed breaks.
  • The skill leaves follow-up action on flags to humans but does not define approval, evidence retention, privacy, or pre-distribution blocking controls.
  • No skill-specific tests or failure examples are supplied; a qualified fund administrator should independently validate it against known cases.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

This skill independently recomputes an LP’s capital account from the period’s fund NAV pack before an LP statement is distributed. It pulls ownership, fund P&L, fees, expenses, and waterfall outputs from the NAV pack, then compares the results with the generated statement line by line. The tolerance is 0.01, and the output identifies pass/fail results, recomputed values, statement values, and likely drivers of mismatches. It flags issues for review and does not edit the statement.

Reads a generated LP statement and a period NAV pack supplied through the nav MCP; recomputes ending capital from beginning capital, paid contributions, cash and in-kind distributions, allocated net income or loss, and crystallized carried interest; compares each statement line with the recomputed value using a 0.01 tolerance; checks, when available, that this statement’s ending capital equals the next period draft’s beginning capital; checks that total LP ending capital agrees with fund NAV within rounding; checks commitment, unfunded, and recallable figures against the commitment register; and produces line-level pass/fail results, recomputed values, statement values, and flags.

  1. A fund administration team reviews LP capital accounts before distributing quarterly statements.
  2. A fund accountant investigates a break caused by ownership percentages, P&L allocation, fees, expenses, or waterfall outputs.
  3. An operations team validates that statement ending capital rolls into the next period’s draft.
  4. A fund administrator checks that the aggregate of LP ending capitals agrees with fund NAV after period close.

Pros & cons

Pros
  • Uses the NAV pack as the source of truth for an independent recomputation.
  • Defines a concrete 0.01 tolerance and requires drivers for mismatches.
  • Includes roll-forward, aggregate NAV, and commitment-register consistency checks.
  • Produces review flags without changing the statement.
Limitations
  • Requires the nav MCP and usable NAV pack data.
  • The source does not document nav MCP deployment, permissions, or input schemas.
  • The source provides no test suite, sample output, or platform validation evidence.
  • It identifies and flags breaks but does not resolve or edit them.

How to install

Add the repository as a Claude Cowork plugin: open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and select the required vertical. The skill is located at plugins/vertical-plugins/fund-admin/skills/nav-tieout/. The README does not document a standalone installation command for this individual skill.

How to use

Provide the generated LP statement, the period NAV pack, and, when needed, the commitment register and next-period draft. Ensure NAV data is available through the nav MCP. An illustrative request is: “Tie out this LP statement to the NAV pack, recompute the capital account line by line, and return pass/fail results, recomputed values, statement values, and mismatch flags using a 0.01 tolerance.” The source does not define a dedicated slash command.

FAQ

Does it edit LP statements?
No. It returns line-level results and flags; the publisher reviews and acts on them.
What inputs are required?
The core inputs are a generated LP statement and the period’s NAV pack. The extra checks may also use a next-period draft and commitment register.
How are mismatches evaluated?
Each line is compared with a 0.01 tolerance, and the output notes the input driving any mismatch.
Could there be additional costs?
The repository is licensed under Apache License 2.0. Its README notes that MCP providers may require a subscription or API key.

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