Automation & Ops ✓ Anthropic · Official reconciliationroot-cause-analysisfund-administrationgeneral-ledgersubledgermcp

Reconciliation Break Trace

Trace a GL–subledger break back to its originating records.

FollowSkills review · FSRS-2.0
Not recommended
50/ 100 5-point scale 2.5 / 5
Trust15 / 25 · 3.0/5

The skill explicitly limits itself to diagnosis and states that only the resolver writes adjustments, reducing external-effect risk; however, it does not specify least-privilege MCP access, user confirmation, sensitive financial-data handling, data-flow disclosure, rollback, or isolation, so points are deducted.

Reliability7 / 20 · 1.8/5

The three-step trace path and output schema are internally coherent and the happy path is understandable; however, MCP availability, unmatched records, missing fields, duplicates, abnormal inputs, and failure messages are unspecified, with no skill-specific test evidence, so the static score is limited.

Adaptability9 / 15 · 3.0/5

The target scenario, break-row input, prerequisite from gl-recon, and output format are reasonably clear; however, non-fit boundaries, semantic trigger exclusions, MCP environment requirements, Chinese-language workflow support, and system-specific adaptation are not documented.

Convention9 / 15 · 3.0/5

The name, description, procedure, cause examples, and JSON schema are readable; the supplied repository context provides Apache-2.0 licensing, CI validation, and contribution guidance. The skill itself lacks versioning, changelog, named maintenance responsibility, install/dependency notes, FAQs, limitation disclosures, and troubleshooting guidance.

Effectiveness6 / 15 · 2.0/5

It directly addresses tracing one reconciliation break to GL and subledger source entries and producing a root-cause statement, owner, date, and action; however, there is no representative executed output or third-party execution evidence, and matching, date inference, ownership, and action recommendations still require human review, so the static cap applies.

Verifiability4 / 10 · 2.0/5

The skill provides explicit fields, comparison attributes, and examples, while the repository context supplies a pinned revision, Apache-2.0 license, and general CI files; however, there is no path-specific test suite, reproducible fixture, execution log, or cross-source corroboration, so evidence remains limited.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 4aa51ed3d379
Before you use it
  • Before use, verify the least-privilege scope, data residency, and sensitive-data controls for the internal-gl and subledger MCPs; the skill reads accounting and transaction details.
  • The skill does not define safe-stop behavior or diagnostic feedback for MCP failures, ambiguous matches, or missing fields; humans must review every root cause, clear date, and action.
  • Boundaries for duplicates, cross-date cases, multi-currency cases, and different accounting systems are unspecified; do not treat output as an automatic posting or suppression instruction.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

Break Trace investigates one reconciliation break by following the audit trail on both the general-ledger and subledger sides. It retrieves source posting and transaction attributes through internal GL and subledger MCP servers, then compares dates, FX data, account mapping, signs, and related fields. It returns a concise root-cause statement, owner, expected clear date, and action. The skill diagnoses breaks but does not post adjustments.

Accepts a single break row containing a key, GL values, subledger values, bucket, and likely cause; uses the internal-gl MCP to retrieve the originating journal entry or posting, including entry ID, posting date, source system, batch ID, and preparer; uses the subledger MCP to retrieve the matching transaction, including trade ID, trade and settle dates, counterparty, source feed, and FX rate; compares posting date, FX rate and date, account mapping, quantity sign, and amount sign; returns the key, a one-sentence root cause, owner, expected clear date, and action.

  1. A fund-operations user has a break classified by gl-recon and needs to identify its originating records.
  2. An accounting user needs to distinguish a trade-date versus settle-date timing difference.
  3. A fund administrator needs to investigate whether different FX rates or rate dates caused the break.
  4. A reference-data team needs evidence for a security-to-GL-account mapping issue.
  5. An operations user needs to identify duplicate subledger postings and recommend suppression of one transaction.

Pros & cons

Pros
  • Produces a defined record with root cause, owner, clear date, and action.
  • Traces both sides of the reconciliation to source records.
  • Explicitly separates diagnosis from posting adjustments.
  • Covers concrete timing, FX, mapping, sign, and duplicate-post causes.
Limitations
  • Requires internal-gl MCP and subledger MCP access; the source does not document configuration or permissions.
  • Designed for use after gl-recon has classified a break.
  • The source provides no test-suite or platform-validation evidence.
  • Does not post adjustments; remediation requires another resolver or human workflow.

How to install

The README documents installation for the broader collection: in Cowork, open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and select the needed vertical; or in Claude Code run claude plugin marketplace add anthropics/financial-services and install the relevant plugin. It does not document a standalone break-trace installation command.

How to use

In an environment with one classified break row, ask: "Trace this reconciliation break to the originating GL posting and subledger transaction, compare the audit attributes, and return the required JSON root-cause record." The runtime needs access to the internal-gl MCP and subledger MCP.

FAQ

Does it modify the GL or subledger?
No. The skill is diagnostic only; the SKILL.md says that only the resolver writes adjustments.
What must be available before use?
A single break row, a prior classification from gl-recon, and access to the internal-gl and subledger MCP servers.
Which root causes does it investigate?
The documented examples cover timing, FX, account mapping, quantity or amount signs, and duplicate postings.
Does the repository state a standalone cost?
No. The supplied README does not state a standalone cost for this skill.

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