Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
anthropics avatar

Break Trace

  • 1 installs
  • 34k repo stars
  • Updated August 4, 2026
  • anthropics/financial-services

Break-trace is a Claude skill that root-causes a reconciliation break by tracing it from the break row to the source entry on the GL and subledger sides.

About

Break-trace root-causes a reconciliation break to its source transaction after gl-recon has classified it. It pulls the GL-side posting and the subledger-side transaction via MCPs, diffs their attributes, and writes a single-sentence root cause naming the side, what happened, and why. It returns a structured JSON record with owner, expected clear date, and action, and diagnoses only without posting adjustments.

  • Root-causes a reconciliation break by tracing the audit trail from the break row back to the source entry on each side
  • Pulls the GL side and subledger side via MCPs, diffs attributes (dates, FX rate, mapping, signs), and names the cause
  • Returns a JSON root-cause record with owner, expected clear date, and action; diagnoses only, never posts

Break Trace by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #909 of 1,106 Finance & Trading skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

break-trace capabilities & compatibility

Capabilities
accrual schedule · audit xls
Use cases
debugging · data analysis
From the docs

What break-trace says it does

Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what differs and why.
SKILL.md
Only the resolver writes adjustments — this skill diagnoses, it does not post.
SKILL.md
npx skills add https://github.com/anthropics/financial-services --skill break-trace

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
repo stars34k
Last updatedAugust 4, 2026
Repositoryanthropics/financial-services

What it does

Trace a reconciliation break to its source posting and produce a root-cause statement with an owner and action.

Who is it for?

Operations and accounting teams resolving GL-vs-subledger reconciliation breaks after classification

Skip if: Posting adjustments or classifying breaks; it only diagnoses and hands off

When should I use this skill?

After gl-recon has classified a break and its source and cause need tracing

What you get

A JSON root-cause record with a one-sentence cause, owner, expected clear date, and action per traced break.

  • One-sentence root-cause statement
  • JSON record with owner, expected clear date, and action

By the numbers

  • 3-step trace path (GL side, subledger side, diff)
  • 4 action values (monitor, adjust, raise-ticket, suppress)

Files

SKILL.mdMarkdownGitHub ↗

Root-cause a break

Given a single break row (key, GL values, subledger values, bucket, likely cause), trace it to source and produce a root-cause statement.

Trace path

1. Pull the GL side — via the internal-gl MCP, fetch the journal entry or posting that produced this GL line: entry id, posting date, source system, batch id, preparer. 2. Pull the subledger side — via the subledger MCP, fetch the matching transaction: trade id, trade/settle dates, counterparty, source feed, FX rate used. 3. Diff the attributes — line up posting date, FX rate/date, account mapping, quantity sign, amount sign. The differing attribute is usually the cause.

Cause → statement

Write the root cause as a single sentence in the form "⟨side⟩ ⟨did what⟩ because ⟨reason⟩", e.g.:

  • "GL posted on settle date (T+2) while subledger posted on trade date — timing break, will clear on 2026-05-07."
  • "Subledger used WM/R 4pm rate; GL used Bloomberg close — FX break of 12 bps on the base amount."
  • "Security ABC123 maps to GL account 11420 in the mapping table but the subledger fed 11410 — mapping break, raise to reference-data."
  • "Subledger posted the trade twice (trade ids 88412 and 88419 are duplicates) — duplicate post, suppress 88419."

Output

For each traced break, return:

{
  "key": "...",
  "root_cause": "one sentence as above",
  "owner": "ops | reference-data | accounting | upstream-system",
  "expected_clear_date": "YYYY-MM-DD or null",
  "action": "monitor | adjust | raise-ticket | suppress"
}

Only the resolver writes adjustments — this skill diagnoses, it does not post.

Related skills

FAQ

Does break-trace post the fix?

No. Only the resolver writes adjustments; this skill diagnoses and does not post.

What does it output per break?

A JSON object with key, one-sentence root_cause, owner, expected_clear_date, and action (monitor, adjust, raise-ticket, or suppress).

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.