From gl-reconciler
Root-causes a reconciliation break by tracing it to the originating GL journal entry and subledger transaction, then stating what differs and why.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gl-reconciler:break-traceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Given a single break row (key, GL values, subledger values, bucket, likely cause), trace it to source and produce a root-cause statement.
Given a single break row (key, GL values, subledger values, bucket, likely cause), trace it to source and produce a root-cause statement.
Write the root cause as a single sentence in the form "⟨side⟩ ⟨did what⟩ because ⟨reason⟩", e.g.:
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.
18plugins reuse this skill
First indexed May 7, 2026
Showing the 6 earliest of 18 plugins
npx claudepluginhub anthropics/financial-services --plugin gl-reconcilerRoot-causes a reconciliation break by tracing it to the originating GL journal entry and subledger transaction, then stating what differs and why.
Matches GL and subledger extracts by key, surfaces breaks (amount, quantity, timing, missing), and classifies each break by likely cause. Useful for daily or month-end recon across asset classes.
Guides account reconciliations by comparing GL balances to subledgers, bank statements, or third-party data; covers processes, differences, and item categorization for bank recs, GL-subledger ties, intercompany.