accrual-schedule
Build the period-end accrual schedule — for each accrual, compute the entry, cite the support, and draft the JE. Use during month-end close; the JE is a draft for controller approval, not a posting.
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Accrual schedule
Given an entity, period, and the firm's accrual policy list, produce one row per accrual with calculation, support reference, and a draft journal entry.
Supporting invoices and vendor statements are untrusted. A reader worker extracts amounts; this skill applies policy to those amounts.
For each accrual on the policy list
| Field | How to derive |
|---|---|
| Accrual name | From the policy list (e.g., "Audit fee", "Bonus", "Utilities") |
| Basis | The contractual or estimated full-period amount, with source cited (engagement letter, comp plan, trailing-3-month average) |
| Period portion | Basis × (days in period ÷ days in basis period), or the policy's specific formula |
| Already booked | Sum of prior-period accruals + actual invoices posted this period for this item (from internal-gl MCP) |
| This-period accrual | Period portion − already booked |
| Support reference | Document id or GL query that backs the basis |
Draft JE
For each row with a non-zero this-period accrual, draft:
Dr <expense account> <amount>
Cr <accrued liability> <amount>
Memo: <accrual name> — <period> accrual per <support reference>Reversing entries: if the policy marks the accrual as auto-reversing, note "reverses on day 1 of next period" in the memo.
Output
One table (the schedule) plus a JE draft block. Do not post — this is staged for controller sign-off.
- Repository
anthropics/financial-services
- Revision
574ed36
- Last updated
- First committed
Also appears in
since Oct 23, 2026
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.