AF expense-categorization
Receipt OCR, GL code mapping, policy compliance checking, and anomaly detection for business expenses. Use when you need to: (1) extract data from receipt images or PDFs via OCR, (2) map expenses to chart of accounts or GL codes, (3) check receipts against expense policies (per diem limits, category restrictions, required fields), (4) detect anomalies like duplicates, out-of-policy amounts, missing receipts, or unusual vendors, (5) batch-process expense reports for approval routing, (6) categorize credit card transactions into accounting categories. Works with QBO chart of accounts, generic GL structures, or custom category lists. NOT for: tax filing or PTIN-backed services, payroll processing, or real-time bank feed categorization without human review.
As a process F 50/100 · Will not run — References files that are not bundled: references/ocr-prompt.md, references/irs-rates.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Receipt OCR, GL code mapping, policy compliance checking, and anom… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
missing-refreference to a missing file: references/ocr-prompt.md - warning
missing-refreference to a missing file: references/irs-rates.md
Process rating: all ten parameters 50/100
- 0Tools and files. 2 referenced file(s) missing: references/ocr-prompt.md, references/irs-rates.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1073 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 763: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.