AF expense-claim
End-to-end business travel expense claim processor. Use this skill whenever a user uploads receipts, bills, invoices, or screenshots of expenses and wants to organize, categorize, or submit a claim. Triggers include: "process my bills", "help me file expenses", "sort my receipts", "create expense PDFs", "how much did I spend", "organize my travel bills", "prepare claim for TCS / SAP Concur / iExpense", or any upload of multiple receipt images/PDFs with intent to claim reimbursement. Also triggers when user asks for a daily spend summary, category-wise breakdown, or currency conversion of travel expenses. Always use this skill — even if the user only uploads a single receipt — if reimbursement or expense filing is the goal.
As a process F 55/100 · Will not run — References files that are not bundled: scripts/build_pdfs.py, scripts/build_xlsx.py, references/fx_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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/build_pdfs.py - warning
missing-refreference to a missing file: scripts/build_xlsx.py - warning
missing-refreference to a missing file: references/fx_rates.md - warning
missing-refreference to a missing file: references/tcs_categories.md
Process rating: all ten parameters 55/100
- 0Tools and files. 4 referenced file(s) missing: scripts/build_pdfs.py, scripts/build_xlsx.py, references/fx_rates.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (expense-claim) differs from the folder (tcs-expense-claim)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 32 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1623 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 732: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.