AF invoice-chaser
Automated invoice follow-up sequences that escalate from friendly to firm. Track unpaid invoices, send timed reminder emails with escalating tone, log payment interactions, and generate AR aging reports. Your agent handles the awkward conversations so you don't have to — preserving cash flow and client relationships while you focus on actual work. Configure invoice tracking, email templates per stage (friendly → firm → final notice), timing rules, and let your agent chase payments 24/7. Use when adding invoices, running payment chases, checking status, or generating accounts receivable reports.
As a process F 43/100 · Will not run — References files that are not bundled: scripts/chase.sh, scripts/status.sh, scripts/report.sh
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/chase.sh - warning
missing-refreference to a missing file: scripts/status.sh - warning
missing-refreference to a missing file: scripts/report.sh - warning
missing-refreference to a missing file: references/accounting-adapters.md
Process rating: all ten parameters 43/100
- 0Tools and files. 4 referenced file(s) missing: scripts/chase.sh, scripts/status.sh, scripts/report.sh
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 100Steps. 48 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2637 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 601: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (13 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.