AC revenue-recognition-agent
ASC 606 / IFRS 15 revenue recognition analysis and compliance for SaaS, services, and multi-element arrangements. Guides the 5-step recognition model, identifies performance obligations, determines transaction prices, allocates revenue across obligations, and tracks deferred/contract revenue. Produces journal entries, deferred revenue schedules, and disclosure checklists for audit-ready financials. Use when: recognizing revenue for contracts with customers, reviewing SaaS subscription treatment, analyzing multi-element bundles, booking deferred revenue, or preparing ASC 606 footnote disclosures. NOT for: tax revenue recognition (different rules), government contracts under ASC 808, or lease accounting (use ASC 842 guidance).
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5298 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5298 tokens
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
- low 11 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 734: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.