AC commercial-forecaster
Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or commit/best-case/pipe-only board number — especially when the CRO needs to walk the board through funnel math + cohort ARR + per-stage conversion assumptions without the theatre of a single undefended number. Decomposes pipeline into commit, best-case, and pipe-only tiers; projects cohort-level NRR/GRR to surface leaky cohorts before they show up in the consolidated number; scores per-stage funnel confidence so soft-floor stages get treated differently from high-confidence ones. Every output explicitly names the conversion rate used, the data window, and the weighting choice. For Head of Commercial, RevOps, VP Sales, and CRO at quarterly forecast or board prep. NOT financial close (see finance/financial-analysis). NOT strategic CRO hiring/territory (see c-level-advisor/cro-advisor). NOT pricing (see sibling pricing-strategist).
Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or commit/best-case/pipe-only board number — especially…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "compatible_tools"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 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. 20 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2728 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
- +3Description length 942: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.