AC ai-opportunity-discovery
Interviews a business owner or manager about their workflows, tools, and pain points, then delivers an evidence-based AI opportunity assessment — prioritized AI use cases, complexity and data-readiness scoring, risks, a build-vs-buy recommendation, and a phased roadmap. Explicitly and honestly flags when plain automation or off-the-shelf software beats AI. Use when a user asks "where can AI help my business", wants an AI opportunity assessment, AI readiness audit, or automation audit, is deciding whether to automate a process or build an AI agent, asks "should I use AI for this", wants to find high-value AI use cases before hiring a developer or vendor, or wants a business AI roadmap.
Interviews a business owner or manager about their workflows, tools, and pain points, then delivers an evidence-based AI opportunity assessment — prioritized…
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 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
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1736 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 693: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 30 items
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.