AB ai-potential-driver
Turn OpenClaw into a PUA-driven breakthrough execution agent that pushes past shallow answers, expands real solution paths, and keeps moving until there is evidence-backed completion or a hard blocker. Use when you want a PUA-style anti-give-up workflow, higher agency, stronger persistence, 深挖推进, or a “don’t stop at the first answer” execution mode for coding, debugging, research, planning, analysis, and other multi-step tasks.
As a process B 69/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
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 69/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 867 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
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 431: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 38 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.