AC double-agent
This skill should be used when designing, implementing, or improving any AI system that requires quality assurance through separation of generation and evaluation roles. It implements the Generator-Evaluator dual-agent architecture (inspired by Anthropic's engineering blog and GAN design), where a Generator produces outputs and a dedicated Evaluator agent independently validates them through real interaction (e.g., Playwright browser operations), eliminating AI self-evaluation bias. Use when: building AI-generated UIs/code that needs quality checks, designing multi-agent pipelines with feedback loops, or upgrading existing coder+tester workflows to real interaction-based evaluation.
As a process C 56/100 · 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: 6. 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 56/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1552 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 691: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.