AC council-v2
Multi-model council review that spawns 3-5 independent AI reviewers and applies mechanical synthesis — votes decide, not orchestrator opinion. Use when you need a second opinion on code before merge, a pre-flight check on a plan, an architecture review for a technical decision, or a structured critique of options. Also use when someone says "is this safe to ship?", "get me a sanity check", "review this with multiple models", or "I want adversarial feedback." Do not use for trivial edits or low-stakes decisions where the overhead exceeds the risk.
As a process C 57/100 · Has gaps — weak spots: result and completion, 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: 11. 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 57/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 41 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1771 tokens
- low 12 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 552: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.