AC oz
Dispatch coding tasks to Warp Oz cloud agents and chain them into multi-agent pipelines — all from chat. Includes a bash wrapper covering every Oz API endpoint (runs, schedules, artifacts, agents) and a Python pipeline orchestrator that chains specialized agents (e.g., architect → developer → security → red-teamer) with automatic severity-based retry loops. Use when you want to kick off cloud coding agents, poll run status, manage cron schedules, run multi-turn conversations in a shared sandbox, or orchestrate multi-agent review pipelines. NOT for local Warp terminal usage.
As a process C 52/100 · 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: 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 52/100
- 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. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1102 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 580: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (4 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: 95.