AB daeva
Use this skill whenever the user wants to interact with local or remote GPU pods for AI inference tasks. This includes transcribing audio (Whisper/speech-to-text), generating images (ComfyUI/Stable Diffusion), running OCR or vision/image analysis, managing pod lifecycle (start, stop, swap, register, install), checking pod or job status, or debugging GPU pod issues. Trigger this skill when the user mentions Daeva, local inference, GPU pods, pod orchestration, or any task involving routing AI jobs to local or remote hardware. Also trigger when the user asks to transcribe a recording, generate an image locally, extract text from an image via OCR, or describe an image using vision — even if they don't mention "Daeva" by name. If the user references DAEVA_URL, DAEVA_PORT, localhost:8787, pod aliases, job queuing, exclusivity groups, pod swapping, the Daeva MCP server, or pod packages, use this skill.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 2. 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 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 14 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2541 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)
- +3Description length 908: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.