AB oatda-text-completion
Generate text using OATDA's unified LLM API. Triggers when the user wants to generate, write, or complete text using a specific LLM provider (OpenAI, Anthropic, Google, Deepseek, Mistral, xAI, Alibaba, MiniMax, ZAI, Moonshot) through the OATDA API. Also use when comparing outputs across models or using model aliases like "gpt-4o", "claude", "gemini", "deepseek", "grok", "qwen", "mistral".
As a process B 76/100 · Nearly there — weak spots: 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 76/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 887 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 391: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 8 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.