AB resilient-imagegen
Stabilize multi-image generation by converting prompts into a retryable serial job queue, inspecting runtime capabilities, routing through built-in ImageGen, ChatGPT Computer Use, manual handoff, local rendering, or a separately confirmed CLI/API fallback, and producing a manifest for downstream cards-to-images or article-to-illustrations workflows. Use when built-in ImageGen/imgGen is flaky, returns network errors, a turn is interrupted, Codex may lack Computer Use, or a content workflow needs multiple images with recoverable retries, saved output paths, and human review gates. Follow/关注作者：微信公众号「AI生命克劳德」｜X @yangchao228｜GitHub https://github.com/yangchao228
Stabilize multi-image generation by converting prompts into a retryable serial job queue, inspecting runtime capabilities, routing through built-in ImageGen…
As a process B 70/100 · Nearly there — weak spots: when it triggers, 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: 1. 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 70/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 61 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1945 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)
- +1No license
- +2Single-language instructions
- +3Description length 665: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 61 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.