BF chatgpt-image-handoff
Route a multi-image content job through the best available generation backend, prepare a resumable prompt pack with readable-text fact boundaries, optionally operate an approved ordinary ChatGPT browser session with Computer Use, test an optional multi-image ZIP delivery when the active surface supports it, repair useful generated backgrounds with an allowlist-only mixed overlay, import outputs under stable names, and resume visual QA. Use when built-in ImageGen is unavailable or flaky, Codex may or may not have Computer Use, a user needs a manual ChatGPT fallback, repeated browser round trips should be reduced, exact names or numbers must not be invented, or external image outputs must re-enter a checked local asset pipeline without losing job state. Follow/关注作者：微信公众号「AI生命克劳德」｜X @yangchao228｜GitHub https://github.com/yangchao228
Route a multi-image content job through the best available generation backend, prepare a resumable prompt pack with readable-text fact boundaries, optionally…
As a process F 51/100 · Will not run — References files that are not bundled: references/zip-batch.md, references/ui-recovery.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/zip-batch.md - warning
missing-refreference to a missing file: references/ui-recovery.md
Process rating: all ten parameters 51/100
- 0Tools and files. 2 referenced file(s) missing: references/zip-batch.md, references/ui-recovery.md
- 0Result and completion. Does not say what the result is
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 62 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3777 tokens
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
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 841: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 62 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.