BF hatch-pet
Turn any keyword—animal, character, brand, object, or style—into a complete installable Codex pet package. Use when a user says ‘生成 Codex 宠物’, ‘做一个宠物包’, ‘Codex pet’, or provides a keyword or reference image and wants one-click pet creation, repair, upgrade, validation, packaging, or installation. Produces Codex-compatible v2 pets with all 9 standard animation rows, 16 look directions, deterministic QA, and spriteVersionNumber 2 packaging.
Turn any keyword—animal, character, brand, object, or style—into a complete installable Codex pet package.
As a process F 44/100 · Will not run — References files that are not bundled: references/layout-guides/, references/canonical-base.png, references/layout-guides/<state>.png
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 21367 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/layout-guides/ - warning
missing-refreference to a missing file: references/canonical-base.png - warning
missing-refreference to a missing file: references/layout-guides/<state>.png
Process rating: all ten parameters 44/100
- 0Tools and files. 3 referenced file(s) missing: references/layout-guides/, references/canonical-base.png, references/layout-guides/<state>.png
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 21367 tokens: crowds the task out of the window
- 30Running it twice. 18 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 85Steps. 212 steps, 3 vague phrases
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +2Single-language instructions
- +3Description length 442: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 212 items
- +3Output format is stated explicitly
- +4Has examples (40 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +3All 17 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.