AD c3d-bpy-scene-placement
Use in every scene_blender env, zone, refine or rebuild session that places anything, and whenever check_placement or the scene_placement gate reported a floating, sunken, unsupported, interpenetrating, cantilevered or out-of-bounds asset, too many free-tagged ones, or a world that ends at its bounds (world_edge). Everything placed is ONE row in a measured table and its feet are sampled against what is under them. Gives what the gate measures and on which geometry, how a collection instance differs from a geometry-nodes cloud, the requirements with their measurements, how to seat and check in raw bpy what the gate samples (no library ships in raw mode), the self-check, and the finding-to-fix table.
Use in every sceneblender env, zone, refine or rebuild session that places anything, and whenever checkplacement or the sceneplacement gate reported a…
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2482 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 707: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.