BD c3d-bpy-scene-lighting
Use when lighting a scene_blender env, zone, refine or rebuild session, or when scene_frames called a Blender frame too dark, blown out or flat. The harness renders with Cycles under AgX at exposure 0 and owns every render setting, so lamp energies, the world strength and the albedos are the only dials. Gives what the frame gate measures with its thresholds, the exposure bands measured for sky, sun, night, practical and interior setups under this renderer, the interface facts (the world is build_env's, what the census counts as atmosphere, which ceilings the overview rig lifts), the sky, lamps and fog in raw bpy (no library ships in raw mode), why an emissive mesh is not a lamp at 32 samples, and how to prove the band on every camera including the harness rig.
The harness renders with Cycles under AgX at exposure 0 and owns every render setting, so lamp energies, the world strength and the albedos are the only dials.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2376 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 770: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 8 items
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.