AD 3d-wood-lighting-scorecard
Light carved wood in a dark room in three.js, with procedural grain and pores, one warm key through a window, soft shadows that touch, light shafts, background rays and dust, then score the render out of 10 on an anchored rubric with a runnable headless scorecard and iterate until each item reaches the target. Use for oiled timber, kumiko, joinery and workshop scenes; wood that reads flat, plastic or washed out; volumetrics that lift the blacks; "score this out of 10"; or "get the lighting to 8".
Light carved wood in a dark room in three.js, with procedural grain and pores, one warm key through a window, soft shadows that touch, light shafts…
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: 8. 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. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2690 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
- +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
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 501: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 19 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.