BF synthclaw
Render Blender files with agent-controlled procedural parameters for synthetic data generation. A key capability of this skill is returning dynamic quality metrics (Naturalness and LPIPS) upon generation and measuring dataset-wide diversity (Shannon entropy), allowing agents to be guided by the metric results to iteratively optimize parameter ranges and improve synthetic data usefulness. Supports CYCLES (production) and EEVEE (fast testing) render engines.
As a process F 52/100 · Will not run — References files that are not bundled: assets/config/render_schema.json, assets/config/render_dataset_schema.json, assets/config/analyze_schema.json
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: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/config/render_schema.json - warning
missing-refreference to a missing file: assets/config/render_dataset_schema.json - warning
missing-refreference to a missing file: assets/config/analyze_schema.json - warning
missing-refreference to a missing file: assets/config/dataset_analysis_schema.json
Process rating: all ten parameters 52/100
- 0Tools and files. 4 referenced file(s) missing: assets/config/render_schema.json, assets/config/render_dataset_schema.json, assets/config/analyze_schema.json
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 56 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2681 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -31 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 460: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.