BD evaluator
Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis. Produces an actionable report (eval.json + eval-report.md) sized for a downstream fixer agent. USE WHEN the user asks to "evaluate / score / grade / review / QA / check quality of" a rendered video, asks "is this video good?", drops an mp4 path with no other instruction, mentions "find issues / problems / artifacts", asks for retention or scroll-stop assessment, or has just rendered something and wants verification before publishing. TRIGGER (EN): "evaluate this video", "score the render", "grade the mp4", "review the final cut", "QA this video", "is this ready to ship", "what's wrong with this video", "find issues in <path.mp4>", "audit the video", "scene-by-scene breakdown", "retention check", "quality gate". See body for ALSO FIRE / DO NOT FIRE / HARD INVARIANTS.
Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis.
As a process D 46/100 · Unfinished process — References files that are not bundled: ../../../docs/playbooks/unit-lifecycle.md
The same skill appears in 1 more place: ralphy
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../docs/playbooks/unit-lifecycle.md - note
frontmatter-keyunknown frontmatter key "namespace" - note
edit-residuethe text marks something as outdated (lines 34, 56, 96, 97): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: ../../../docs/playbooks/unit-lifecycle.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 85Steps. 55 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3337 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 913: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.