AD manim-animation
Create mathematical animations with synchronized voiceover narration and subtitles using Manim Community and manim-voiceover. Use when users want to create animated videos with narration, math animations with voice, educational videos with subtitles, or any request involving Manim scene generation with TTS voiceover. Trigger phrases include: manim animation, math animation, animated video with voice, 数学动画, 动画配音, 动画字幕, manim voiceover, create animation video, or any request to generate narrated mathematical/educational animation videos.
As a process D 39/100 · 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "required_tools" - note
frontmatter-keyunknown frontmatter key "required_packages" - note
frontmatter-keyunknown frontmatter key "network_access"
Process rating: all ten parameters 39/100
- 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
- 40Consistency. Frontmatter name (manim-animation) differs from the folder (manim-animation-cn)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 58 steps
- 100Execution cost. Instruction body is 2094 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 541: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.