CC topic-to-video
Turn ANY topic — or a slide deck — into a narrated explainer short video, automatically: researches the topic, writes and voices the script, designs and builds the visuals (cinematic Remotion tier or HTML pages; a deck's slides full-frame with gentle motion and timed callouts) and burns in captions. Any language; can voice a deck in a different language than its slides. Use whenever the user wants a short video about a subject or from slides — e.g. "make a video explaining how MRI works", "make a launch video for this product", "做一个讲解视频介绍X", "turn these slides into a video", "narrate my pptx", "add a voiceover to my slides", "把幻灯片做成视频", "把英文幻灯片配成中文解说视频". Accepts a topic, .pptx, .pdf, an image folder, or a hand-off from slide-maker. Free by default (edge-tts + ffmpeg); optional cloud TTS. Editable storyboard, a sample for sign-off, then the full video. Trigger even without the word "skill".
Turn ANY topic — or a slide deck — into a narrated explainer short video, automatically: researches the topic, writes and voices the script, designs and…
As a process C 60/100 · Has gaps — References files that are not bundled: scripts/_common.have_tool, scripts/pptx_theme.py, scripts/tier_advice.py
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/tts.py:115Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 47742 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/_common.have_tool - warning
missing-refreference to a missing file: scripts/pptx_theme.py - warning
missing-refreference to a missing file: scripts/tier_advice.py - warning
missing-refreference to a missing file: scripts/remotion_segments.py - warning
missing-refreference to a missing file: scripts/device_script.py - warning
missing-refreference to a missing file: scripts/shot_director.PROVENANCE - warning
missing-refreference to a missing file: scripts/dna_migrate.py - warning
missing-refreference to a missing file: scripts/cues.py - warning
missing-refreference to a missing file: scripts/clock_qa.py - warning
missing-refreference to a missing file: assets/fonts/NOTO-SC-SUBSET-NOTE.txt - warning
missing-refreference to a missing file: scripts/onscreen_text_qa.py - warning
missing-refreference to a missing file: scripts/scenes.py - warning
missing-refreference to a missing file: assets/html/base.css - warning
missing-refreference to a missing file: scripts/_cdp.py - warning
missing-refreference to a missing file: scripts/sources.py - warning
missing-refreference to a missing file: assets/brand/ - warning
missing-refreference to a missing file: assets/fonts/ - note
edit-residuethe text marks something as outdated (lines 445, 474): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 60/100
- 0Tools and files. 17 referenced file(s) missing: scripts/_common.have_tool, scripts/pptx_theme.py, scripts/tier_advice.py
- 10Execution cost. Instruction body is 47742 tokens: crowds the task out of the window
- 30Running it twice. 62 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 120 steps, 3 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 15 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (139 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 902: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -234 emoji in the instructions: noise for the model
- -37 of 37 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 120 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (17 of 22)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.