DC explainer
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Turn an article, doc or release note into a short explainer clip — one person to camera, or a voiceover over illustrative footage. The user supplies the source text and the model generates the speech; audio cannot be uploaded, measured. A 30-second clip holds about eighty spoken words in eight sentences — measured, and well under a tenth of a 1,200-word post — so this skill does not summarise an article, it picks the single idea worth saying and helps choose which one. Use when a user asks to turn writing into a short spoken video, e.g. "make a 30-second explainer from this blog post", "explain this feature in a short video", "turn our changelog into a clip", "a quick video explaining what this paper found". Do not use for a scene between people (see seedance-short-drama), a brand or product ad (see seedance-ad-creative), a handheld creator clip (see ugc-ads), or when the user already has both a portrait and the finished words (see talking-head). Budget sentences as well as words — each sentence boundary costs about 0.7 seconds of silence, so a script with more sentences runs longer at the same word count.
Requires OFOXAPIKEY — create one at https://app.ofox.ai. Turn an article, doc or release note into a short explainer clip — one person to camera, or a…
As a process C 51/100 · Has gaps — References files that are not bundled: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md
How to improve
- Shorten the description to 1024 characters.
- 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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1182 chars, limit 1024 - warning
body-longSKILL.md body ≈ 14034 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../ofox-video-core/SKILL.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/prompt-structure.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/creative-brief.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/approval-gate.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/api-params.md - warning
missing-refreference to a missing file: ../shorts-reels/SKILL.md - warning
missing-refreference to a missing file: references/*.md - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 205): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 51/100
- 0Tools and files. 7 referenced file(s) missing: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 25 mutating operations with no state check
- 40Execution cost. Instruction body is 14034 tokens: crowds the task out of the window
- 100Steps. 35 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 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 23 top-level sections: this looks like several domains in one skill
- 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
- +3Description length 1182: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 38 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (12 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.