SKILLEMALL.ai
GitHub ↗ RU Sign in

AF muse-video

When the user asks to 策划/构思/设计/写脚本/画分镜 for a video project — e.g. '帮我策划一个广告创意' '这个产品演示视频怎么拍' '帮我写科幻短片的分镜脚本' '给我这个品牌TVC的美术方向'。Not for actual video rendering/compositing or AI image/video generation.

ClawHub Hermes author: Jiang Yong Luo v1.0.1 MIT-0 67 files body ≈ 677 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

When the user asks to 策划/构思/设计/写脚本/画分镜 for a video project — e.g. '帮我策划一个广告创意' '这个产品演示视频怎么拍' '帮我写科幻短片的分镜脚本' '给我这个品牌TVC的美术方向'。Not for actual video…

As a process F 37/100 · Will not run — References files that are not bundled: references/roles/<name>.md

ProcedureMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
F
37/100
Will not run
References files that are not bundled: references/roles/<name>.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 197 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: references/roles/<name>.md

Process rating: all ten parameters 37/100

Will not run. References files that are not bundled: references/roles/<name>.md
  • 0Tools and files. 1 referenced file(s) missing: references/roles/<name>.md
  • 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
  • 0Consistency. Frontmatter name (muse-video) differs from the folder (muse-video-skill)
  • 0Progress reporting. Says nothing while it works
  • 100Steps. 24 steps
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 677 tokens
  • 100Running it twice. No mutating operations

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
  • +3Output format is not stated: the model decides each time
  • -33 of 6 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 197: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
This video-planning skill is mostly creative tooling, but it also tells agents to call image-generation tools, prepare execution-ready generator configs, and update/push repository content despite describing itself as non-generation planning.
LLM: suspicious (high) · 12 Jun 2026