SKILLEMALL.ai
GitHub ↗ RU Sign in

BF tencent-vod-intl

Tencent Cloud VOD (Video on Demand) command generation assistant. Must trigger whenever the user's request involves any VOD operation: [Upload] local/URL pull upload, expiration/SessionId/storage path; [Media Processing] transcode/TESHD/screenshot/sprite/enhance/real-person/drama/scene/remux/HLS/GIF/adaptive bitrate/review/procedure; [Media Query] FileId query details/transcode/subtitles/cover/metadata; [AIGC] text2img/text2video/img2video (Kling/Hunyuan/Vidu/GG/GV/Hailuo/MJ/Qwen/SI/OG/Jimeng/Mingmou/OS/Seedance/PixVerse), LLM chat (GPT/Gemini models, streaming), scene AIGC/outfit change/image expansion/product image/custom elements; [AIGC Audio] text-to-sfx/video-to-sfx/text-to-music/BGM/ASMR (Kling/MiniMaxMusic/GL); [AIGC Token/Usage] token management, usage stats; [Search] name/semantic/knowledge base; [Image] super-res/denoise/enhance/understand; [Sub-app/Task] sub-app query, task status. Do NOT trigger: MPS operations, COS direct upload, live streaming.

ClawHub Agent Skills author: tencent-mpaas-skills v1.1.3 MIT-0 42 files body ≈ 8 860 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 65/100 · Will not run — References files that are not bundled: URL, references/*.md

GeneratorMedia and videoAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
98
Quality 40%
65
Run on models
none yet
Process rating
F
65/100
Will not run
References files that are not bundled: URL, references/*.md
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Obfuscation obf-base64-blob scripts/vod_aigc_video.py:630
    Long base64-looking blob (detector / deny-list definition)
    help='JSON array of multiple reference images, format: [{"Type":"Url","Url":"...","Category":"Image","Usage":"Reference","Text":"pic1","ReferenceType":"subject"}]; supports all SDK fields: Type/FileId
    detector
  • low Secrets in code secret-high-entropy-token scripts/vod_scene_aigc_image.py:452
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    python3 vod_scene_aigc_image.py query --task-id "2510…xxx"
    quoted

Files scanned: 42. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8860 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: URL
  • warning missing-ref reference to a missing file: references/*.md

Process rating: all ten parameters 65/100

Will not run. References files that are not bundled: URL, references/*.md
  • 0Tools and files. 2 referenced file(s) missing: URL, references/*.md
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 19 mutating operations with no state check
  • 40Execution cost. Instruction body is 8860 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 42 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 (28 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)
  • +3Description length 972: 120–800 characters recommended
  • -249 emoji in the instructions: noise for the model
  • -31 of 20 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 42 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (18 of 18)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
The skill is mostly aligned with Tencent VOD workflows, but it automatically modifies local packages and persists or loads cloud credentials in ways users should review before installing.
LLM: suspicious (high) · 9 Aug 2026