SKILLEMALL.ai
GitHub ↗ RU Sign in

CF nx-matting

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除，并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片，或 MP4/MOV/WebM 视频的场景；无需 Python、PyTorch 或 CUDA。

ClawHub Agent Skills author: xiaowu89 v0.1.0 MIT-0 11 files · 1 script body ≈ 640 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除，并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片，或 MP4/MOV/WebM 视频的场景；无需…

As a process F 28/100 · Will not run — References files that are not bundled: assets/bin/windows-x64/

ProcedureSoftware developmenttype 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
C
66/100
safety, quality, tests
Safety 60%
63
Quality 40%
70
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: assets/bin/windows-x64/
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  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 · 9

✓ No critical or high findings

Medium and low: 9
  • medium Dangerous commands cmd-execpolicy-bypass README.md:32
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "scripts/matting.ps1" image `
  • medium Dangerous commands cmd-execpolicy-bypass README.md:36
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "scripts/matting.ps1" video `
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:56
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" image `
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:61
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" image `
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:66
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" video `
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:70
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" video `
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:88
    Runs PowerShell with execution policy bypassed
    powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" doctor
  • low Obfuscation obf-base64-blob scripts/matting.ps1:41
    Long base64-looking blob (quoted — discussed, not commanded)
    "5rip6aao5o+Q6Ya…5L2/55So…5Zu+5Yqf…Y6K+35re…DI2"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/matting.ps1:41
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "5rip6aao5o+Q6Ya…5L2/55So…5Zu+5Yqf…Y6K+35re…DI2"
    quoted

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: assets/bin/windows-x64/

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: assets/bin/windows-x64/
  • 0Tools and files. 1 referenced file(s) missing: assets/bin/windows-x64/
  • 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. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (nx-matting) differs from the folder (skill-matting)
  • 100Steps. 24 steps
  • 100Execution cost. Instruction body is 640 tokens

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
  • +2Single-language instructions
  • +3Description length 176: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (2 code blocks)
  • +3All 1 scripts are documented
  • +1License stated

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

External checks

ClawHub: suspicious
This skill mostly performs local image and video background removal, but it also forces an unrelated contact notice into user-facing replies and uses execution-adjacent downloads that deserve review before installation.
LLM: suspicious (high) · VirusTotal: · 6 Aug 2026