SKILLEMALL.ai
GitHub ↗ RU Sign in

BF gemini-watermark-remover

Remove visible Gemini AI watermarks from images via reverse alpha blending. Use for cleaning Gemini-generated images, removing the star/sparkle logo watermark.

ClawHub Agent Skills author: FZLR v1.1.2 6 files body ≈ 428 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 33/100 · Will not run — References files that are not bundled: assets/bg_48.png, assets/bg_96.png

GeneratorInfrastructureDesigntype 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
89/100
safety, quality, tests
Safety 60%
96
Quality 40%
78
Run on models
none yet
Process rating
F
33/100
Will not run
References files that are not bundled: assets/bg_48.png, assets/bg_96.png
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. 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 · 4

✓ No critical or high findings

Medium and low: 4
  • low Obfuscation obf-base64-blob scripts/remove_watermark.py:22
    Long base64-looking blob (quoted — discussed, not commanded)
    BG_4…E64 = """iVBO…NxD+FvKM…7qy/Ab2o/gNmC…zgA++HbH2…BiB/RYgo+hkGSF
    quoted
  • low Secrets in code secret-high-entropy-token scripts/remove_watermark.py:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    BG_4…E64 = """iVBO…NxD+FvKM…7qy/Ab2o/gNmC…zgA++HbH2…BiB/RYgo+hkGSF
    quoted
  • low Obfuscation obf-base64-blob scripts/remove_watermark.py:24
    Long base64-looking blob (quoted — discussed, not commanded)
    BG_9…E64 = """iVBO…ABt+uBvA…saM/Ckjd…vbG/ibparBGjwzpnF+bjnv…U2H
    quoted
  • low Secrets in code secret-high-entropy-token scripts/remove_watermark.py:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    BG_9…E64 = """iVBO…ABt+uBvA…saM/Ckjd…vbG/ibparBGjwzpnF+bjnv…U2H
    quoted

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: assets/bg_48.png
  • warning missing-ref reference to a missing file: assets/bg_96.png

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: assets/bg_48.png, assets/bg_96.png
  • 0Tools and files. 2 referenced file(s) missing: assets/bg_48.png, assets/bg_96.png
  • 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. 6 mutating operations with no state check
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 428 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 159: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 13 items
  • +4Has examples (4 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This skill appears to work as advertised, but its advertised purpose is to strip visible AI provenance watermarks before possible sharing or publishing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026