SKILLEMALL.ai
GitHub ↗ RU Sign in

BB ad-designer

Generate marketing ad images using Nano Banana Pro (Gemini 3 Pro Image). Accepts campaign-planner creative briefs, reads brand bible for visual style, constructs marketing-optimized prompts, and produces platform-ready images at correct aspect ratios. Supports 1:1, 9:16, 16:9, 4:5 formats. Includes self-review loop to catch hallucinated logos, wrong text, and quality issues. Draft-first workflow (1K fast iteration, 4K final). Outputs to /tmp/marketing/assets/images/.

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 3 045 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Generate marketing ad images using Nano Banana Pro (Gemini 3 Pro Image).

As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice

GeneratorAI and agentsMarketingtype 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
86/100
safety, quality, tests
Safety 60%
98
Quality 40%
68
Run on models
none yet
Process rating
B
70/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:29
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    If `uv` is missing: tell the user to install it with `curl -LsSf https://astral.sh/uv/install.sh | sh`.
    quoted
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:280
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation table row)
    | `uv: command not found` | Run `curl -LsSf https://astral.sh/uv/install.sh | sh` then retry |
    table

Files scanned: 2. 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")

Process rating: all ten parameters 70/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 2 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 100Steps. 30 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3045 tokens
  • 100Progress reporting. Reports progress
  • low 12 top-level sections: this looks like several domains in one skill

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
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +3Description length 471: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.