SKILLEMALL.ai

BF nano-banana-2-runcomfy

Nano Banana 2 on RunComfy. Nano Banana 2 is Google's flash-tier text-to-image model in the Gemini family — fast iteration, predictable framing, in-image typography rendering, optional web-grounded context. This skill calls Nano Banana 2 through the RunComfy CLI: `runcomfy run google/nano-banana-2/text-to-image`. Nano Banana 2 is the right Nano Banana variant for marketing drafts, social thumbnails, and batch variants. Triggers on "nano banana", "nano-banana", "nano banana 2", "nano-banana-2", "Google Nano Banana", "Gemini image", or any explicit ask to generate with Nano Banana.

ClawHub Agent Skills author: mew v1.0.0 MIT-0 2 files body ≈ 3 040 tokens Open the sourceclawhub.ai analyzed 16 h ago

Nano Banana 2 on RunComfy.

As a process F 59/100 · Will not run — References files that are not bundled: ../nano-banana-edit

ProcedureAI and agentsSoftware developmentDesigntype and topics are labelled automatically from the skill text
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
69
Run on models
none yet
Process rating
F
59/100
Will not run
References files that are not bundled: ../nano-banana-edit
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
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.
  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: 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")
  • warning missing-ref reference to a missing file: ../nano-banana-edit
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "emoji"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "clawdis"

Process rating: all ten parameters 59/100

Will not run. References files that are not bundled: ../nano-banana-edit
  • 0Tools and files. 1 referenced file(s) missing: ../nano-banana-edit
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 27 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3040 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 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

  • +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
  • +5Description quotes 6 example trigger phrases
  • +3Description length 585: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 27 items
  • +4Has examples (7 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: clean
This skill is a disclosed RunComfy image-generation helper with one routing caveat: its trigger phrase for “Gemini image” is broader than the specific Nano Banana 2 model.
LLM: benign (high) · VirusTotal: · 27 Jul 2026