plugins/handbook-nano-banana/skills/nano-banana-prompting/SKILL.md
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.
npx skillsauth add nikiforovall/claude-code-rules nano-banana-promptingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Interactive prompt crafting for Nano Banana Pro image generation. This skill guides users through a structured process to create effective prompts by clarifying intent and applying proven techniques.
Before asking questions, check if the user has provided:
If reference materials are available, this affects which techniques apply (e.g., Reference Role Assignment, Character Consistency).
Use the AskUserQuestion tool to understand the user's goal. Ask questions in batches of 2-4, focusing on the most important aspects first.
Output Type - What kind of image?
Subject - Who or what is the main focus?
If Photo/Realistic:
If Reference Images Provided:
If Text Needed:
If Educational/Infographic:
Based on user responses, select the appropriate prompt format from references/guide.md:
| User Need | Recommended Style | |-----------|-------------------| | Simple, quick generation | Narrative Prompt (Technique 1) | | Precise control over details | Structured Prompt (Technique 2) | | Era-specific aesthetic | Vibe Library + Photography Terms (Techniques 3-4) | | Magazine/poster with text | Physical Object Framing (Technique 5) | | Conceptual/interpretive | Perspective Framing (Technique 6) | | Diagram/infographic | Educational Imagery (Technique 7) | | Editing existing image | Image Transformation (Technique 8) | | Multiple views/panels | Multi-Panel Output (Technique 9) | | Multiple reference images | Reference Role Assignment (Technique 12) |
Construct the prompt by:
references/guide.md to access technique detailsPresent the generated prompt to the user with:
Offer to refine based on feedback.
After the user is satisfied with the prompt, recommend using the nano-banana skill to generate the actual image. Inform the user:
"Your prompt is ready! Would you like me to generate the image now? I can use the nano-banana skill to create it."
If the user agrees, invoke the nano-banana skill with the crafted prompt.
User wants... → Use Technique...
─────────────────────────────────────────────────────
Simple description → 1 (Narrative)
Detailed control → 2 (Structured YAML/JSON)
Specific era look → 3 (Vibe Library)
Professional photo style → 4 (Photography Terms)
Magazine/poster → 5 (Physical Object Framing)
"How X sees Y" → 6 (Perspective Framing)
Educational diagram → 7 (Educational Imagery)
Edit existing image → 8 (Image Transformation)
Multiple panels in one → 9 (Multi-Panel)
Exclude something → 10 (Negative Prompts)
Specific dimensions → 11 (Aspect Ratio)
Multiple reference images → 12 (Reference Roles)
Same character across images → 13 (Character Consistency)
Merge multiple images → 14 (Image Blending)
Enhance/restore image → 15 (Upscaling)
Translate text in image → 16 (Translation)
guide.md - Complete prompting guide with 16 techniques, examples, and patterns. Load this file when constructing prompts to access specific technique details and examples.development
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.
tools
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
tools
--- name: reflect description: Analyze a Claude Code session for "wrong-turn" moments (corrections, retries, waste, reversals, dead-ends) and produce an interactive HTML dashboard with copy-able recommendations (CLAUDE.md rules, docs, scripts, hooks, memory entries, sub-skills, etc.) that would help future agents reach the goal faster. Defaults to reflecting on the current in-context session; optionally accepts a session ID or JSONL path. Use when the user invokes /reflect or asks to learn from
tools
--- name: reflect-tree description: Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections, retries, reversals, and backtracking. Sibling to /reflect (which produces an incidents+recommendations dashboard); this one shows the journey itself. Defaults to the current in-context session; optionally accepts a session ID or JSONL path. Use when the user invokes /refl