Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

image-generation

Sterne5

Forks0

Aktualisiert16. März 2026 um 13:12

Generate or edit images with Nano Banana 2 (Gemini 3.1 Flash Image). Use for any image create/modify requests. Supports text-to-image + image-to-image; 1K/2K/4K resolutions.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

mrtolkien

mrtolkien/GHOST

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Spezialeffektkünstler und AnimatorenKunst, Design, Unterhaltung, Sport und Medien·SOC 27-1014

Datei-Explorer

2 Dateien

SKILL.md

readonly

name	image-generation
description	Generate or edit images with Nano Banana 2 (Gemini 3.1 Flash Image). Use for any image create/modify requests. Supports text-to-image + image-to-image; 1K/2K/4K resolutions.

Image Generation (Nano Banana 2)

Generate new images or edit existing ones using Google's Gemini 3.1 Flash Image API.

Usage

Run the bundled script via shell. Images are saved to $WORKSPACE/tmp/.

Generate new image:

uv run {{skill_dir}}/scripts/generate_image.py --prompt 'your image description' --filename 'tmp/yyyy-mm-dd-hh-mm-ss-name.png'

Edit existing image:

uv run {{skill_dir}}/scripts/generate_image.py --prompt 'editing instructions' --filename 'tmp/yyyy-mm-dd-hh-mm-ss-name.png' --input-image 'path/to/input.png'

Resolution option: Append --resolution 1K|2K|4K (default: 1K).

Filename Convention

yyyy-mm-dd-hh-mm-ss-descriptive-name.png

Timestamp in 24-hour format
Descriptive lowercase text with hyphens (1-5 words)
Derive from the user's prompt or conversation context
If unclear, use a random identifier (e.g. x9k2)

Prompt Handling

For generation: Pass the OPERATOR's image description as-is to --prompt. Only rework if clearly insufficient.

For editing: Pass editing instructions in --prompt (e.g. "add a rainbow in the sky", "make it look like a watercolor painting").

Preserve the OPERATOR's creative intent in both cases.

Prompt Templates (for vague requests)

Generation: "Create an image of: . Style: . Composition: <camera/shot>. Lighting: <lighting>. Background: <background>. Color palette: <palette>. Avoid: <list>."
Editing (preserve everything else): "Change ONLY: . Keep identical: subject, composition/crop, pose, lighting, color palette, background, text, and overall style. Do not add new objects."

Common Failures

Error: No API key provided. -> set GEMINI_API_KEY in .env
Error loading input image: -> wrong path or unreadable file
403 / quota errors -> wrong key, no access, or quota exceeded

Output

Saves PNG to the specified path (always under $WORKSPACE/tmp/)
Script outputs the full path to the generated image
Do not read the image back — just inform the OPERATOR of the saved path

Mehr aus diesem Repository

gleiches Repository

db-migrations

mrtolkien/GHOST

SQLite migration rules for the Ghost codebase. MUST READ before writing or modifying any file in migrations/. Covers: table recreation patterns, column ordering, CHECK constraint changes, NOT NULL safety, and the validation checklist. A faulty migration that ships breaks the production daemon on startup with no recovery path short of manual DB surgery — these rules are non-negotiable.

2026-04-075

knowledge-navigator

mrtolkien/GHOST

Read when you need to browse, traverse, or query the knowledge system beyond basic knowledge_search — graph traversal, tag exploration, orphan detection, reference browsing, topic listing, or direct SQL access.

2026-04-075

reference-import

mrtolkien/GHOST

Import and update external content in the knowledge base — git repos, web crawls, documents (PDF, DOCX), and books (EPUB). Use when the OPERATOR wants persistent, searchable reference material from a git repository, website, document, or book, or when existing references may be stale and need refreshing.

2026-04-075

lua-scripting

mrtolkien/GHOST

Ghost's Lua scripting layer internals. MUST READ before modifying anything in src/scripting/, prompts/stdlib/, prompts/agents/*/agent.lua, or agent hook logic. Covers: ScriptHost VM lifecycle, sandbox, host globals, ctx bindings, nudge library, template module, custom tools, type stubs, and the PreTurnState contract.

2026-03-315

system-management

mrtolkien/GHOST

Use when reading or changing GHOST configuration (providers, models, timing, compaction, services, any config.toml key), adding or switching LLM providers, answering questions about GHOST's own features or capabilities, a CLI tool is missing or "not found", services need starting/stopping/debugging, updating GHOST to a newer version, managing the Nix shell environment, or troubleshooting GHOST setup.

2026-03-285

fix-feedback

mrtolkien/GHOST

Triage and fix issues reported via Ghost's /feedback command. MUST READ when the user points you to a feedback folder, mentions a feedback report, or asks you to investigate a bug that happened during a GHOST session. Covers: retrieving feedback from remote servers, reading transcripts and debug request dumps, root-cause categorization, and the fix workflow.

2026-03-265

name	image-generation
description	Generate or edit images with Nano Banana 2 (Gemini 3.1 Flash Image). Use for any image create/modify requests. Supports text-to-image + image-to-image; 1K/2K/4K resolutions.

Image Generation (Nano Banana 2)

Generate new images or edit existing ones using Google's Gemini 3.1 Flash Image API.

Usage

Run the bundled script via shell. Images are saved to $WORKSPACE/tmp/.

Generate new image:

uv run {{skill_dir}}/scripts/generate_image.py --prompt 'your image description' --filename 'tmp/yyyy-mm-dd-hh-mm-ss-name.png'

Edit existing image:

uv run {{skill_dir}}/scripts/generate_image.py --prompt 'editing instructions' --filename 'tmp/yyyy-mm-dd-hh-mm-ss-name.png' --input-image 'path/to/input.png'

Resolution option: Append --resolution 1K|2K|4K (default: 1K).

Filename Convention

yyyy-mm-dd-hh-mm-ss-descriptive-name.png

Timestamp in 24-hour format
Descriptive lowercase text with hyphens (1-5 words)
Derive from the user's prompt or conversation context
If unclear, use a random identifier (e.g. x9k2)

Prompt Handling

For generation: Pass the OPERATOR's image description as-is to --prompt. Only rework if clearly insufficient.

For editing: Pass editing instructions in --prompt (e.g. "add a rainbow in the sky", "make it look like a watercolor painting").

Preserve the OPERATOR's creative intent in both cases.

Prompt Templates (for vague requests)

Generation: "Create an image of: . Style: . Composition: <camera/shot>. Lighting: <lighting>. Background: <background>. Color palette: <palette>. Avoid: <list>."
Editing (preserve everything else): "Change ONLY: . Keep identical: subject, composition/crop, pose, lighting, color palette, background, text, and overall style. Do not add new objects."

Common Failures

Error: No API key provided. -> set GEMINI_API_KEY in .env
Error loading input image: -> wrong path or unreadable file
403 / quota errors -> wrong key, no access, or quota exceeded

Output

Saves PNG to the specified path (always under $WORKSPACE/tmp/)
Script outputs the full path to the generated image
Do not read the image back — just inform the OPERATOR of the saved path