CommunityBildgithub.com

getedgehq/generate-image

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

Was ist generate-image?

generate-image is a Codex agent skill that generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

Funktioniert mit~Claude CodeCodex CLI~Cursor
npx skills add https://github.com/getedgehq/skills/tree/main/generate-image

Installed? Explore more Bild skills: steipete/songsee, affaan-m/frontend-design-direction, affaan-m/ios-icon-gen · View all 6 →

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Generate Image

Creates images via OpenAI GPT Image 2. Auth runs through the Codex CLI logged in with a ChatGPT account, so generation is covered by the user's Plus subscription. There is no OpenAI API key and no separate per-image API billing.

Before you start

This Skill does not talk to OpenAI directly. It shells out to the Codex CLI, and that CLI has to already be installed on this machine and already signed in to a ChatGPT account with an active Plus subscription. Check with codex --version and run codex login if it is not signed in. There is no API key to paste, and no separate per-image charge; the images are billed to that subscription.

Without a signed-in Codex CLI nothing here works, and the script fails at the first call rather than producing a file.

Quick start

# from this Skill's own directory, wherever your agent installed it
./scripts/generate-image.sh "a shiba inu wearing sunglasses, studio photo"

Saves to the resolved output folder (see below) as a slugified PNG, e.g. assets/images/a-shiba-inu-wearing-sunglasses-studio-photo.png.

Workflow

  1. Turn the user's request into a strong English prompt. Follow the build order and levers in PROMPTING.md (scene → subject → details → invariants → use). Refine vague requests before calling; do not pass a bare one-liner when the asset matters.
  2. Run the script with the prompt. Optionally pass --out and --name.
  3. Report the saved path back to the user. For changes, iterate in small single-variable steps and restate the invariants (see PROMPTING.md).

Output location

When --out is not given, the script resolves the folder automatically:

ConditionTarget folder
./public/ exists (web/app initiative)./public/images/
otherwise./assets/images/ (created if missing)

This establishes a consistent assets/images/ convention across projects while respecting web projects, where images must live under public/ to be served.

Options

FlagEffect
--out <dir>Write into this directory instead of the resolved default
--out <file>.pngWrite to this exact file path
--name <basename>Use this basename instead of slugifying the prompt

Existing files are never overwritten: the script appends -2, -3, ... instead.

Deliverable naming

These outputs are work assets, so they get short functional names by default. If an image is a stakeholder deliverable, pass an explicit --name following the file-naming rule, e.g. --name "20260612_Hero Banner_v1".

Requirements

  • codex CLI installed (brew install --cask codex)
  • Logged in with a ChatGPT account: codex login (Plus or higher; image generation is not available on Free)

The script checks both and fails with a clear message if either is missing.

Individual skills in this repo

This repo contains 15 individual skills — each has its own dedicated page.

getedgehq/agent-evals

Build evals for an AI agent that already does real work. Use when someone asks "how do I know my agent is right", wants to test an agent before trusting it, compare models on cost versus quality, or turn production failures into tests. Walks from first tasks and yes/no verifiers, to isolated environments, to a trace-driven improvement loop.

getedgehq/cli-ux-review

Audit a command-line tool for user-friendliness — clear situation / next-step / options in every output, colour-highlighted runnable commands, no raw jargon, no silent hangs. Invoke for "CLI UX audit", "review my CLI", "is this CLI intuitive", or before any CLI release.

getedgehq/harness-first

Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set, judge, cost caps, data layer, action approvals, tracing) before blaming or swapping the model. Use when someone says an agent is "burning tokens", "hallucinating", "brittle", gives inconsistent answers, asks whether to switch to a cheaper/better model, or wants to ship an agent or prompt change to customers.

getedgehq/http-error-triage

Run before concluding anything from an HTTP error on a third-party API. Separates a real credential/entitlement problem from a CDN or WAF block, a wrong endpoint, or a client-signature ban. Use whenever an API returns 401/403/402/429 and you are about to say "the key is dead", "credits are exhausted", "the plan lacks access", or "we are rate limited".

getedgehq/linkedin-media-prep

Convert, crop, resize, and compress images and videos for optimal LinkedIn upload quality and file size. Use when the user wants to prepare a photo, image, or video for LinkedIn (profile picture, cover photo, post image, article featured image, post video, or video ad), optimize file size for LinkedIn, crop and resize for LinkedIn dimensions, convert HEIC/RAW/PNG/MOV to LinkedIn-ready JPEG or MP4, or mentions LinkedIn media requirements, specs, or limits.

getedgehq/monid

>-

getedgehq/opendraft

An 18-agent pipeline that turns one topic line into a drafted

getedgehq/people-search

Find and rank professional people for recruiting, partnerships, sales, or research from user-provided data, public web sources, an authenticated search session, or a connected provider. Use for people discovery, LinkedIn or Sales Navigator search design, profile-list ranking, or provider filter translation.

getedgehq/product-launch-video

Turn a product URL, launch brief, or approved script into a production-ready launch video. Use for product reveals, feature announcements, SaaS launches, and narrated product films; not for generic explainers or editing existing footage.

getedgehq/rocketlist

Turn a CV into a shortlist of live startup roles from Rocketlist's public job board, including adjacent job titles the person would never have searched for, each with its published salary, the evidence for the fit, and a direct apply link. Use for "find roles I would be a strong fit for", career pivots, remote or VC-backed job hunts, and salary-visible role discovery.

getedgehq/security-audit-checklist

Run a comprehensive security audit across application code, cloud infrastructure, containers, CI/CD pipelines, and infrastructure-as-code. Covers privacy compliance, OWASP basics, secret leakage, API security, IAM misconfigurations, storage exposure, Kubernetes hardening, and network security. Use when the user asks to audit, review, or harden app or cloud security, check for secrets, scan for XSS/SQLi, verify security headers, review Terraform/CloudFormation, audit AWS/GCP/Azure configs, or perform any security-focused review.

getedgehq/shadcn-first

>-

getedgehq/strip-image-ai-metadata

Strip C2PA and AI-generation metadata from images (PNG, JPEG, WebP) to remove "Generated by AI" / "ChatGPT" / "DALL-E" labels that platforms like LinkedIn, Instagram, and X display. Use when the user wants to clean AI-generated images before posting, remove AI attribution from photos, strip C2PA manifests, sanitize image metadata for professional use, or verify whether an image contains C2PA data.

getedgehq/top-down-comms

>-

getedgehq/workplan

Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects

Verwandte Skills