gpt2api-image-generator
GPT2API Image Generator
Overview
Use this skill for direct image-generation and direct image-edit requests. It
calls the configured GPT2API public image endpoints, stores generated images
under .run/artifacts/generated/, and returns local artifact paths that can be
sent with reply-current --image.
Do not answer image-generation requests with text only unless generation fails. Do not use GPT2API session APIs for this skill.
Config
The private config lives at:
.bridge-private/gpt2api-image.json
That directory is gitignored. The required fields are:
More from acking-you/codex-bridge
reply-current
Use when a Codex turn running inside codex-bridge must send normal results back to the active QQ conversation as text, image, or file
1invoke-capability
Call another registered model (Claude via Kiro, Gemini images, ...) to produce this turn's reply, keeping Codex as the harness but letting a better-suited model own the actual voice. Use liberally for conversational / emotional / creative turns; Codex's own voice is a poor fit for most QQ chat.
1qq-current-history
Query normalized QQ message history for the current conversation only, with optional time, sender, keyword, and free-form filters
1qq-quoted-image-recovery
Use when a quoted QQ message likely contained an image or screenshot but the bridge only exposed a quote marker or flattened text
1staticflow-kiro-log-diagnoser
Use when a Codex turn needs to diagnose StaticFlow Kiro upstream failures by reading the backend error log and correlating real usage events through sf-cli
1