메뉴
Generate images with OpenAI's gpt-image models. Use when the user asks you to create, draw, make, design, or generate a picture, image, illustration, logo, diagram, or artwork. Saves the result to the group workspace and delivers it via send_file.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Build and publish a website. Use whenever the user asks to make, create, build, or publish a website, landing page, dashboard, status page, one-pager, or anything else a human will load in a browser. Covers both the publish recipe (no tunnels, no third-party hosts) and the design discipline that keeps the result from looking like generic AI slop.
Use for Clemson GC curriculum content questions — what a specific course teaches, what skills or projects it includes, what assignments are used, where a topic or learning outcome is covered, and how courses relate to each other pedagogically. This is about course *content*, not degree rules or credit requirements (use gc-advisor for those).
Use for ANY Clemson procurement or purchasing question — what's allowed or required, policy, rules, P-card, requisitions, purchase orders, suppliers, approvals, spending limits, bids/quotes. Use the procurement tools; never answer Clemson procurement from your own knowledge.
Use for Clemson class schedules and instructor scheduling — finding course sections, what an instructor is teaching, section details (time/seats/location), room availability, and academic terms. Use these tools, not your own knowledge.
Use for questions about Clemson Graphic Communications alumni outcomes — where graduates work now, first-job placement, career trajectories, AI exposure of GC occupations, industry/occupation distribution, grad-school rates, and outcome trends by graduation cohort. Data comes from the gc-alumni MCP server (read-only SQLite). For degree rules or course content use gc-advisor or clemson-curriculum instead.
Use for Clemson GC degree rules and academic requirements — degree audit (which requirements has a student met?), credit counts, gen-ed rules, specialty-area rules, prerequisite checking, course planning, and academic regulation lookups. This is about *rules and requirements*, not course content or pedagogy (use clemson-curriculum for what a course teaches, its skills/projects/assignments). Always pulls from the pinned catalog database — never from memory or the live website.
| name | image-gen |
| description | Generate images with OpenAI's gpt-image models. Use when the user asks you to create, draw, make, design, or generate a picture, image, illustration, logo, diagram, or artwork. Saves the result to the group workspace and delivers it via send_file. |
Generate images using OpenAI's gpt-image model family. The result is saved to the group's workspace as a PNG and then sent to the user as a file attachment.
Do NOT use this for image editing of an uploaded photo — this skill only does text-to-image generation.
Call the generator with Bash:
node /home/node/.claude/skills/image-gen/generate.js \
--prompt "a watercolor of a koala drinking coffee" \
--model gpt-image-2 \
--size 1024x1024 \
--output /workspace/group/generated/koala.png
The script prints the output path to stdout on success. On failure it exits non-zero and writes the error to stderr (typically an OpenAI API message).
--prompt (required) — text description of the image.--model (default gpt-image-2) — pick one:
gpt-image-2 — highest quality, default. Requires a verified OpenAI
organization. If you see a "must be verified" error, fall back to
gpt-image-1.5 and tell the user they can verify at
platform.openai.com/settings/organization/general.gpt-image-1.5 — fast and broadly available, good fallback.gpt-image-1 — previous generation, still capable.gpt-image-1-mini — fastest, cheapest.dall-e-3 — legacy, only if the user asks for it by name.--size (default 1024x1024) — 1024x1024, 1792x1024 (landscape),
or 1024x1792 (portrait).--output (required) — absolute path where the PNG should be saved.
Put files under /workspace/group/generated/ so the group stays tidy.After the script succeeds, send the file with the send_file MCP tool:
mcp__nanoclaw__send_file({
file_path: "/workspace/group/generated/koala.png",
caption: "Your watercolor koala"
})
Include a short caption that references what was requested so the user has context alongside the image.
gpt-image-2 unless the user has indicated a preference.gpt-image-2 returns a verification error, retry with
gpt-image-1.5 and note the fallback in your reply.gpt-image-1-mini./workspace/group/generated/ (create if missing — the
script handles this).koala.png,
sales-pipeline-dashboard.png.koala-1.png, koala-2.png.gpt-image-2 on unverified orgs.
Fall back to gpt-image-1.5 and tell the user what to do.