siliconflow-photo-reply
Generate an edited photo with SiliconFlow and send it back to the current channel.
Skill by cuichuankai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cuichuankai-siliconflow-photo-reply
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/siliconflow-photo-reply
What's inside
- Skill name
siliconflow-photo-reply- Description
- Generate an edited photo with SiliconFlow and send it back to the current channel. Invoke when user asks for your photo or requests a scene-style self photo.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- generate_photo.sh · scripts/
SKILL.md (first lines)
# SiliconFlow Photo Reply
## When to use
Use this skill immediately when the user asks for a photo, especially requests like:
- “发一下你在锻炼的照片”
- “发一张你在做饭的照片”
- “来一张你在办公室的自拍”
## Behavior
1. Convert the user request into a concise scene context, such as:
- `working out in a gym`
- `cooking dinner in a modern kitchen`
- `sitting in an office with laptop`
2. Run:
```bash
bash .primagen/skills/siliconflow-photo-reply/scripts/generate_photo.sh "<scene-context>"
```
3. The script prints one absolute local image path on success.
4. Send the image back with `send_message` using:
- `content`: short confirmation text
- `attachments`: `[{"type":"image","path":"<script-output-path>"}]`
5. If the script fails:
- Read the tool output and use the actual stderr reason in your reply.
- Retry once with a simpler scene context.
- If retry still fails, return a short failure message including the key error text.
## Notes
- Requires environment variable `SILICONFLOW_API_KEY`.
- Never print or send API keys.
- If generation fails, reply with a short failure message and ask user to retry.From cuichuankai/Primagen, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 24, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cuichuankai/Primagen
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cuichuankai
Cite this page
siliconflow-photo-reply skill. Agent Mart. https://agentmart.dev/skills/cuichuankai-siliconflow-photo-reply (last updated 2026-10-24)