Yuxi is a self-hosted, multi-tenant knowledge-agent platform that combines document retrieval, knowledge graphs, multi-agent workflows, tools, sandboxes, and access controls in one workspace. Teams use it to build source-backed question answering and multi-step agents while managing their data, models, and permissions. The catalogue entries provide agents, skills, and instructions for Yuxi workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xerrors/Yuxi --skill image-gengit clone --depth 1 https://github.com/xerrors/YuxiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xerrors/yuxi/image-gen)<a href="https://agentmods.dev/skills/xerrors/yuxi/image-gen"><img src="https://agentmods.dev/badge/skills/xerrors/yuxi/image-gen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xerrors/yuxi/image-gen"><img src="https://agentmods.dev/badge/skills/xerrors/yuxi/image-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 14 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 46 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 45 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 45 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00873 |
| Opus 5.5 | $0.00019 | $0.00349 |
| Sonnet 5.5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade B, and why
image-gen scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "https://api.siliconflow.cn/v1/images/generations", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post( How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
图片生成技能
当用户要求生成图片、海报、插画、文生图,或明确提到 Qwen-Image 时,使用此技能组织图片生成流程。
默认生成接口
默认使用 SiliconFlow 的 Qwen-Image 接口:
- Endpoint:
POST https://api.siliconflow.cn/v1/images/generations - Model:
Qwen/Qwen-Image - 默认参数:
negative_prompt:""num_inference_steps:20guidance_scale:7.5
调用外部接口时,必须在 Agent 沙盒执行环境中读取 SILICONFLOW_API_KEY。不要依赖后端进程环境变量。
操作流程
- 明确用户要生成的图片内容、风格、尺寸或约束;信息不足但不影响生成时,使用合理默认值,不要反复追问。
- 使用可用的执行工具在沙盒中运行脚本,调用图片生成接口,传入用户需求整理后的
prompt,并按需传入negative_prompt、num_inference_steps、guidance_scale。 - 从生成接口响应中读取图片地址,默认路径为
images[0].url。 - 在同一个沙盒脚本中用
Authorization: Bearer $SILICONFLOW_API_KEY下载该图片地址;如果接口直接返回 base64,则直接解码保存。 - 将最终图片保存到当前 Workdir 的
outputs/下,例如outputs/generated-image.png。 - 调用
present_artifacts,传入保存后的 outputs 虚拟路径,让前端展示图片产物。 - 最终回复简要说明图片已生成,不要把外部临时 URL 当作最终结果展示。
脚本示例
可根据用户需求调整 prompt 和输出文件名:
import os
import requests
from pathlib import Path
api_key = os.environ["SILICONFLOW_API_KEY"]
prompt = "根据用户需求整理后的图片提示词"
response = requests.post(
"https://api.siliconflow.cn/v1/images/generations",
headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
json={
"model": "Qwen/Qwen-Image",
"prompt": prompt,
"negative_prompt": "",
"num_inference_steps": 20,
"guidance_scale": 7.5,
},
timeout=120,
)
response.raise_for_status()
image_url = response.json()["images"][0]["url"]
image_response = requests.get(
image_url,
headers={"Authorization": f"Bearer {api_key}"},
timeout=120,
)
image_response.raise_for_status()
output_path = Path("outputs/generated-image.png")
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_bytes(image_response.content)
print(output_path.as_posix())
多模型扩展
如果用户指定其它图片生成模型或兼容接口,可以按该接口的协议先生成图片。只要最终拿到图片 bytes 或 base64,就保存到当前 Workdir 的 outputs/,再调用 present_artifacts 展示。
关键约束
- 不要把外部生成接口返回的临时 URL 当作最终结果直接展示给用户。
- 不要调用后端 MinIO 上传工具;图片生成和下载都应在沙盒内完成。
- 如果
SILICONFLOW_API_KEY缺失,应明确提示用户需要在 Agent 沙盒环境变量中配置。 - 保存到 outputs 后必须调用
present_artifacts,否则前端不会自动展示生成图片。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +2 lines f86f7f02c03d
- 1mo ago First seen · 83 lines · 48 tokens per session scan B 667165f2a46d
image-gen is a skill published in the GitHub repository xerrors/Yuxi (7,434 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 873 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…
reviewing-blogs
Reviews and critiques blog posts in src/content/blog/posts/ against Appwrite's established standards for voice, tone, structure, SEO, formatting, and accuracy. Use when the user asks to review, audit, critique, or improve an existing blog post.
first-reader
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…