SenseNova Environment Doctor

What it does

When your agent uses it

• Setting up SenseNova-Skills for the first time
• A SenseNova skill fails because of a missing dependency or API key
• Verifying the environment after changing the gateway URL or keys

Example prompts

• “Run the SenseNova environment check and tell me what is missing.”
• “My SenseNova image skill says the API key is not set. Diagnose the setup.”
• “Configure the SenseNova API variables in .env and reload the environment.”

Requirements

• Python
• The SenseNova-Skills project with `sn-image-base`
• A SenseNova API key and base URL

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Verify network connectivity
2. 2Check firewall settings
3. 3Verify API endpoint URLs are correct
4. 4Test with curl

What it can do on your machine

Read from SKILL.md and the folder at commit 7838651. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • token.sensenova.cn

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SN_API_KEY
  • SN_CHAT_API_KEY
  • SN_IMAGE_GEN_API_KEY
  • SN_TEXT_API_KEY
  • SN_VISION_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SenseNova Environment Doctor loads about 1.4k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 249 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~87

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:7

  them to .env file. After configuration, reloads environment and suggests agent restart if needed.

• NoteMentions a .env fileSKILL.md:33

  ing required variables and save them to `.env`

• NoteMentions a .env fileSKILL.md:66

  er values below to save them to /path/to/.env.

• NoteMentions a .env fileSKILL.md:71

  ✅ Saved to /path/to/.env: SN_API_KEY

• NoteMentions a .env fileSKILL.md:82

  ✅ Saved to /path/to/.env: SN_API_KEY

• NoteMentions a .env fileSKILL.md:151

  # Or create a .env file

• NoteMentions a .env fileSKILL.md:152

  cat > .env << EOF

• NoteMentions a .env fileSKILL.md:159

  # Load .env file

• NoteMentions a .env fileSKILL.md:160

  source .env  # Or use a tool like python-dotenv

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenSenseNova/SenseNova-Skills at commit 7838651, republished under its MIT licence (© OpenSenseNova). 249 words, ~1,389 tokens.

name

sn-image-doctor

description

Environment diagnostic skill for SenseNova-Skills project. Checks that sn-image-base is properly installed and configured, validates dependencies and environment variables. Prompts user to configure missing required variables and saves them to .env file. After configuration, reloads environment and suggests agent restart if needed.

triggers

SenseNova-Skills环境检查, SenseNova-Skills doctor, sn环境检查, sn-image-doctor, environment check, health check, 诊断环境

metadata.project

SenseNova-Skills

metadata.tier

0

metadata.category

infrastructure

metadata.user_visible

true

# Basic check
python scripts/check_environment.py

# Verbose output with detailed diagnostics
python scripts/check_environment.py --verbose

=== SenseNova-Skills Environment Check ===

[1/3] Checking sn-image-base installation...
  ✅ Installation looks good

[2/3] Checking Python dependencies...
  ✅ Python 3.11.0
  ✅ All required packages installed

[3/3] Checking environment variables...
  ❌ SN_IMAGE_GEN_API_KEY: Image generation API key is not set; configure SN_API_KEY, or configure SN_IMAGE_GEN_API_KEY only for an image-generation-specific override

  Some required environment variables are missing.
  Enter values below to save them to /path/to/.env.
  Press Enter to skip a variable.

  SN_API_KEY: <user input>

  ✅ Saved to /path/to/.env: SN_API_KEY
  🔄 Reloading environment...
  ✅ Environment reloaded successfully

=== Summary ===
✅ Environment is properly configured

  ✅ Saved to /path/to/.env: SN_API_KEY
  🔄 Reloading environment...
  ⚠️  Failed to reload environment: <error message>
  💡 Suggestion: Restart the agent to apply new configuration

=== SenseNova-Skills Environment Check ===

[1/3] Checking sn-image-base installation...
  ❌ sn-image-base directory not found
  Expected location: /path/to/skills/sn-image-base

[2/3] Checking Python dependencies...
  ❌ Missing packages: httpx, pillow
  Run: pip install -r skills/sn-image-base/requirements.txt

=== Summary ===
❌ Environment check failed
Please fix the errors above before using SenseNova-Skills.

# Ensure you're in the project root
cd /path/to/SenseNova-Skills

# Verify the directory exists
ls -la skills/sn-image-base

# Install dependencies
pip install -r skills/sn-image-base/requirements.txt

# Or use a virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r skills/sn-image-base/requirements.txt

# If all capabilities use the same gateway, set only the global values.
export SN_API_KEY="your-api-key"
export SN_BASE_URL="https://your-api-endpoint.com"

# Or create a .env file
cat > .env << EOF
SN_API_KEY=your-api-key
SN_BASE_URL=https://token.sensenova.cn/v1
SN_CHAT_TYPE=openai-completions
SN_CHAT_MODEL=sensenova-6.8-flash-lite
EOF

# Load .env file
source .env  # Or use a tool like python-dotenv

# 1. Run doctor check
python skills/sn-image-doctor/scripts/check_environment.py

# 2. If checks pass, use other skills
python skills/sn-image-base/scripts/sn_agent_runner.py sn-image-generate \
    --prompt "A beautiful landscape"

© OpenSenseNova, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/sn-image-doctor of OpenSenseNova/SenseNova-Skills.

• SKILL.md
• scripts/check_environment.py

Open the folder on GitHubat commit 7838651