rei
- Repo stars 39
- Author updated Live
- Author repo awesome-omni-skill
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @diegosouzapw · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Required · Vendor-specific
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: rei
description: Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei t…
category: ai
runtime: no special runtime
---
# rei output preview
## PART A: Task fit
- Use case: Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints. Rei is served via an OpenAI-compatible endpoint at coder.reilabs.org. requires Vendor-specific API key. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Setup via Script / Setup via Agent / Switching Models” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints. Rei is served via an OpenAI-compatible endpoint at coder.reilabs.org. requires Vendor-specific API key. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Setup via Script / Setup via Agent / Switching Models” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
## Running Rules
- read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/model`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Setup via Script / Setup via Agent / Switching Models”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: rei
description: Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei t…
category: ai
source: diegosouzapw/awesome-omni-skill
---
# rei
## When to use
- Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or trouble…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Setup via Script / Setup via Agent / Switching Models” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "rei" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Setup via Script / Setup via Agent / Switching Models
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | may access external network resources
guardrails -> requires Vendor-specific API keys + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Rei
Rei is served via an OpenAI-compatible endpoint at coder.reilabs.org.
Setup via Script
./skills/rei/scripts/setup.sh YOUR_REI_API_KEYThis adds the provider, adds it to the model allowlist, and restarts the gateway.
Setup via Agent
Ask your agent:
"Set up Rei with API key: YOUR_KEY"
The agent will read this skill and run the setup script for you.
Switching Models
Via chat:
/model rei
/model opusVia script:
./skills/rei/scripts/switch.sh rei
./skills/rei/scripts/switch.sh opusVia agent:
"Switch to Rei" or "Switch back to Opus"
Revert
If something breaks, restore the backup:
./skills/rei/scripts/revert.shManual Setup
Add to ~/.clawdbot/clawdbot.json:
{
"models": {
"providers": {
"rei": {
"baseUrl": "https://coder.reilabs.org/v1",
"apiKey": "YOUR_API_KEY",
"api": "openai-completions",
"headers": { "User-Agent": "Clawdbot/1.0" },
"models": [{
"id": "rei-qwen3-coder",
"name": "Rei Qwen3 Coder",
"contextWindow": 200000,
"maxTokens": 8192
}]
}
}
},
"agents": {
"defaults": {
"models": {
"rei/rei-qwen3-coder": { "alias": "rei" }
}
}
}
}Then restart: clawdbot gateway restart
Troubleshooting
403 errors: The User-Agent: Clawdbot/1.0 header is required. The setup script adds this automatically. If you configured manually, make sure the header is present.
"Model not allowed": Rei must be in agents.defaults.models to switch to it. The setup script handles this. For manual setup, add the allowlist entry shown above.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review