rei
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.
92
88%
Does it follow best practices?
Impact
100%
1.66xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description for a niche configuration task. It excels at completeness with a clear 'Use when' clause and has excellent distinctiveness through specific proper nouns and error codes. The only minor weakness is that the 'what' portion could enumerate more specific actions beyond just 'set up'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (model provider setup) and some actions (configuring, adding, troubleshooting 403 errors), but doesn't list comprehensive concrete actions like specific configuration steps or multiple troubleshooting scenarios. | 2 / 3 |
Completeness | Clearly answers both 'what' (set up Rei Qwen3 Coder as a model provider) and 'when' (configuring coder.reilabs.org, adding Rei to Clawdbot, troubleshooting 403 errors) with an explicit 'Use when' clause containing specific triggers. | 3 / 3 |
Trigger Term Quality | Includes highly specific natural keywords users would say: 'Rei Qwen3 Coder', 'coder.reilabs.org', 'Clawdbot', '403 errors', 'Rei endpoints'. These are precise terms that match real user queries about this specific setup. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely distinct with highly specific proper nouns (Rei Qwen3 Coder, coder.reilabs.org, Clawdbot) and a specific error code (403). Very unlikely to conflict with any other skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides multiple concrete paths for setup (script, agent, manual) with copy-paste ready commands and configuration. It's concise and well-organized. The main gap is the lack of a verification/validation step after setup to confirm the provider is working correctly before the user encounters errors.
Suggestions
Add a verification step after setup, e.g., 'Verify: `clawdbot model list | grep rei` or test with `/model rei` and send a test message'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what OpenAI-compatible endpoints are or how JSON configuration works—it assumes Claude's competence. Every section serves a clear purpose with no padding. | 3 / 3 |
Actionability | Provides fully executable commands (setup script, switch scripts, revert script), copy-paste ready JSON configuration, and specific chat commands. Multiple concrete paths to accomplish each task. | 3 / 3 |
Workflow Clarity | The setup workflow is clear (run script), and switching/reverting are straightforward. However, there's no explicit validation step after setup—no way to verify the provider was added correctly or that the connection works before proceeding. For a configuration task that can produce 403 errors, a verification step (e.g., 'test the connection with: curl ...') would be valuable. | 2 / 3 |
Progressive Disclosure | Well-structured with progressive complexity: script setup (simplest) → agent setup → switching models → manual setup (most detailed). The content is appropriately sized for a single file with no need for external references, and sections are clearly labeled for easy navigation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
45f9fac
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.