CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

96

1.66x

Quality

95%

Does it follow best practices?

Impact

100%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

100%

58%

Add Rei Model Provider to Clawdbot

Correct Rei provider JSON configuration

Criteria
Without context
With context

Correct baseUrl

0%

100%

Correct api type

0%

100%

User-Agent header present

0%

100%

Correct model id

100%

100%

Correct model name

100%

100%

Correct contextWindow

0%

100%

Correct maxTokens

100%

100%

Allowlist entry key

0%

100%

Allowlist alias value

0%

100%

Existing config preserved

100%

100%

Valid JSON output

100%

100%

Without context: $0.4735 · 1m 55s · 32 turns · 3,872 in / 5,601 out tokens

With context: $0.1865 · 43s · 11 turns · 13 in / 2,647 out tokens

100%

25%

Create Rei Onboarding Script for Development Team

Automated setup script with jq and backup

Criteria
Without context
With context

Uses jq for JSON

100%

100%

Backup before modify

100%

100%

Gateway restart

40%

100%

Correct baseUrl embedded

100%

100%

Correct api type embedded

100%

100%

User-Agent header embedded

0%

100%

Allowlist entry added

0%

100%

Config file path

100%

100%

Accepts API key arg

100%

100%

Valid bash script

100%

100%

README produced

100%

100%

Without context: $2.3128 · 6m 27s · 28 turns · 29 in / 7,121 out tokens

With context: $0.2982 · 1m 10s · 17 turns · 461 in / 3,526 out tokens

100%

37%

Diagnose and Fix Broken Rei Integration

Troubleshoot 403 errors and revert guidance

Criteria
Without context
With context

403 root cause identified

0%

100%

User-Agent header added

0%

100%

Correct header value

0%

100%

Allowlist entry added

100%

100%

Model not allowed explained

100%

100%

Revert procedure documented

100%

100%

Gateway restart mentioned

62%

100%

Existing config preserved

100%

100%

Valid JSON output

100%

100%

Troubleshooting doc produced

100%

100%

Without context: $0.4017 · 1m 39s · 18 turns · 21 in / 4,934 out tokens

With context: $0.3136 · 1m 5s · 18 turns · 21 in / 3,707 out tokens

Repository
Demerzels-lab/elsamultiskillagent
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.