AGENT SKILL

mistral-debug-bundle

Collect Mistral AI debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Mistral AI problems. Trigger with phrases like "mistral debug", "mistral support bundle", "collect mistral logs", "mistral diagnostic".

适用职业开发工程师
License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
mistral-debug-bundle
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Collect Mistral AI debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Mistral AI problems. Trigger with phrases like "mistral debug", "mistral support bundle", "collect mistral logs", "mistral diagnostic".
allowed-tools
Read, Bash(grep:*), Bash(curl:*), Bash(tar:*), Grep

03 SKILL.md 正文

Mistral AI Debug Bundle

Overview

Collect all necessary diagnostic information for Mistral AI support tickets.

Prerequisites

  • Mistral AI SDK installed
  • Access to application logs
  • Permission to collect environment info

Instructions

Step 1: Create Debug Bundle Script

#!/bin/bash
# mistral-debug-bundle.sh

BUNDLE_DIR="mistral-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE_DIR"

echo "=== Mistral AI Debug Bundle ===" > "$BUNDLE_DIR/summary.txt"
echo "Generated: $(date)" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

Step 2: Collect Environment Info

# Environment info
echo "--- Environment ---" >> "$BUNDLE_DIR/summary.txt"
echo "Node.js: $(node --version 2>/dev/null || echo 'not installed')" >> "$BUNDLE_DIR/summary.txt"
echo "Python: $(python3 --version 2>/dev/null || echo 'not installed')" >> "$BUNDLE_DIR/summary.txt"
echo "npm: $(npm --version 2>/dev/null || echo 'not installed')" >> "$BUNDLE_DIR/summary.txt"
echo "pip: $(pip --version 2>/dev/null || echo 'not installed')" >> "$BUNDLE_DIR/summary.txt"
echo "OS: $(uname -a)" >> "$BUNDLE_DIR/summary.txt"
echo "MISTRAL_API_KEY: ${MISTRAL_API_KEY:+[SET]}" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

Step 3: Gather SDK and API Info

# SDK version (Node.js)
echo "--- SDK Versions ---" >> "$BUNDLE_DIR/summary.txt"
npm list @mistralai/mistralai 2>/dev/null >> "$BUNDLE_DIR/summary.txt" || echo "Node SDK: not installed" >> "$BUNDLE_DIR/summary.txt"

# SDK version (Python)
pip show mistralai 2>/dev/null | grep -E "^(Name|Version)" >> "$BUNDLE_DIR/summary.txt" || echo "Python SDK: not installed" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

# API connectivity test
echo "--- API Connectivity ---" >> "$BUNDLE_DIR/summary.txt"
echo -n "API Status: " >> "$BUNDLE_DIR/summary.txt"
HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: Bearer ${MISTRAL_API_KEY}" \
  https://api.mistral.ai/v1/models)
echo "$HTTP_STATUS" >> "$BUNDLE_DIR/summary.txt"

# List available models (redact API key from output)
echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- Available Models ---" >> "$BUNDLE_DIR/summary.txt"
curl -s -H "Authorization: Bearer ${MISTRAL_API_KEY}" \
  https://api.mistral.ai/v1/models 2>/dev/null | \
  jq -r '.data[].id' 2>/dev/null >> "$BUNDLE_DIR/summary.txt" || \
  echo "Could not fetch models" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

Step 4: Collect Logs (Redacted)

# Recent logs (redacted)
echo "--- Recent Logs (redacted) ---" >> "$BUNDLE_DIR/logs.txt"
if [ -d "logs" ]; then
  grep -i "mistral" logs/*.log 2>/dev/null | tail -100 >> "$BUNDLE_DIR/logs.txt"
fi

# npm debug logs
if [ -d "$HOME/.npm/_logs" ]; then
  grep -i "mistral" "$HOME/.npm/_logs"/*.log 2>/dev/null | tail -50 >> "$BUNDLE_DIR/logs.txt"
fi

# Configuration (redacted - secrets masked)
echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- Config (redacted) ---" >> "$BUNDLE_DIR/summary.txt"
if [ -f ".env" ]; then
  cat .env 2>/dev/null | sed 's/=.*/=***REDACTED***/' >> "$BUNDLE_DIR/config-redacted.txt"
fi

# package.json dependencies
if [ -f "package.json" ]; then
  echo "" >> "$BUNDLE_DIR/summary.txt"
  echo "--- Dependencies ---" >> "$BUNDLE_DIR/summary.txt"
  jq '.dependencies, .devDependencies' package.json 2>/dev/null >> "$BUNDLE_DIR/summary.txt"
fi

Step 5: Capture Error Details

# Error reproduction script
cat > "$BUNDLE_DIR/reproduce.sh" << 'SCRIPT'
#!/bin/bash
# Minimal reproduction script

curl -X POST https://api.mistral.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${MISTRAL_API_KEY}" \
  -d '{
    "model": "mistral-small-latest",
    "messages": [{"role": "user", "content": "Hello"}]
  }' 2>&1

echo ""
echo "Exit code: $?"
SCRIPT
chmod +x "$BUNDLE_DIR/reproduce.sh"

Step 6: Package Bundle

# Create timestamp file
echo "Bundle created: $(date -u +%Y-%m-%dT%H:%M:%SZ)" > "$BUNDLE_DIR/timestamp.txt"

# Package everything
tar -czf "$BUNDLE_DIR.tar.gz" "$BUNDLE_DIR"
rm -rf "$BUNDLE_DIR"

echo "Bundle created: $BUNDLE_DIR.tar.gz"
echo ""
echo "IMPORTANT: Review the bundle for sensitive data before sharing!"
echo "Run: tar -tzf $BUNDLE_DIR.tar.gz"

Complete Script

#!/bin/bash
# mistral-debug-bundle.sh - Complete version

set -e

BUNDLE_DIR="mistral-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE_DIR"

echo "Creating Mistral AI debug bundle..."

# Summary file
cat > "$BUNDLE_DIR/summary.txt" << EOF
=== Mistral AI Debug Bundle ===
Generated: $(date)
Hostname: $(hostname)

--- Environment ---
Node.js: $(node --version 2>/dev/null || echo 'not installed')
Python: $(python3 --version 2>/dev/null || echo 'not installed')
OS: $(uname -a)
MISTRAL_API_KEY: ${MISTRAL_API_KEY:+[SET]}

--- SDK Versions ---
EOF

npm list @mistralai/mistralai 2>/dev/null >> "$BUNDLE_DIR/summary.txt" || echo "Node SDK: not installed" >> "$BUNDLE_DIR/summary.txt"
pip show mistralai 2>/dev/null | grep -E "^(Name|Version)" >> "$BUNDLE_DIR/summary.txt" || echo "Python SDK: not installed" >> "$BUNDLE_DIR/summary.txt"

echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- API Test ---" >> "$BUNDLE_DIR/summary.txt"
HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Bearer ${MISTRAL_API_KEY}" https://api.mistral.ai/v1/models 2>/dev/null)
echo "HTTP Status: $HTTP_STATUS" >> "$BUNDLE_DIR/summary.txt"

# Redacted config
if [ -f ".env" ]; then
  cat .env | sed 's/=.*/=***REDACTED***/' > "$BUNDLE_DIR/config-redacted.txt"
fi

# Package
tar -czf "$BUNDLE_DIR.tar.gz" "$BUNDLE_DIR"
rm -rf "$BUNDLE_DIR"

echo "Bundle created: $BUNDLE_DIR.tar.gz"

Output

  • mistral-debug-YYYYMMDD-HHMMSS.tar.gz archive containing:
    • summary.txt - Environment and SDK info
    • logs.txt - Recent redacted logs
    • config-redacted.txt - Configuration (secrets removed)
    • reproduce.sh - Minimal reproduction script

Error Handling

Item Purpose Included
Environment versions Compatibility check Yes
SDK version Version-specific bugs Yes
Error logs (redacted) Root cause analysis Yes
Config (redacted) Configuration issues Yes
API connectivity test Network issues Yes

Sensitive Data Handling

ALWAYS REDACT:

  • API keys and tokens
  • Passwords and secrets
  • PII (emails, names, IDs)
  • Internal URLs and IPs

Safe to Include:

  • Error messages
  • Stack traces (redacted)
  • SDK/runtime versions
  • HTTP status codes

TypeScript Debug Helper

interface DebugInfo {
  timestamp: string;
  sdkVersion: string;
  nodeVersion: string;
  apiKeySet: boolean;
  lastError?: {
    message: string;
    status?: number;
    requestId?: string;
  };
}

function collectDebugInfo(error?: Error): DebugInfo {
  return {
    timestamp: new Date().toISOString(),
    sdkVersion: require('@mistralai/mistralai/package.json').version,
    nodeVersion: process.version,
    apiKeySet: !!process.env.MISTRAL_API_KEY,
    lastError: error ? {
      message: error.message,
      status: (error as any).status,
      requestId: (error as any).requestId,
    } : undefined,
  };
}

// Usage
try {
  await client.chat.complete({ /* ... */ });
} catch (error) {
  const debug = collectDebugInfo(error as Error);
  console.error('Debug info:', JSON.stringify(debug, null, 2));
}

Resources

Next Steps

For rate limit issues, see mistral-rate-limits.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k