exa-debug-bundle
Collect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Exa problems. Trigger with phrases like "exa debug", "exa support bundle", "collect exa logs", "exa diagnostic".
Best use case
exa-debug-bundle is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Collect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Exa problems. Trigger with phrases like "exa debug", "exa support bundle", "collect exa logs", "exa diagnostic".
Teams using exa-debug-bundle should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/exa-debug-bundle/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How exa-debug-bundle Compares
| Feature / Agent | exa-debug-bundle | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Collect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Exa problems. Trigger with phrases like "exa debug", "exa support bundle", "collect exa logs", "exa diagnostic".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# Exa Debug Bundle
## Current State
!`node --version 2>/dev/null || echo 'N/A'`
!`npm list exa-js 2>/dev/null | grep exa-js || echo 'exa-js not installed'`
!`echo "EXA_API_KEY: ${EXA_API_KEY:+SET (${#EXA_API_KEY} chars)}"`
## Overview
Collect all necessary diagnostic information for Exa support tickets. Exa error responses include a `requestId` field — always include it when contacting support at hello@exa.ai.
## Instructions
### Step 1: Quick Connectivity Test
```bash
set -euo pipefail
echo "=== Exa Connectivity Test ==="
echo "API Key: ${EXA_API_KEY:+SET (${#EXA_API_KEY} chars)}"
echo ""
# Test basic search endpoint
HTTP_CODE=$(curl -s -o /tmp/exa-debug.json -w "%{http_code}" \
-X POST https://api.exa.ai/search \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"query":"debug connectivity test","numResults":1}')
echo "HTTP Status: $HTTP_CODE"
if [ "$HTTP_CODE" = "200" ]; then
echo "Status: HEALTHY"
python3 -c "import json; d=json.load(open('/tmp/exa-debug.json')); print(f'Results: {len(d.get(\"results\",[]))}')" 2>/dev/null
else
echo "Status: UNHEALTHY"
echo "Response:"
cat /tmp/exa-debug.json | python3 -m json.tool 2>/dev/null || cat /tmp/exa-debug.json
fi
```
### Step 2: Capture Request/Response Details
```typescript
import Exa from "exa-js";
const exa = new Exa(process.env.EXA_API_KEY);
async function debugSearch(query: string) {
const startTime = performance.now();
try {
const result = await exa.searchAndContents(query, {
numResults: 3,
text: { maxCharacters: 500 },
});
const duration = performance.now() - startTime;
console.log("=== Debug Info ===");
console.log(`Query: "${query}"`);
console.log(`Duration: ${duration.toFixed(0)}ms`);
console.log(`Results: ${result.results.length}`);
console.log(`Has autoprompt: ${!!result.autopromptString}`);
for (const r of result.results) {
console.log(` [${r.score.toFixed(3)}] ${r.title} (${r.url})`);
console.log(` Text: ${r.text ? `${r.text.length} chars` : "none"}`);
}
} catch (err: any) {
const duration = performance.now() - startTime;
console.error("=== Error Debug ===");
console.error(`Query: "${query}"`);
console.error(`Duration: ${duration.toFixed(0)}ms`);
console.error(`Status: ${err.status || "unknown"}`);
console.error(`Message: ${err.message}`);
console.error(`RequestId: ${err.requestId || err.request_id || "none"}`);
console.error(`Error tag: ${err.error_tag || err.tag || "none"}`);
}
}
```
### Step 3: Create Debug Bundle Script
```bash
#!/bin/bash
set -euo pipefail
# exa-debug-bundle.sh
BUNDLE_DIR="exa-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE_DIR"
echo "=== Exa Debug Bundle ===" > "$BUNDLE_DIR/summary.txt"
echo "Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> "$BUNDLE_DIR/summary.txt"
# Environment info
echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- Environment ---" >> "$BUNDLE_DIR/summary.txt"
echo "Node: $(node --version 2>/dev/null || echo 'N/A')" >> "$BUNDLE_DIR/summary.txt"
echo "npm: $(npm --version 2>/dev/null || echo 'N/A')" >> "$BUNDLE_DIR/summary.txt"
echo "OS: $(uname -a)" >> "$BUNDLE_DIR/summary.txt"
echo "EXA_API_KEY: ${EXA_API_KEY:+SET}" >> "$BUNDLE_DIR/summary.txt"
# SDK version
echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- SDK ---" >> "$BUNDLE_DIR/summary.txt"
npm list exa-js 2>/dev/null >> "$BUNDLE_DIR/summary.txt" || echo "exa-js not found" >> "$BUNDLE_DIR/summary.txt"
# API connectivity test
echo "" >> "$BUNDLE_DIR/summary.txt"
echo "--- API Test ---" >> "$BUNDLE_DIR/summary.txt"
HTTP_CODE=$(curl -s -o "$BUNDLE_DIR/api-response.json" -w "%{http_code}" \
-X POST https://api.exa.ai/search \
-H "x-api-key: ${EXA_API_KEY:-missing}" \
-H "Content-Type: application/json" \
-d '{"query":"debug test","numResults":1}' 2>/dev/null)
echo "HTTP Status: $HTTP_CODE" >> "$BUNDLE_DIR/summary.txt"
# Package bundle
tar -czf "$BUNDLE_DIR.tar.gz" "$BUNDLE_DIR"
echo "Bundle created: $BUNDLE_DIR.tar.gz"
echo ""
echo "IMPORTANT: Review $BUNDLE_DIR/summary.txt before sharing."
echo "Include the requestId from any error responses when contacting hello@exa.ai"
```
## Output
- `exa-debug-YYYYMMDD-HHMMSS.tar.gz` archive containing:
- `summary.txt` — environment, SDK version, API connectivity
- `api-response.json` — raw API response from test query
## Sensitive Data Handling
**Always redact before sharing:**
- API keys and tokens
- Query content containing PII
- Internal URLs or domain names
**Safe to include:**
- HTTP status codes and error tags
- `requestId` from error responses
- SDK and runtime versions
- Latency measurements
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| `curl: command not found` | curl not installed | Install curl or use node script |
| Empty API response | Network firewall | Check outbound HTTPS to api.exa.ai |
| 401 in connectivity test | Bad API key | Regenerate at dashboard.exa.ai |
| Bundle script fails | Missing permissions | Run with `bash` not `sh` |
## Resources
- [Exa Error Codes](https://docs.exa.ai/reference/error-codes)
- [Exa Support](mailto:hello@exa.ai)
## Next Steps
For rate limit issues, see `exa-rate-limits`. For common error solutions, see `exa-common-errors`.Related Skills
workhuman-debug-bundle
Workhuman debug bundle for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman debug bundle".
wispr-debug-bundle
Wispr Flow debug bundle for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr debug bundle".
webflow-debug-bundle
Collect Webflow debug evidence for support tickets and troubleshooting. Gathers SDK version, token validation, rate limit status, site connectivity, CMS health, and error logs into a single diagnostic bundle. Trigger with phrases like "webflow debug", "webflow support bundle", "collect webflow logs", "webflow diagnostic", "webflow troubleshoot".
vercel-debug-bundle
Collect Vercel debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Vercel problems. Trigger with phrases like "vercel debug", "vercel support bundle", "collect vercel logs", "vercel diagnostic".
veeva-debug-bundle
Veeva Vault debug bundle for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva debug bundle".
vastai-debug-bundle
Collect Vast.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Vast.ai problems. Trigger with phrases like "vastai debug", "vastai support bundle", "collect vastai logs", "vastai diagnostic".
twinmind-debug-bundle
Collect comprehensive diagnostic information for TwinMind issues. Use when preparing support requests, investigating complex problems, or gathering evidence for bug reports. Trigger with phrases like "twinmind debug", "twinmind diagnostics", "collect twinmind info", "twinmind support bundle".
together-debug-bundle
Together AI debug bundle for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together debug bundle".
techsmith-debug-bundle
TechSmith debug bundle for Snagit COM API and Camtasia automation. Use when working with TechSmith screen capture and video editing automation. Trigger: "techsmith debug bundle".
supabase-debug-bundle
Collect Supabase diagnostic info for troubleshooting and support tickets. Use when debugging connection failures, auth issues, Realtime drops, Storage errors, RLS misconfigurations, or preparing a support escalation. Trigger: "supabase debug", "supabase diagnostics", "supabase support bundle", "collect supabase logs", "debug supabase connection".
stackblitz-debug-bundle
Collect WebContainer diagnostic info: boot state, file system, process list. Use when working with WebContainers or StackBlitz SDK. Trigger: "stackblitz debug".
speak-debug-bundle
Collect diagnostic information for Speak API issues: auth verification, audio format validation, session inspection, and network testing. Use when implementing debug bundle features, or troubleshooting Speak language learning integration issues. Trigger with phrases like "speak debug bundle", "speak debug bundle".