model-debugging
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. For taking action on user tiers, see tier-management skill.
npx skills add majiayu000/claude-skill-registry --skill model-debugging --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Diagnoses model errors and high error rates in Pollinations services, identifies affected users (billing, permissions, backend), and analyzes Tinybird/Cloudflare logs for patterns. It is used when investigating model failures, errors, or service issues, and when diagnosing specific request failures.
How it works
The skill provides a workflow and concrete commands to follow:
- Check Model Monitor at the given URL to view current health.
- Query recent errors from the D1 database with a command that aggregates by model, status, and error_message for the last hour.
- Capture live logs from Cloudflare Workers and other services via wrangler tail or SSH journalctl commands.
- Use License and environment guidance to update secrets when needed, including how to decrypt/encrypt env.json and restart services.
- Run log analysis commands to count errors by type and identify content-filter or DNS-related issues, and verify DNS resolution on servers.
- Cross-reference with model-specific debugging references to understand common issues per model.
When to use it
Use when investigating model failures, high error rates, or service issues; when identifying users affected by errors (401/402/403/400 patterns) and when analyzing logs for patterns; and when diagnosing specific request failures.
What it can touch
It references tools and environments such as:
- Cloudflare Workers Observability API
- wrangler (CLI) for D1 database queries
- SSH access to enter-services and specific pollinations services
- Environment variables and secrets in SOPS-encrypted files
- Commands touching image.pollinations.ai and text.pollinations.ai services
Caveats
The skill describes error patterns and diagnostic steps, including common issues like DNS errors, content filters, and backend failures. It notes that high 401/402/403/400 rates are expected from real-world usage and that focus should be on 500/504 backend failures. It outlines procedures for updating Azure/Vertex/OpenAI related endpoints and keys, and restart steps after secret updates.
# Model Debugging Skill Use this skill when: - Investigating model failures, high error rates, or service issues - Finding users affected by errors (402 billing, 403 permissions, 500 backend) - Analyzing Tinybird/Cloudflare logs for patterns - Diagnosing specific request failures **Related skill**: Use `tier-management` to upgrade users or check balances after identifying issues here. --- # Understanding Model Monitor Error Rates **Why does the Model Monitor show high error rates when models work fine manually?** The Model Monitor at https://monitor.pollinations.ai shows **all real-world traffic**, including: - **401 errors**: Anonymous users without API keys (most common) - **402 errors**: Users with insufficient pollen balance or exhausted API key budget - **403 errors**: Users denied access to specific models (API key restrictions) - **400 errors**: Invalid request parameters (e.g., `openai-audio` without `modalities` param) - **429 errors**: Rate-limited requests - **500/504 errors**: Actual backend failures (investigate these) When you test manually with a valid secret key (`sk_`), you bypass auth/quota issues, so models appear to work fine. **Key insight**: High 401/402/403/4
- 1. Check Model Monitor
- 2. Query Recent Errors from D1 Database
- 3. Capture Live Logs
- enter.pollinations.ai (Cloudflare Worker)
- image.pollinations.ai (EC2 systemd)
- text.pollinations.ai (EC2 systemd)
- Azure Content Safety DNS Failure
- Azure Kontext Content Filter
- Vertex AI Invalid Image
- Translation Service Down
- OpenAI Audio Invalid Voice
- Veo No Video Data
- image.pollinations.ai
- text.pollinations.ai
Via enter.pollinations.ai worker (requires wrangler) cd enter.pollinations.ai wrangler tail --format json | tee logs.jsonl Or with formatting: wrangler tail --format json | npx tsx scripts/format-logs.ts Real-time logs ssh enter-services "sudo journalctl -u image-pollinations.service -f" Last 3 minutes ssh enter-services "sudo journalctl -u image-pollinations.service --since '3 minutes ago' --no-pager" > image-service-logs.txt Recent errors only
What does the model-debugging skill do?
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. For taking action on user tiers, see tier-management skill.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill model-debugging --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.