openrouter-known-pitfalls
Avoid common OpenRouter integration pitfalls and gotchas. Use proactively when designing or reviewing an integration. Trigger with phrases like 'openrouter pitfalls', 'openrouter gotchas', 'openrouter mistakes', 'openrouter best practices'.
- License 许可
- MIT
- 最近更新
- 2026-05-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- openrouter-known-pitfalls
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Avoid common OpenRouter integration pitfalls and gotchas. Use proactively when designing or reviewing an integration. Trigger with phrases like 'openrouter pitfalls', 'openrouter gotchas', 'openrouter mistakes', 'openrouter best practices'.
- allowed-tools
- Read, Write, Edit, Grep
- compatible-with
- claude-code, codex, openclaw
02 资源文件 9
- 参考文档references/authentication-issues.md746 B
- 参考文档references/cost-surprises.md1.3 KB
- 参考文档references/error-handling-gaps.md876 B
- 参考文档references/errors.md323 B
- 参考文档references/examples.md3.2 KB
- 参考文档references/model-name-mistakes.md1.1 KB
- 参考文档references/provider-differences.md811 B
- 参考文档references/rate-limiting-mistakes.md798 B
- 参考文档references/request-format-errors.md844 B
03 SKILL.md 正文
Openrouter Known Pitfalls
Overview
This skill documents the most common mistakes developers make when integrating OpenRouter and how to avoid them.
Prerequisites
- OpenRouter integration (planned or existing)
Instructions
- Avoid hardcoding model IDs: Models get renamed or removed; always validate model availability at startup and handle missing models gracefully
- Don't ignore token limits: Each model has different context windows; always check
context_lengthfrom the models API and validate prompt size before sending - Handle provider differences: The same prompt can produce different results across providers; test critical prompts with your specific model, not just any model
- Set max_tokens explicitly: Without
max_tokens, models may generate very long (and expensive) responses; always set a reasonable limit - Don't store API keys in code: Use environment variables or a secrets manager; add
.envto.gitignore; rotate keys if they're ever exposed
Output
- Checklist of common pitfalls with prevention strategies
- Code review checklist for OpenRouter integrations
- Configuration validation script that catches common mistakes
Error Handling
| Error | Cause | Fix |
|---|---|---|
model_not_found after working fine |
Model was renamed or deprecated | Query /models at startup; maintain a fallback model list |
| Unexpectedly large bill | No max_tokens set on expensive model |
Always set max_tokens; implement cost tracking middleware |
| Different behavior across models | Assuming all models handle prompts identically | Test with each model you plan to use; adjust prompts per model if needed |
See ${CLAUDE_SKILL_DIR}/references/errors.md for full error reference.
Examples
See ${CLAUDE_SKILL_DIR}/references/examples.md for runnable code samples.
Resources
04 同仓库更多 Skills
zustand-store-ts
Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.
zustand-store-creator
Zustand Store Creator - Auto-activating skill for Frontend Development. Triggers on: zustand store creator, zustand store creator Part of the Frontend Development skill category.
zero-trust-config-helper
Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.
zapier-integration-helper
Zapier Integration Helper - Auto-activating skill for Business Automation. Triggers on: zapier integration helper, zapier integration helper Part of the Business Automation skill category.
zai-cli
Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.
yt-research
Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.