Summary
Teaches Claude how to handle errors in the iii platform by branching on specific error codes like `function_not_found`, `FORBIDDEN`, and `timeout` instead of parsing message strings. Covers the distinction between SDK-local errors and engine-side invocation failures, plus retryability rules (don't retry RBAC denials, be careful with timeouts unless your work is idempotent). Includes working exception handling patterns for Node, Python, Rust, and browser SDKs. The honest take: error codes in distributed systems always feel like they need one more layer of context, but having a reference that tells you not to retry `FORBIDDEN` blindly is worth it when you're debugging at 2am.
Install to Claude Code
npx -y skills add iii-hq/iii --skill iii-error-handling --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
