
Insforge Debug
When you've got a concrete error in an InsForge project (SDK error, 4xx/5xx response, failing edge function, broken auth flow), this skill walks you through the diagnostic commands to pinpoint the cause. The fastest path is `diagnose --ai` with your error message, which inspects backend state and returns both diagnosis and suggested fixes. If you want more control, the manual scenarios map symptoms to specific log sources and health checks: PostgREST logs for PGRST errors, database connection checks for timeouts, function logs for 502s. One thing to know: 429 rate limits aren't logged backend-side, so you'll need to audit client-side request patterns instead. For proactive health audits without a specific failing request, use insforge-backend-advisor instead.
- skills.sh installs
- 15.8K
- GitHub stars
- 30
- last updated
- Jul 14, 2026
Install
$ npx -y skills add insforge/agent-skills --skill insforge-debug --agent claude-codeInstalls into .claude/skills of the current project.
Files
InsForge Debug
Diagnose problems in InsForge projects by combining the backend's observability primitives — logs, metrics, db-health, advisor, policies, metadata, error objects, deploy state, and AI assist. This skill provides:
- A reference per debug primitive (one observability surface each — under
references/) - Symptom Recipes (below) that name the primitive sequence for known reactive symptoms and proactive audits
Always use npx -y @insforge/cli — never install the CLI globally.
Fastest Path: AI-Assisted Triage
When the user gives a concrete description (error message, failing URL, HTTP status), hand it to the InsForge debug agent. Unlike the other primitives, this one returns suggestions, not just observations — verify the diagnosis against the primitives it cites before acting on it.
npx -y @insforge/cli diagnose --ai "<issue description>"
See references/ai-assisted.md for when to use this first vs when to skip, and how to verify the output.
Debug Primitives
Sponsors
Details
- Repository
- github.com/insforge/agent-skills
- Categories
- AI & Agent Building, Debugging
- First seen
- Apr 16, 2026