# Convex Advisor

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause...

- Repository: https://github.com/openclaw/clawhub (9543 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add openclaw/clawhub --skill convex-advisor -g -a claude-code -y`
Codex: `npx skills add openclaw/clawhub --skill convex-advisor -g -a codex -y`
Cursor: `npx skills add openclaw/clawhub --skill convex-advisor -g -a cursor -y`
Gemini CLI: `npx skills add openclaw/clawhub --skill convex-advisor -g -a gemini-cli -y`

## Description

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

<!-- GENERATED from convex-agents content/capabilities/convex-advisor.json, do not edit by hand. -->

# Live-deployment advisor

Static review guesses; the deployment KNOWS. The official Convex MCP ships an `insights` tool with typed 72h health events per function, documentsReadLimit / bytesReadLimit (hard limit hits), documentsReadThreshold / bytesReadThreshold (approaching), occFailedPermanently / occRetried (write contention), each carrying evidence (table_name, bytes_read, documents_read, occ document id + retry count). The advisor turns each event into a root-caused finding by reading the flagged function's actual code, and emits findings on the findings bus (specs/finding.schema.json) so fixers can be dispatched and launch-readiness can score.

## Workflow

The rest: https://github.com/openclaw/clawhub/blob/HEAD/.agents/skills/convex-advisor/SKILL.md