$ loading_
Helps users choose the right Convex skill for vague app tasks.
The material indicates this is essentially an open-source prompt/routing document with no required secrets, no declared remote endpoints, and no stated local execution or data-access capability, so overall risk is low. The README does mention external install commands and links, but that does not by itself make this skill inherently high risk.
The material explicitly states there are no required keys or environment variables; the README also does not request tokens, API keys, or account credentials, and shows no sign of credential collection, storage, or exfiltration.
No remote endpoints are declared, and the system marks it as prompt-only. The README only contains documentation links and a suggested install command; it does not indicate that the skill itself performs network connections or sends user data out.
As a prompt-only skill, the material does not describe any mechanism for spawning local processes, executing scripts, or invoking system capabilities. The `npx convex ai-files install` line in the README is a recommendation to the user, not evidence of execution privileges held by the skill itself.
There is no declared ability to read or write local files, project data, databases, or other resources; the description only says it routes Convex requests to more specific skills, with no stated data-access scope.
Positive factors include being open source on GitHub and auditable. However, the repository has no declared license, 0 stars, and unknown maintenance status, which limits source confidence. The README also points users to external `npx` installation and third-party links, so manual review of the repo contents and related dependencies is advisable before adoption.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "convex" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/clawhub/main/.agents/skills/convex/SKILL.md 2. Save it as ~/.claude/skills/convex/SKILL.md 3. Reload skills and tell me it's ready
I want to build a Convex app with authentication and real-time comments, but I’m not sure which skill to start with. Help me choose and route it.
Identifies the most suitable specialized Convex skill and briefly explains why.
Help me build a Convex backend for tasks, user data, and basic queries; if this is too broad, first break it down and route it to the right skills.
Breaks the broad request into clearer sub-tasks and maps each to the right Convex skill.
I’m about to ask several Convex-related questions. Act as the main entry point and tell me which skill should handle each one.
Provides routing guidance for each Convex question so the user reaches the correct workflow quickly.
Use this as the routing skill for Convex work in this repo.
If a more specific Convex skill clearly matches the request, use that instead.
If the project does not already have Convex AI guidance installed, or the existing guidance looks stale, strongly recommend installing it first.
Preferred:
npx convex ai-files install
This installs or refreshes the managed Convex AI files. It is the recommended starting point for getting the official Convex guidelines in place and following the current Convex AI setup described in the docs:
Simple fallback:
Prefer npx convex ai-files install over copying rules by hand when possible.
After that, use the most specific Convex skill for the task:
convex-quickstartconvex-setup-authconvex-create-componentconvex-migration-helperconvex-performance-auditIf one of those clearly matches the user's goal, switch to it instead of staying in this skill.
Plan Convex schema and data migrations for safe, zero-downtime rollouts.
Audit Convex performance issues across reads, subscriptions, writes, and function limits.
Perform ClawHub moderation actions like bans, role changes, and status checks.
Build reusable Convex components with isolated tables and app-facing backend APIs.
Set up authentication, identity mapping, and access control in Convex apps.
Set up Convex in a new or existing app quickly.
Build production-ready Convex apps with reusable agent skills and templates.
Turn a repeated workflow into a reusable skill file from the current session.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Convert skills from other AI coding assistants into Amplifier-native SKILL.md files.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Manage Linear issues, projects, and team workflows with AI assistance