convex-explain-app Skill for Claude Code: What It Does and How to Install It

Makes Claude explain an existing Convex app: its tables, public and internal functions, auth model, components and request flow.

Installs: 38.4K; on skills.sh
Stars: 68; on GitHub
Updated: Oct 2026; last repo commit

This skill makes Claude explain a Convex app from its schema and function list. It covers the tables and how they link, which functions are public and which are internal, how identity and ownership work, which components and HTTP routes are installed, and one or two end-to-end request paths.

SKILL.md calls it read-only and descriptive. It maps what exists and sends audits to other skills, and sends changes to design or convex-expert. With a deployment it can use the Convex MCP tools functionSpec and tables, and without one it reads the source. Its folder holds only SKILL.md.

Good for

Developers who just joined a Convex project and need a quick map
Anyone about to change or audit a Convex backend who wants to know what is there first

Install convex-explain-app

Claude Code

Copy this prompt.

Install the convex-explain-app skill in Claude Code. Run this command:

npx skills add https://github.com/convex/agent-skills --skill convex-explain-app --skill convex-deploy-guard

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

SKILL.md hands work to convex-deploy-guard, so the first command installs it too. It also mentions convex-reviewer and convex-authz as optional hand-offs; install those separately if you want them. Convex's docs say the skills CLI installs skills into .agents/skills/ in your project. The "All Convex skills" command installs every skill in the repo, which has 33 skill folders. One of them, convex-improve-convex-plugin, is listed in the Convex docs as sending your coding session's transcript to the Convex team. Run this skill with /convex-explain-app in Claude Code or $convex-explain-app in Codex, or let the agent pick it when the task fits. This skill reads your deployment through the official Convex MCP server, which is not part of the skills. Add the server command to your client's MCP settings; the Convex docs also describe an official plugin that starts it for you. This skill works on your project folder, so this page offers no Claude app upload route.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

Sections in SKILL.md

Workflow
Rules

Key facts

Author: Convex (GitHub organisation convex; the vendor's own repo)
License: Apache-2.0 (stated in the README and the LICENSE file)
Installs on skills.sh: 38,351 (Nov 2, 2026)
GitHub stars: 68 for the whole convex/agent-skills repo (Nov 2, 2026)
Last repo commit: Oct 29, 2026
Audits on skills.sh: Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass
What it includes: 1 file: SKILL.md (the repo tree lists nothing else in the folder)
Part of: The convex/agent-skills repo: 33 skill folders in the tree. The README names 6 skills, and this one is not among them

What it includes

Finds the convex/ folder, schema.ts and whether a deployment exists
deploy-guard classifies any deployment read as read-only.
Read · Detect the app
Lists every table with its fields, id links between tables and indexes
The links are described in words, such as "tasks belong to projects and users".
Read · Map the data model
Splits public query, mutation and action functions from internal ones, one line each
Uses functionSpec from the Convex MCP when a deployment exists.
Try: “Explain this Convex app to me”
Network · List the function surface
Says how identity is set up and how ownership is enforced, or that there is no auth
It describes the model and leaves hole-hunting to convex-authz.
Read · State the auth and ownership model
Names installed @convex-dev components, http.ts routes, crons and external API calls
Read · List components and outside calls
Follows one or two paths from a client call to the data it reads or writes
Read · Trace a flow
Points on to convex-reviewer, convex-authz, launch-readiness, design or convex-expert
SKILL.md says never to invent behavior the source does not show.
Present the map and next steps

From the official docs

Permissions

Low risk

What it can do

Read your data
Create and change things
Delete things
Read-only modeHow to turn it on

Watch out for

The Convex MCP server limits production access by default
The Convex docs say the MCP server is safe by default: in production deployments agents cannot access PII and can only perform read-only operations. Write access and PII reads on production need --dangerously-enable-production-deployments or --cautiously-allow-production-pii. docs.convex.dev

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md describes the skill as read-only and says the app is not modified.
Sign-in and keys	SKILL.md names no credentials.
Scopes	Reads the schema, convex/ source files and, if you connect the MCP server, function and table metadata from a deployment

Questions

What does convex-explain-app do?

It makes Claude read a Convex app's schema and functions and write a map of it. The map covers tables and relations, public and internal functions, the auth and ownership model, components and a request flow.

Does it change my app?

SKILL.md labels it read-only and says the app is not modified. Any deployment introspection it does is read-only too, per deploy-guard.

Does it need a running deployment?

Not necessarily. SKILL.md says that with a deployment it uses functionSpec and tables from the official MCP for the live surface, and without one it reads the source directly. The install box lists the MCP server command from the Convex docs.

How is it different from convex-reviewer or convex-authz?

convex-explain-app describes what is there. SKILL.md says judgment goes to the audit skills, so convex-reviewer and convex-authz audit, and launch-readiness scores.

How do I install it?

Use the install box at the top of this page. The first command installs convex-explain-app together with convex-deploy-guard. The next-step skills it names (convex-reviewer, convex-authz, launch-readiness, design, convex-expert) are optional. Run it with /convex-explain-app in Claude Code or $convex-explain-app in Codex.

Is it safe?

SKILL.md describes it as read-only, and it bundles no scripts. If you connect the Convex MCP server, it can read from your deployment, and the docs say production access is off by default. Our advice: point it at a dev deployment.

Is it official?

It is in the convex/agent-skills repo under the Convex GitHub organisation, which is the vendor's own repo.

Information

updated Nov 2, 2026

Repository: convex/agent-skills
Folder: skills/convex-explain-app

convex/agent-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

convex/agent-skills README · github.com
skills CLI commands · github.com
Convex docs: Agent Skills · docs.convex.dev
convex-explain-app SKILL.md · github.com
Convex docs: MCP server · docs.convex.dev