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

Makes Claude offer one matching Convex component when you hand-write something a component already does.

Installs: 38.2K; on skills.sh
Stars: 68; on GitHub
Updated: Oct 2026; last repo commit

This skill makes Claude watch your code and requests for patterns that a Convex component already solves. When it spots one, it offers a single suggestion after it finishes your task. The suggestion names the component, quotes the code or phrase that triggered it and says why the component fits better.

SKILL.md lists 13 detector rules. Examples: setInterval or cron code points to @convex-dev/crons, rate-limit counters in the database point to @convex-dev/rate-limiter, and Pinecone or another external vector database points to @convex-dev/rag. It never installs without your yes. On yes it runs /add with the component name or follows the install hint. SKILL.md points to a generators/suggest-detector.mjs file that is not in this skill's folder, which holds only SKILL.md.

Good for

Convex developers who may be rebuilding crons, rate limits, counters or search by hand
Teams who want component tips without being interrupted mid-task

Install convex-suggest

Claude Code

Copy this prompt.

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

npx skills add https://github.com/convex/agent-skills --skill convex-suggest --skill convex-add

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-add, so the first command installs it too. 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-suggest in Claude Code or $convex-suggest in Codex, or let the agent pick it when the task fits. 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

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

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: 38,230 (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

Looks at code snippets and your request without blocking the current task
Read · Observe passively
Compares what it sees with 13 pattern-to-component rules, such as email to resend
Others include push to expo-push, counters to sharded-counter, long actions to workflow and collaborative editing to prosemirror-sync.
Read · Match the detector rules
After your task, names one component, the code that triggered it and why it fits
Offer one suggestion
Runs /add with the component or follows the detector's install hint, only after you agree
Runs code · Install on yes
Does not repeat a suggestion you declined or ignored
Drop it on no

From the official docs

Permissions

Low risk

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

A yes can install packages
Accepting a suggestion runs /add or the detector's install hint, which installs a component and edits your project. convex-add then follows steps it fetches from a Convex-run server. github.com
Consent rule in SKILL.md
It says to never install without explicit consent, to suggest after finishing the task, and not to repeat a declined suggestion. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md says the skill is passive and never installs without explicit consent.
Sign-in and keys	SKILL.md names no credentials.
Scopes	Reads the code and requests in your session to match patterns After your yes, runs /add to install a component and edit your project

Questions

What does convex-suggest do?

It makes Claude recommend a ready-made Convex component when it sees you building something the component already does. It speaks up once, after it finishes what you asked for.

Will it interrupt me or install things on its own?

SKILL.md says it is passive and must never interrupt the current task, and that it must never install without explicit consent. It offers one suggestion at a time and drops it if you decline.

Which patterns does it look for?

It has 13 rules in SKILL.md. They cover email and SMTP, push notifications, setInterval or cron, shared counters, collect().length scans, long-running actions, bounded concurrency, database rate-limit counters, file uploads, Elasticsearch or Algolia, presence and typing, external vector databases and collaborative editing.

How do I install it?

Use the install box at the top of this page. The first command installs convex-suggest and convex-add, because a yes on a suggestion sends Claude to /add. Run it with /convex-suggest in Claude Code or $convex-suggest in Codex.

Is it safe?

The skill suggests and waits for your yes. A yes can install packages and edit your project through /add, and convex-add follows steps it fetches from a Convex-run server, so read what comes next before approving.

How is it different from convex-add?

convex-add adds a capability when you ask for one. convex-suggest notices a pattern in your code and proposes the component first.

Is it official?

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

Is it part of Convex's Claude Code plugin?

Convex's official Claude Code plugin (/plugin install convex@claude-plugins-official, per the Convex docs) is a separate package. Its manifest lists a skills folder, a commands folder, two subagents (convex-expert and convex-reviewer), an MCP server that runs npx -y convex@1.46.0 mcp start, hooks (a check at session start, a lint check before file writes and edits, and a typecheck when a turn ends) and background monitors. The plugin repo has its own skill folder named suggest, which is a separate file from this repo's convex-suggest.

Information

updated Nov 2, 2026

Repository: convex/agent-skills
Folder: skills/convex-suggest

convex/agent-skills skills.sh

Sources

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

Show all 8

convex/agent-skills README · github.com
skills CLI commands · github.com
Convex docs: Agent Skills · docs.convex.dev
convex-suggest SKILL.md · github.com
Convex docs: Agent Plugins · docs.convex.dev
convex plugin.json · github.com
convex plugin hooks.json · github.com
convex plugin .mcp.json · github.com