convex-suggest
get-convex/agent-skills
Suggest the right Convex component when you detect hand-rolled patterns it already solves.
What is convex-suggest?
This skill passively observes your code and asks, then suggests a matching Convex component (crons, rate-limiter, storage, search, presence, workflow, RAG, etc.) when it detects a pattern you're duplicating. It never interrupts the current task and requires explicit consent before installing anything.
- Detects hand-rolled patterns matching Convex components (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync)
- Surfaces one targeted suggestion after task completion, never mid-task
- Cites specific code or phrases from your own work to explain why the component fits
- Waits for explicit consent before installing; never auto-installs
- Avoids repeating suggestions or suggesting already-installed components
How to install convex-suggest
npx skills add https://github.com/get-convex/agent-skills --skill convex-suggestHow to use convex-suggest
- 1.Install the skill via `npx skills add https://github.com/get-convex/agent-skills --skill convex-suggest`
- 2.Write or modify code normally; the skill observes passively in the background
- 3.After you complete a task, the skill analyzes your code against its detector rules
- 4.If a match is found, the skill offers one suggestion with the component name, the specific code that triggered it, and why it fits better
- 5.Review the suggestion and reply yes to install, or no/ignore to dismiss
- 6.If you consent, the skill runs the install command or provides the install hint
Use cases
- You write setInterval logic and the skill suggests @convex-dev/crons
- You implement a shared counter with concurrent increments; it suggests @convex-dev/sharded-counter to avoid OCC conflicts
- You query .collect().length to count records; it suggests @convex-dev/aggregate for efficiency
- You build presence/typing indicators; it suggests @convex-dev/presence
- You integrate an external vector DB; it suggests @convex-dev/rag
- Convex developers building backend features
- Teams scaling from prototype to production
- Developers unfamiliar with Convex's built-in components
convex-suggest FAQ
No. It only suggests after you finish the current task, never mid-work.
Simply say no or ignore it. The skill will not repeat the same suggestion and will not auto-install anything.
No. It picks the highest-priority match and suggests one component at a time, unless you ask for more.
The skill checks for already-installed components and will not suggest them again.
No. It only fires on code patterns related to Convex; generic coding questions (sorting, CSS, etc.) are ignored.
Full instructions (SKILL.md)
Source of truth, from get-convex/agent-skills.
name: convex-suggest description: "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."
<!-- GENERATED from convex-agents content/capabilities/suggest.json — do not edit by hand. -->Proactively suggest the right Convex component
When you see code or intent that duplicates what a Convex component already does, surface a targeted suggestion: ONE component, WHY (anchored in the user's own code or ask), and a concrete install hint. Never install without explicit consent. Never suggest more than one component at a time unless the user asks.
Workflow
- Observe the codeSnippets and userAsk passively — never block the current task to suggest.
- Match against the detector rules (see generators/suggest-detector.mjs): email/SMTP → resend; push notifications → expo-push; setInterval/cron → @convex-dev/crons; shared counter increments → @convex-dev/sharded-counter; .collect().length scans → @convex-dev/aggregate; multi-step/long-running actions → @convex-dev/workflow; bounded concurrency → @convex-dev/workpool; rate-limit counters in DB → @convex-dev/rate-limiter; fs.write/S3 uploads → Convex Storage; Elasticsearch/Algolia → built-in full-text search; presence/typing → @convex-dev/presence; Pinecone/external vector DB → @convex-dev/rag; collaborative editing → @convex-dev/prosemirror-sync.
- After finishing the current task, offer ONE suggestion: name the component, quote the specific code or phrase that triggered it, explain why the component fits better.
- If the user says yes: run
/add <component>or follow the installHint from the detector. - If the user says no or ignores it: drop it. Do not repeat the same suggestion.
Rules
- Passive — never interrupt the current task; surface the suggestion AFTER completing what the user asked.
- One at a time — pick the highest-priority match; do not dump a list of five components.
- Cite WHY from the user's own code or ask — 'I noticed you wrote
post.likes + 1in a mutation that many users call concurrently; that causes OCC conflicts at scale.' - Never install without explicit consent — suggest, explain, wait for a yes.
- Do not suggest a component the user has already installed.
- Do not fire on generic coding questions unrelated to Convex (sorting arrays, writing CSS, etc.).
Related skills
More from get-convex/agent-skills and the wider catalog.
convex-test
Generate convex-test tests for Convex functions using vitest and an in-memory backend.
convex-verify
Verify Convex features work by seeding data, driving as multiple users, and asserting authorization and behavior.
convex
All-TypeScript reactive backend platform with database, auth, realtime sync, and AI agent components—prototype to production without rewrite.
convex-add
Add backend capabilities (billing, auth, search, crons) to your Convex app with always-current procedures.
cargo
Router and entry point for the Cargo CLI skill bundle — load first for multi-domain tasks or when unsure which skill to use.
cargo-ai
Build and configure AI agents in Cargo with prompts, RAG knowledge, MCP servers, and memory management.