Convex Explain App
Map an existing Convex app — data model, public vs internal functions, auth model, request→data flows. Read-only.
- What
- Map an existing Convex app — data model, public vs internal functions, auth model, request→data flows. Read-only.
- Cost
- Free
- Needs
- a Convex project (see the repo README for setup); optionally a deployment and the official Convex MCP for the live function surface
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — "the before-you-touch": produces the accurate map of an existing Convex app from the two sources that can't lie — the schema (data model + relationships: which `v.id("other")` fields point where, which indexes reveal the intended access paths) and the function surface (functionSpec) — splitting PUBLIC from INTERNAL functions (the attack/API surface), stating the auth/ownership model plainly (including "there is no auth foundation" when that's the case), listing components and HTTP/cron edges, and tracing 1–2 representative request→data flows. Deliberately DESCRIPTIVE: it explains what IS and hands judgment to the audit capabilities (convex-reviewer, convex-authz) and changes to the fixers — it never evaluates. No get-convex equivalent has been published before. By @get-convex, listed here with credit to its creator. Honest caveats: requires a Convex project (free tier exists); read-only — the app is never modified; deployment introspection goes through deploy-guard discipline. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: a Convex project (see the repo README for setup); optionally a deployment and the official Convex MCP for the live function surface Install "Convex Explain App" for me. Give my agent the workflow for mapping my existing Convex app — data model and relationship graph from schema.ts, public vs internal function split, auth/ownership model stated plainly, components and external edges, 1–2 end-to-end request→data flows — descriptive only, read-only, never guessing behavior the code doesn't show Repository: https://github.com/get-convex/agent-skills/blob/main/skills/convex-explain-app/SKILL.md 1. Fetch the SKILL.md file for the get-convex-agent-skills-convex-explain-app skill from the repository into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md into the agent's skills directory, in a folder named "get-convex-agent-skills-convex-explain-app". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. point at the app to explain). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.