Convex Production Self-Heal
Production error → triaged, root-caused, repaired, and certified fix PR — the human keeps the merge button
- What
- Production error → triaged, root-caused, repaired, and certified fix PR — the human keeps the merge button
- Cost
- Free
- Needs
- a Convex account and a deployed Convex app; sentinel for prod error capture (the skill offers to install it if absent)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a gated production self-healing loop. It captures errors with sentinel (prod errors in your own deployment, redacted at write time), triages each new or recurring error (transient blips are retried or ignored — no PR for a one-off network hiccup; config/secret errors are handed to the env micro power, never guessed), root-causes on the findings bus, prepares the repair, then certifies the fix against real invariants (tsc + rehearsal on a preview + reproduce-then-gone) before opening a PR — and never auto-merges; the human merge is the fixed boundary. Sentry/Datadog/Vercel can go error→investigate→draft-PR, but they treat the backend as opaque and stop at the human gate with an unverified diff; Convex can do the step they can't, because the error rows live in your own deployment and the fix can be rehearsed against it. Requires a Convex account, a deployed app, and sentinel for error capture (offered for install if absent). By @get-convex, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: a Convex account and a deployed Convex app; sentinel for prod error capture (the skill offers to install it if absent) Install "Convex Production Self-Heal" for me. Production error → triaged, root-caused, repaired, and certified fix PR — the human keeps the merge button Repository: https://github.com/get-convex/agent-skills/blob/main/skills/convex-self-heal/SKILL.md 1. Fetch the SKILL.md file for the get-convex-convex-self-heal 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 and scripts 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 and its helper files into the agent's skills directory, in a folder named "get-convex-convex-self-heal". 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. any accounts, API keys, or CLI tools mentioned in the prerequisites above). 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.