Improve Convex Plugin
Send the coding session transcript to the Convex team for an AI post-mortem — opt-in, consent required
- What
- Send the coding session transcript to the Convex team for an AI post-mortem — opt-in, consent required
- Cost
- Free
- Needs
- a Convex project (see the repo README for setup); a coding session transcript (Claude/Codex .jsonl); willingness to share — strictly opt-in
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the system-improvement loop, not a dev skill: sends the current coding session transcript to the Convex team's AI post-mortem endpoint so the runbook, bootstrap script, skills and components improve. Sharing is OPT-IN by construction: the anteater-served helper asks once (Always / Just this once / Never, remembered) and the skill never sends until the user has explicitly chosen — the findings target the system, not end-user data, and keys/tokens are redacted before upload. ⚠️ Honest labeling: the workflow runs `curl … | bash` against a Convex endpoint; never run it without having made an explicit sharing choice. No equivalent in the catalogue. By @get-convex, listed here with credit to its creator. Honest caveats: requires a Convex project and a session transcript (Claude/Codex .jsonl); sending is entirely optional and remembered. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: a Convex project (see the repo README for setup); a coding session transcript (Claude/Codex .jsonl); willingness to share — strictly opt-in Install "Improve Convex Plugin" for me. Give my agent the opt-in feedback workflow: run the anteater-served helper (curl | bash) to send this session's transcript to the Convex team's AI post-mortem endpoint, ask the user to choose Always / Just this once / Never if consent hasn't been given (never send before an explicit choice), summarize system findings — never send raw secrets (keys/tokens are redacted before upload) Repository: https://github.com/get-convex/agent-skills/blob/main/skills/convex-improve-convex-plugin/SKILL.md 1. Fetch the SKILL.md file for the get-convex-agent-skills-convex-improve-convex-plugin 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 beyond the documented curl | bash (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-improve-convex-plugin". 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. make my Always/once/never sharing choice before any sending). 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.