Convex Advisor
Turn the live deployment's 72h health events into evidence-backed findings with root-caused fixes
- What
- Turn the live deployment's 72h health events into evidence-backed findings with root-caused fixes
- Cost
- Free
- Needs
- a Convex project (see the repo README for setup); a cloud Convex deployment with ~72h of traffic (dev or prod); the official Convex MCP
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — "the deployment knows": reads the typed 72h health events from the official Convex MCP `insights` tool (documentsReadLimit, bytesReadLimit, occFailedPermanently, occRetried, thresholds), root-causes each event in the flagged function's actual code, and emits evidence-backed findings with concrete fixes on the findings bus — missing index → `.withIndex`; read-modify-write hotspot → `@convex-dev/sharded-counter`. Distinct from `get-convex-convex-insights` (lot 32): insights is the disciplined READING of MCP tools (logs, functionSpec) to turn an operational question into narrow queries; advisor is ANALYSIS + root-cause + actionable findings. And if the deployment has no evidence, the advisor has no findings — it says so instead of inventing them. By @get-convex, listed here with credit to its creator. Honest caveats: requires a cloud Convex deployment with ~72h of traffic (the insights tool is unavailable on previews/deploy-key contexts); advisory passes are read-only by construction, they apply no fix without confirmation. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Convex Advisor is a free Muse skill that turns the live deployment's 72-hour health events into evidence-backed findings. It reads the typed health events from the official Convex MCP insights tool, root-causes each event in the flagged function's actual code, and emits concrete fixes on the findings bus, such as adding a missing index or fixing a read-modify-write hotspot.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 2cfe645Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Convex project (see the repo README for setup); a cloud Convex deployment with ~72h of traffic (dev or prod); the official Convex MCP Install "Convex Advisor" for me. Give my agent the workflow for advising on my live Convex deployment: read the typed 72h health events via the MCP insights tool, root-cause each event in the actual function code, emit evidence-backed findings (perf/cost/health) with concrete fixes — and say so honestly if the deployment has no evidence Repository: https://raw.githubusercontent.com/get-convex/agent-skills/2cfe645c87f971242cfc8ef3eb53662cbec26a53/skills/convex-advisor/SKILL.md Pinned version: install the code at commit 2cfe645c87f971242cfc8ef3eb53662cbec26a53 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the get-convex-agent-skills-convex-advisor skill from the repository into a temporary folder 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-advisor". 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. have a cloud deployment with traffic, install the Convex MCP). 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2cfe645 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.