Build, change or remove a module of the owner's personal web dashboard, and push data to it. Use when the owner asks to see something on their dashboard, add a page or a card to it, or have a cron post a report there.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Dashboard
The owner has a personal web dashboard next to you. It started empty: every module on it is one they asked you for. The code is in `~/projects/dashboard`, a git repository on their GitHub, and it runs as the `dashboard` service.
1. Read `~/projects/dashboard/AGENTS.md` first: it has the stack, the recipe to add a module and the rules. Follow the code that is already there.
2. Build only what the owner asked, as one module (a page, its line in the sidebar, its mark). If the request is vague, pick the most useful small version and say what you chose.
3. To see what a Hermes endpoint returns before you use it: `dashboard hermes /api/cron/jobs` (sessions, crons, skills, usage, status).
4. Ship with `dashboard deploy`. It typechecks, tests and builds before restarting, and keeps the old version online if anything fails: read the error, fix it, deploy again.
5. Commit and push: `cd ~/projects/dashboard && git add -A && git commit -m "<module>: <what it shows>" && git push`.
6. Answer the owner in one or two lines: what the module shows and its address (the `url` line of `dashboard status`, plus the module path).
…
The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_rvzh32vgkcrhn5yq
GET https://markdownregistry.com/api/v1/resolve?ref=melvynx/ai-maxxing-skills/dashboard
GET https://markdownregistry.com/api/v1/blob/8ea24fa6bfb56e90406a5d07e15f6a7e8910928fa0d889631da6271db45e6277
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
melvynx/ai-maxxing-skills · skills/audit-safety/SKILL.md · Audit one feature of a web app (TanStack Start, Next.js, Convex) for authorization, tenant isolation, ownership…
melvynx/ai-maxxing-skills · skills/cloudflare/SKILL.md · Run every Cloudflare job through the official `cf` CLI - domains, DNS, Workers deploys, secrets and custom domains, KV…
melvynx/ai-maxxing-skills · skills/code-debug/SKILL.md · Debug hard bugs and performance regressions with a tight red-capable loop, falsifiable hypotheses, a focused fix…
melvynx/ai-maxxing-skills · skills/connect-tool/SKILL.md · Connect any tool (Notion, Stripe, ClickFunnels...) to every agent: install its official CLI, or write a one-file Python…
melvynx/ai-maxxing-skills · skills/connect-vps/SKILL.md · Connect the user's VPS (Hostinger, Hetzner, OVH...) to their terminal as `ssh hermes`, finding the server and its SSH…
melvynx/ai-maxxing-skills · skills/convex/SKILL.md · Set up, secure and optimize a Convex backend. Use for Convex project setup, schema and indexes, queries and mutations…
melvynx/ai-maxxing-skills · skills/create-internal-app/SKILL.md · Create a private internal app on the user's VPS through Dokploy, locked by password and IP allowlist, then hand it to…
melvynx/ai-maxxing-skills · skills/create-landing/SKILL.md · Create a landing page, sales page or waitlist on Cloudflare with TanStack Start, shadcn/ui, a Lumail email form and an…
melvynx/ai-maxxing-skills · skills/create-software/SKILL.md · Create and deploy a public web app on Cloudflare with TanStack Start, shadcn/ui, Convex, Better Auth, Lumail and…
melvynx/ai-maxxing-skills · skills/dev-browser/SKILL.md · Drive the user's dedicated Chrome AI window with the dev-browser CLI to open sites, click, fill forms, read pages, take…
melvynx/ai-maxxing-skills · skills/grill-me/SKILL.md · Interview the user in batches of 10 questions with recommended answers to sharpen a plan, an idea or an app before…
melvynx/ai-maxxing-skills · skills/install-skills/SKILL.md · Install skills of the ai-maxxing package on the user's VPS so their Hermes agent (and Claude Code on the server) can…
nexu-io/open-design · design-templates/dashboard/SKILL.md · Admin / analytics dashboard in a single HTML file. Fixed left sidebar,
top bar with user/search, main grid of KPI cards…
openonion/connectonion · connectonion/cli/co_ai/skills/builtin/dashboard/SKILL.md · Update the agent's Control Center. Use when the user says "update my Control Center", "update my dashboard", "redesign…
suboss87/fdeops · skills/dashboard/SKILL.md · Review the portfolio across existing engagement records. Use for status across customers; requires accessible permitted…
ericrisco/rsc-harness · skills/dashboard/SKILL.md · Use when building or fixing a KPI dashboard decision-makers must read in one screen: which metrics earn a tile, how…
wellwelwel/lagune · .claude/skills/dashboard/SKILL.md · Authoritative reference for the Lagune dashboard, a live view of a project's .lagune/ chain with a locked-down local…
tomtomsatnav/agent-orchestration-standard · plugin/skills/dashboard/SKILL.md · The AOS dashboard: a read-only live monitor of Claude Code agents (agents, tasks, cost, file conflicts, alerts…
