agentleFS
MelvynxMelvynx/ai-maxxing-skills/skills/setup-my-hermes-dashboard/hermes-skill/SKILL.md

dashboard

Skill46 starsChanged 26 days agoMITView on GitHub

Build, change or remove a module of the owner's personal web dashboard, push data to it, or dress it in their brand. Use when the owner asks to see something on their dashboard, add a page or a card to it, have a cron post a report there, or put it in their colors, logo or font.

  • Commits and pushes

64 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use activity, telemetry and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gokite-aiSkill

    activity

    View transaction history and recent account activity. Invoke when the user asks about past spending, wants to verify a payment went through, check if an order completed, review wallet transfers, or see a log of all account actions. Covers wallet transfers, faucet drops, API payments, shopping checkouts, agent registrations, and session approvals.

    Also in 3 projects that use this

  • OpenAISkill

    telemetry

    Add and verify lightweight macOS runtime telemetry. Use when wiring Logger events or inspecting logs for windows, sidebars, menus, and actions.

    Also in 3 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 7 projects that use this

  • soilmassSkill

    export

    Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.

    Also in 4 projects that use this

  • seongjaeryuSkill

    save

    Complete and save your current thinking to Bindly

    Also in 4 projects that use this

  • seongjaeryuSkill

    organize

    Organize knowledge into Sets

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ~/projects/dashboard/AGENTS.md first: it has the stack, the recipe to add a module and the rules.

    line 19
  2. Very specific:

    Commit and push: cd ~/projects/dashboard && git add -A && git commit -m "<module>: <what it shows>" && git push.

    line 23
  3. Very specific:

    When the owner asks for the dashboard in their own brand ("my colors", "my logo", "my site is acme.com"), follow …

    line 26
  4. Very specific:

    Never print a key or a token, never publish the dashboard another way than it already is, and never delete the database in …

    line 34

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dashboard

The owner has a personal web dashboard next to you. Every module on it is one they asked you for; the System monitoring group is built in for admins: Conversations (your latest sessions), Infra (server health, the daily infra-audit cron, fixes sent to your board) and Models (the model you answer with; the owner can switch it there, and connecting a new provider stays with you). 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).

When the owner asks for the dashboard in their own brand ("my colors", "my logo", "my site is acme.com"), follow ~/projects/dashboard/BRANDING.md: get the name, logo, main color and font from their site or from them, show what you found, apply it, dashboard deploy, commit and push.

To push data from a cron or a task (a morning report, today's numbers), the module needs a write route (step 5 of the recipe). Then dashboard-cli post /api/v1/<name> '<json>'. If dashboard-cli get /api/v1/whoami says there is no key, run dashboard key once.

Several people may sign in, each with their email and a code (dashboard member list): admins see everything, members see the modules but not System monitoring (Conversations, Infra, Models, the Hermes link), the API keys or the Team page. A module that only admins should see or change uses getViewer() or requireAdmin() from src/server/viewer.ts (see the AGENTS.md). To let someone in: dashboard member add <email> --invite (admin only when the owner says so, in those words); dashboard member remove <email> signs them out at once. Admins can also add and remove members on the Team page (/team). The dashboard has its own sign-in: never put it behind the gate, never add a way in without signing in.

An Infra task on your board (title "Fix: ...") came from the owner pressing "Fix": follow it, never open a port in the firewall, and ask the owner before anything that could cut their access (SSH, firewall, a restart of the server). dashboard-cli get /api/v1/infra gives the last check and audit.

Never print a key or a token, never publish the dashboard another way than it already is, and never delete the database in ~/.local/share/dashboard.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.