maintain-usage-dashboard
Update and verify the private Madabot usage dashboard.
Skill by madacol
Chalk Labs
Need help deploying maintain-usage-dashboard?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/madacol-maintain-usage-dashboard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/maintain-usage-dashboard
What's inside
- Skill name
maintain-usage-dashboard- Description
- Update and verify the private Madabot usage dashboard.
- License
- Unlicense
- Instructions
- 11 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions call the network
Agent Skills spec issues
- name: "maintain-usage-dashboard" does not match folder "usage-guide"
Files (6)
- SKILL.md
- app.js · public/
- dashboard.html · public/
- style.css · public/
- server.js
- website.json
SKILL.md (first lines)
# Usage dashboard maintenance The site runs `server.js` against the existing durable usage service. No build step is needed. Update `public/` for browser presentation and `../../usage/dashboard.js` for the saved-report response. Keep the manifest private. Do not restart Madabot to publish dashboard changes. From the repository root, run `pnpm test tests/usage-dashboard.test.js tests/workspace-usage-report.test.js`, `pnpm run type-check`, and `pnpm run type-check:tests`. Then run `site-manager deploy docs/usage-guide/website.json` and verify `curl --fail --max-time 15 https://usage-guide.babyjarvis.com/` and `curl --fail --max-time 30 https://usage-guide.babyjarvis.com/api/usage`. The manager supplies PORT and runs Node from this directory. The manifest pins the installed Node 24 executable because the system `/usr/bin/node` is Node 18 and lacks `node:sqlite`; update the path when the host runtime moves. Data uses the existing configured retained usage location, with optional `MADABOT_USAGE_DIRECTORY` override. Page reads do not collect or reprice data. The explicit Refresh usage button uses the existing service collector and its locking; it is restricted to same-origin requests. Confirm the server Host and browser Origin are preserved through the proxy when testing refresh. Check current versus historical periods, missing snapshots versus valid zero usage, workspace and model totals, and a narrow mobile viewport. Never combine overlapping windows or equate API-equivalent cost with subscription billing. Collection coverage remains owned by the separate cross-environment capture task.
From madacol/whatsapp-llm-bot, Unlicense.
More from madacol/whatsapp-llm-bot
- 0.544score
set-channel-description
madacol
Learn how to read, update, or clear the current chat's description when requested by the user or required by an authorized workflow.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
logging-diagnostics
madacol
Manage diagnostic logging with minimal context: find relevant logs, inspect status, enable or disable narrow logging, add runtime toggles when missing, and…
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
auto-tasks
madacol
Learn how to schedule reminders and agent work to run once or repeatedly in the current chat.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
send-files
madacol
Learn how to send local files, media, or directories to the chat.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
architecture-site
madacol
Refresh the architecture website's generated delivery status after changing linked task evidence.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
workspace-editor
madacol
Open this chat's workspace in the shared browser editor to browse files and edit them directly.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
scheduled-prompts
madacol
Compatibility name for Auto tasks.
SkillBFreshness: B★ 1Claude Code +9 - 0.533score
generate-video
madacol
Generate a video artifact and return it to the chat.
SkillBFreshness: B★ 1Claude Code +9 - 0.486score
generate-image
madacol
Generate a new image or edit existing images and return the result to the chat.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
show-architecture-report
madacol
Publish architecture review HTML reports for this repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
domain-modeling
madacol
Build and sharpen a project's domain model.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
improve-codebase-architecture
madacol
Find deepening opportunities in a codebase, informed by the project architecture map, glossary, constraints, and decisions in docs/adr/.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Unlicense
- Repository
- github.com/madacol/whatsapp-llm-bot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from madacol
- 0.544score
set-channel-description
madacol
Learn how to read, update, or clear the current chat's description when requested by the user or required by an authorized workflow.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
logging-diagnostics
madacol
Manage diagnostic logging with minimal context: find relevant logs, inspect status, enable or disable narrow logging, add runtime toggles when missing, and…
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
auto-tasks
madacol
Learn how to schedule reminders and agent work to run once or repeatedly in the current chat.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
send-files
madacol
Learn how to send local files, media, or directories to the chat.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
scheduled-prompts
madacol
Compatibility name for Auto tasks.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
workspace-editor
madacol
Open this chat's workspace in the shared browser editor to browse files and edit them directly.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get maintain-usage-dashboard running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
maintain-usage-dashboard skill. Agent Mart. https://agentmart.dev/skills/madacol-maintain-usage-dashboard (last updated 2026-10-24)