A community website that tracks the best, most-used skills, connectors, and prompts for Muse — Meta's personal AI chat assistant — ranked by community popularity. Think ClawHub or Smithery, rebuilt for a consumer life assistant instead of a developer agent.
The MVP directory site. It may go live slightly after this document — if the link doesn't resolve yet, check back soon.
1Vision & problem
AI assistants keep adding "skills" (installable playbooks that teach the assistant how to do things) and "connectors" (OAuth integrations to apps like Gmail, Spotify, and Google Calendar). The catalog grows fast — and nobody can tell what's actually useful inside the assistant. Users scroll past long alphabetical lists, try things at random, and give up. Creators ship great playbooks and nobody finds them.
Muse Stacks is the community-ranked discovery layer for Muse. One trusted front page that answers "what should I add to my Muse?" the way Rotten Tomatoes answers "what should I watch?" — with popularity rankings, freshness signals, install counts, and use-case browsing, all driven by the community rather than by an app store team.
ClawHub (clawhub.ai) and Smithery (smithery.ai) solved this for developer agents; Muse Stacks solves it for a consumer life assistant — where the "app store" is the assistant itself, and installs should feel as easy as chatting.
2Research findings
Ecosystem research was completed 2026-09-15 and is summarized below. Claims marked verified live were read in a real browser that day; index-only claims come from web-index snippets and were not re-verified. The full report lives with the project notes.
The eight steal-worthy ideas
Three-tab install panel: CLI / one-liner / "copy this prompt to your agent." ClawHub skill page — verified live at clawhub.ai/anotb/skills/homeassistant-skill. The Prompt tab is a pre-written message with safety-vetting instructions ("inspect metadata before installing…"), required env vars, required binaries, and the skill URL — designed to be pasted to your agent, which does the install.
"Add to toolbox" card buttons + a personal Toolbox (cart). Smithery — verified live at smithery.ai. Cards carry one-click "Add to toolbox" buttons plus usage counts ("22.49k uses") as the headline social signal instead of stars. (Smithery was acquired by Arcade.dev in 2026 — also verified live via the site banner.)
"Skills for the apps you already use" — app-tile browsing. ClawHub homepage — verified live at clawhub.ai. Zapier-style app-centric discovery (Gmail, Notion, Slack, WhatsApp…) grouped by Chat / Docs & specs / Web / Cloud. Directly fits Muse's connector concept.
Organize by use case, price filter with a Free-mode slider, release-history feed. There's An AI For That — index-only: beehiiv case study. Organized by real use case ("remove background from 200 photos"), 1.7M newsletter subscribers with $0 paid ads.
In-chat OAuth connect link — authorize without leaving the conversation. index-only: Composio's composio_connect returns an in-chat OAuth link (github.com/k3-2o/pi-composio); Smithery's npx smithery mcp add notion → browser authorize URL flow (verified live at smithery.ai).
Submit-your-skill self-serve: CLI publish + "import from GitHub" + versioning (latest tags, changelogs, rename/merge, pin installs). ClawHub — verified live homepage publish section at clawhub.ai.
Freshness-as-trust: "re-checked daily, 90-days-quiet = delisted" + last-push dates in tables. index-only: pjdurden/claude-skills-live (GitHub) — anything archived, deleted, or 90 days quiet is flagged and delisted; hmzainjamil/awesome-claude-code's dead-link <7-day policy and tier emojis 🔥/⭐/🧪.
Other patterns worth noting
Vercel's agent self-install pattern:index-only — npx skills add <owner/repo> plus a find-skills skill that lets the agent itself search and install without the user leaving chat (github.com/vercel-labs/skills). This is the model for Muse Stacks' agent-executed installs.
Anthropic's Agent Skills open standard (index-only, agentskills.io): the SKILL.md format (six frontmatter fields: name, description, license, compatibility, metadata, allowed-tools) is the packaging format the wider ecosystem converges on — a strong hint for Muse Stacks' own skill spec.
Awesome-list curation mechanics (index-only): GitHub stars as currency, curation tiers, freshness CI, submit-via-PR (the lowest-friction submit flow in the ecosystem), sponsor-block monetization.
The viral top-N list format: "8 skills that actually matter" style roundups are the unit of social distribution for directories — every ranking on Muse Stacks should be exportable as a share card (see §6).
What did NOT verify: exact conversion rates for copy-prompt vs install-button — no public data found; the comparison is structural, not empirical. ClawHub's reported 200k GitHub-star-scale community claims rest on a single blog. Chrome Web Store / Raycast in-app flows were index-only.
3Content model
Three entry types — kept deliberately simple, because a directory lives or dies on whether a new visitor instantly gets it:
Skills — SKILL.md-style playbooks: a Markdown document plus optional scripts and references that teaches Muse how to do a job ("plan my trip", "inbox-zero routine", "meal-prep planner"). The trigger line ("Use when…") is the entry's headline.
Connectors — OAuth integrations to third-party apps (Gmail, Spotify, Google Calendar, Strava…). Each entry shows what data it unlocks, what permissions it asks for, and which skills pair with it.
Prompts — Copy-paste power prompts: single messages that make Muse do something remarkable right now, no install needed. The bracket convention ([your city], [paste your receipt]) is standardized so every prompt is editable at a glance.
Entry fields
title — human name, e.g. "Weekend trip planner"
type — skill · connector · prompt
one-liner — what it does, under 120 characters (the card headline)
description — the trigger text ("Use when…") plus what to expect
category — one of the 8 categories below
use_cases — free-text tags ("plan a trip", "declutter inbox") for use-case browsing
author — handle + profile link
permissions — for connectors: exactly what OAuth scopes it requests, in plain English
badges — verified-safe · maintained · documented (see §4)
last_verified — date of last freshness check (see §4)
source_url — repo, author page, or original prompt source
The 8 categories
💰 Money✈️ Travel🏃 Health⚡ Productivity💬 Communication🛍️ Shopping📚 Learning🏠 Home
Categories are the shelf; use-case browsing is the front door. Visitors should be able to start from "plan my week", "find cheap flights", or "get fit" — à la There's An AI For That's use-case organization — and land on ranked entries, with categories as a secondary filter.
4Ranking approach
Seed-stage honesty: until real usage data exists, all scores are illustrative seed values — curated by the editorial team, never presented as download or install counts. The site labels them plainly as "seed ranking" until the first telemetry milestone replaces them.
Seed ranking (v1): hand-seeded editorial scores per entry, clearly marked as editorial. Explicitly not downloads, installs, or usage — and never phrased that way.
Community upvoting: signed-in users upvote entries; votes decay with age so fresh hits can climb. Anti-gaming: one vote per account, rate-limited, flagging for abuse.
Trust badges:verified-safe (passed a manual security review — no credential exfiltration, no prompt injection), maintained (author active, working with current Muse), documented (install payload complete, permissions disclosed). Badges are awarded by moderators, not self-claimed.
Freshness-as-trust: every entry shows a last-verified date. Entries quiet for 90 days are flagged; if still quiet after the grace window, they're delisted — the pjdurden/claude-skills-live policy, adapted for consumers.
Roadmap to real data: once install flows run through the site, ranking graduates to real signals — install counts, 7-day retention (did the skill stay enabled?), completion rates, and ratings from installers only (the Chrome Web Store rule).
5Install mechanics
Installing into a chat assistant should feel like chatting — not like configuring software. Four mechanisms, stacked:
The 3-tab install panel (stolen from ClawHub). Every entry page shows three copy-buttoned tabs: Command (CLI one-liner), One-liner (npx-style, Vercel pattern), and Prompt for Muse — a pre-written setup message the user pastes to their assistant, which then performs the install. The prompt tab embeds safety-vetting instructions and required credentials, ClawHub-style.
Agent-executable "Prompt for Muse" messages. The prompt isn't just instructions for a human — it's written so Muse itself can act on it mid-conversation: search the entry, fetch the playbook, and enable it. This is the Vercel find-skills pattern: the agent installs itself with zero context switch.
3-tap connector setup. For connectors: tap Connect → authorize in the app's OAuth screen → confirm in chat. The Composio pattern — the OAuth link arrives in-chat, so the user never leaves the conversation.
"Add to Muse" toolbox cart (stolen from Smithery). A persistent cart: collect entries across the site, review the bundle, then install everything in one agent-executed prompt. The cart doubles as a shareable "skill stack" (see §6).
6Viral loops
Share cards per entry: every skill, connector, and prompt renders an OG card with its rank ("#3 in Productivity · 12.4k installs") — the unit of distribution on X, Threads, and group chats.
Weekly top-10 drops: a ranked "10 skills that actually matter this week" list, pushed to the newsletter and socials. The top-N listicle is the directory's native viral format.
Creator profiles with install counts + embeddable badges: authors get public profiles, live install counts, and a "Featured on Muse Stacks" badge to embed in their READMEs and sites — the GitHub-star mechanics of awesome-lists, ported to the web.
Self-serve submit-your-skill: a public submit form (ClawHub's GitHub-import flow as the model): paste a repo or SKILL.md, get a draft entry, moderators approve. Lowest friction wins the catalog race.
Shareable "skill stacks": bundles that install together — e.g. "New parent stack", "Freelancer finance stack", "Marathon training stack". One link, one agent prompt, a whole setup. Stacks are themselves ranked and shared.
Newsletter: the TAAFT playbook — a weekly "new this week" drop driving traffic back to the site and carrying the premium sponsorship inventory later.
7MVP scope
What shipped (or ships) in v1:
~50 hand-seeded entries across all 8 categories and all 3 types (seed scores clearly labeled editorial)
Ranking + community upvoting with vote decay
Copy/install flows: the 3-tab install panel + "Prompt for Muse" messages + toolbox cart
Trust badges (verified-safe, maintained, documented) and last-verified dates
Public submit-your-skill form
Methodology page — how ranking works, what seed scores mean, the 90-day delisting policy
"New this week" feed — the release-history surface that becomes the newsletter
Deliberately out of v1: real usage telemetry, author dashboards, programmatic SEO pages, monetization. The directory earns trust first, scale second.
Author dashboard — installs, errors, retention per entry (the Smithery publishing analytics model).
Programmatic SEO pages — /skills/<slug>, /category/<name>, /use-case/<slug>, plus pairwise connector × skill pages — the Zapier 50k-page playbook.
Claim/verify monetization — the TAAFT model: creators claim their auto-generated pages and pay for verification tiers and newsletter placement.
Deep-link install — if the Muse product ever supports it, one-tap muse:// (or universal-link) install cards in chat, mirroring the claude:// / cursor:// deep-link buttons used by MCP server authors.
9Open questions
The true one-click surface. Does the Muse product expose a muse:// deep link or an agent-executed install command? Until validated with the product team, the "Prompt for Muse" copy-paste path is the install primitive.
OAuth without leaving chat. How do connectors get authorized without breaking the conversation? The Composio in-chat link pattern is the target UX — but it needs product support for link rendering and token handoff.
Moderation at scale. Manual security review works for 50 entries; it doesn't work for 5,000. What automated vetting (static analysis of SKILL.md, sandbox testing, permission diffing) gates the self-serve submit flow?
External skill repos. Can Muse read external skill repos directly (GitHub raw, versioned bundles), or does every entry need to be mirrored/hosted by the directory? This decides whether Muse Stacks is a registry or an index.