{ "markdown": "
\n\n\"Schedulala\n\n# Schedulala\n\n### Your agent posts. Replies. Measures. Listens.\n\n**12 Platforms. Any Agent. One Prompt.**\n\n[![npm CLI](https://img.shields.io/npm/v/schedulala?label=schedulala&color=cb3837)](https://www.npmjs.com/package/schedulala)\n[![npm MCP server](https://img.shields.io/npm/v/%40schedulala%2Fmcp-server?label=%40schedulala%2Fmcp-server&color=cb3837)](https://www.npmjs.com/package/@schedulala/mcp-server)\n[![License MIT](https://img.shields.io/badge/License-MIT-blue)](LICENSE)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-com.schedulala%2Fschedulala-8A2BE2)](https://registry.modelcontextprotocol.io/v0/servers?search=schedulala)\n[![X Follow](https://img.shields.io/badge/X-%40schedulala-000)](https://x.com/schedulala)\n\n
\n\n---\n\nSchedulala teaches any AI agent to run your social media end to end: schedule\nand publish to **12 platforms** — Twitter/X, Instagram, TikTok, LinkedIn,\nYouTube, Facebook, Threads, Bluesky, Pinterest, Mastodon, Telegram, and Google\nBusiness Profile — with **first comments on 8 of them through one API field**,\nevery post **validated against each platform's character limits and media\nrules before anything publishes**, plus analytics, comment triage, and keyword\nlistening from the same conversation. The skill was tested against genuinely\ncold agents until one installed, connected, and posted with zero human help.\n\n## Quick start\n\nWorks with OpenClaw, Hermes, Claude Code, Cursor, Codex, claude.ai, ChatGPT,\nand anything with a shell. Per-runtime guides: [schedulala.com/agents](https://schedulala.com/agents).\n\n**CLI · MCP (remote or stdio) · sandbox keys that never publish**\n\nGet your API key from [schedulala.com](https://schedulala.com/dashboard?view=developer), then send this message to your agent:\n\n> Read https://schedulala.com/SKILL.md and follow it to set up Schedulala.\n> My API key is sk_live_·········\n\nThat's the whole install. The hosted skill walks your agent through the CLI\n(`npm i -g schedulala`, zero tool-schema tokens), or MCP if you prefer typed\ntools — and teaches the safe workflow: draft → validate/preview → confirm →\npublish → verify, plus the per-platform rules that reject posts (TikTok\nprivacy + postMode, Instagram media, YouTube titles, character limits, …).\n\nNo key yet? A free one takes two minutes (`npx schedulala init --email\nyou@example.com`) and includes 2 connected accounts and 4 posts to try the\nloop. `sk_test_` keys simulate everything without publishing.\n\n## The hosted connector (claude.ai / Claude Desktop / ChatGPT)\n\nNo install at all — interactive widgets included (post previews, in-chat\nmedia upload, analytics cards, calendar, inbox). In Claude:\n**Settings → Connectors → Add custom connector** and paste:\n\n```\nhttps://schedulala.com/api/mcp\n```\n\nOAuth sign-in, no API key handling. Requires a paid Claude plan for custom\nconnectors; the same URL works in ChatGPT.\nSetup guide: https://schedulala.com/developers/docs/claude-connector\n\n

\n \"Connecting\n   \n \"Posting\n

\n

\n Set up in two minutes — then post everywhere from one chat.
\n Full 45s demo (sound on) ·\n Setup ·\n Posting ·\n Comments ·\n Bulk ·\n Best times ·\n Analytics\n

\n\n## Install the skill locally (optional)\n\nThe one-liner above needs no install. If your runtime prefers a local skill:\n\n```bash\n# skills CLI\nnpx skills add schedulala/schedulala-agent\n\n# Claude Code plugin marketplace\n/plugin marketplace add schedulala/schedulala-agent\n\n# OpenClaw (ClawHub)\nopenclaw skills install schedulala\n\n# plain git\ngit clone https://github.com/schedulala/schedulala-agent ~/.claude/skills/schedulala-agent\n```\n\nPair it with either:\n\n- the **local MCP server** — `npx -y @schedulala/mcp-server` with\n `SCHEDULALA_API_KEY` (Claude Desktop / Claude Code / Cursor config in the\n [package README](https://www.npmjs.com/package/@schedulala/mcp-server)), or\n- the **CLI** — `npx schedulala init --email you@example.com`, then\n `npx schedulala post \"Hello\" --platforms twitter --now`. Every command\n supports `--json`; exit codes 0–7.\n\n## What's in this repo\n\n```\nskills/schedulala/SKILL.md the skill: install, workflow, rules, decision trees\nskills/schedulala/references/ per-platform schemas, media protocol, CLI, widgets\nexamples/ ready-to-adapt JSON payloads (tiktok, threads, bulk, …)\n.claude-plugin/ Claude Code plugin + marketplace manifest\n```\n\n## Links\n\n- Developer docs (REST API, CLI, connector): https://schedulala.com/developers/docs\n- Per-agent setup pages: https://schedulala.com/agents\n- Connector setup: https://schedulala.com/developers/docs/claude-connector\n- Claude integration page: https://schedulala.com/integrations/claude\n- CLI on npm: [`schedulala`](https://www.npmjs.com/package/schedulala) ·\n MCP server on npm: [`@schedulala/mcp-server`](https://www.npmjs.com/package/@schedulala/mcp-server)\n- Pricing: https://schedulala.com/pricing\n\n## License\n\nMIT — see [LICENSE](LICENSE). The skill documents the Schedulala service,\nwhich is a separate commercial product.\n", "bytes": 6004, "sha": "674a150c965e95ac8c5d37c0d2c613afec6692294aaa8a94c41bef42d39ad34a", "repo_slug": "schedulala/schedulala-agent", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_com_schedulala_schedulala_c51827fb/readme" }