The post that gets traction isn't the first one — it's the fifteenth. Most tools die before anyone gets there because after the launch spike, daily distribution is just repetitive manual work: write a post, pick a channel, pick an angle, stay under 280 characters for X but 500 for Mastodon, check what you already said last week, repeat tomorrow.
I built marketing-pipeline to handle that recurring work after a project ships.
Onboarding a new project is one command:
marketing onboard --name my-tool --repo owner/repo --kind mcp-server
That fetches the README, sends it to Claude, and saves a structured profile — problem statement, specific facts, rotation angles — to projects.yml. After that, a GitHub Actions cron at 14:00 UTC on weekdays runs marketing cycle, which picks the least-recently-used angle for each project, drafts channel-appropriate posts, and publishes across Bluesky, Dev.to, Hashnode, and Mastodon without any manual intervention.
Two constraints worth knowing about. First, per-channel length limits are enforced in code: 280 chars for X, 300 for Bluesky, 500 for Mastodon, 150–400 words for Dev.to and Hashnode. Second, there's an antislop gate in pipeline/antislop.py that hard-rejects specific tokens before any post goes out — "excited", "game-changer", "unlock", "AI-powered", emoji, hashtags, and exclamation points are all blocked at the gate. The drafts read like a practitioner wrote them or they don't ship.
The kind field routes projects to type-specific directories automatically. An mcp-server hits MCP Registry, Smithery, Glama, and PulseMCP; a claude-skill targets awesome-claude-code (payload generated, but their rules require a human to submit via GitHub issue — that one can't be fully automated); a browser-extension covers Chrome Web Store, Firefox AMO, and Edge Add-ons.
Requirements: Anthropic API key, plus credentials for at least Bluesky, Dev.to, and Hashnode. Mastodon and Slack are optional.
Top comments (0)