build-signal-engine
Build a personal signal engine from scratch - a system that reads every source someone cares about each day (changelogs and release notes, communities, feeds, videos, papers), makes a quick decision on every item, lets an LLM read only what survives, and delivers one short digest. Interviews the user first to pin down what they need to keep up with, the sources where it actually shows up, and the one question that decides what is worth their time, then builds it one stage at a time into their own repo, proving each stage on real data. Agnostic about the coding agent, the decision model and where the data comes from. Use when the user wants to keep up with AI or their field without doomscrolling, build an AI news digest, a daily briefing, a content engine, a research or competitor monitor, a changelog watcher, or "something that reads everything and tells me what matters"; and when they mention signal vs noise, an information diet, or falling behind.
Install
With your agent
Install OMGSkills skill "coleam00/skills:build-signal-engine" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/coleam00/skills /tmp/skills && ln -s /tmp/skills/.claude/skills/build-signal-engine ~/.claude/skills/build-signal-engineFrom README
Build a signal engine What the user typed: $ARGUMENTS If a path was given, it is the repo to build in; confirm it in one sentence. If not, ask whether to start a new folder or use the current one. Then go straight to Round 1. A signal engine reads everything so its owner doesn't have to. Every morning it pulls from the places things actually happen, decides on every single item, hands an LLM only the few worth reading, and delivers one digest. Keeping up is a filtering problem, not a reading problem. Reading more makes people feel more behind. The engine encodes the user's own filter and runs it on everything. Build it into the user's repo. Do not hand them a plan. Every stage below ends with code committed and output from a real run they can look at. --- Output discipline The interview and the build are long. What you say is not. | Moment | Budget | |---|---| | Between questions | Nothing. Ask the next one.
More skills
archon-cli
Drive Archon through its CLI: run AI workflows on a repo, watch and answer the runs that need a decision, drive the...
archon
Interactive Archon integration for knowledge base and project management via REST API.
excalidraw-diagram
Used to create Excalidraw diagram JSON files that make visual arguments.