igloo302/interest-radar

★ 19Audience · generalComplexity · 1/5ActiveSetup · easy

Mindmap

mindmap
  root((interest-radar))
    Inputs
      Link
      Text passage
      User feedback
    Outputs
      Relevance score
      Reasoning
      Read or skip verdict
    Use Cases
      Filter shared links
      Batch filter recommendations
      Tune scores over time
    Tech Stack
      Markdown
      SKILL md
      Agent runtime

mindmap root((interest-radar)) Inputs Link Text passage User feedback Outputs Relevance score Reasoning Read or skip verdict Use Cases Filter shared links Batch filter recommendations Tune scores over time Tech Stack Markdown SKILL md Agent runtime

Things people build with this

USE CASE 1

Forward a link to your agent and get a relevance verdict before reading it

USE CASE 2

Call batch_judge from another skill to filter a feed down to high-relevance items

USE CASE 3

Train the radar over time by confirming or dismissing past judgments

USE CASE 4

Install the skill into Claude Code or Cursor without adding a Python runtime

Tech stack

MarkdownAgentSkill

Getting it running

Difficulty · easy Time to first run · 5min

No runtime to install, but the skill needs an agent that exposes some memory or search tool at runtime to do useful scoring.

In plain English

Interest Radar is a small skill module that judges whether a piece of outside content is relevant to you. The README states what it does not do as clearly as what it does: it does not collect data, it does not push notifications, and it does not store anything. Its single job is to look at a link or a passage you share and tell you how related it is to your interests, why it reached that conclusion, and whether you should bother reading further. The project is described as platform-agnostic. It is not tied to one specific agent system, so the same files can run inside Hermes, Claude Code, Codex, Cursor, or ChatGPT, according to the README. It also has no code dependency. The whole behavior is defined in a SKILL.md file rather than a Python script or external runtime, which the author calls a zero code dependency design. At runtime the skill is meant to detect whatever memory or search tools happen to be available and use those, without assuming any particular tool exists. The README lists three small capabilities the author calls MVP features. The first is forwarding a link and asking about it, which triggers a relevance check and returns a judgment. The second is a batch_judge interface that other recommendation skills can call to filter a list down to only the high-relevance items. The third is a feedback loop: when the user replies with confirm or dismiss, those responses are supposed to adjust later scoring so the judgments improve with use. Installation is described as copying the SKILL.md file and a references folder into the agent's skills directory. The README also points to a set of reference documents in that folder covering the batch interface, the feedback loop, the output format, and a snapshot cache scheme. The README itself is short and does not go into deeper implementation detail beyond that.

Copy-paste prompts

Prompt 1

Install Interest Radar by copying SKILL.md and references into my agent skills folder, then test it on a link

Prompt 2

Use Interest Radar to score this article URL against my stated interests and tell me whether to read it

Prompt 3

Call interest-radar batch_judge on these 20 links and return only the ones scored high relevance

Prompt 4

Wire Interest Radar feedback into my agent so confirm and dismiss adjust later scoring

Prompt 5

Read the references folder and summarise the snapshot cache scheme Interest Radar uses

Open on GitHub → Explain another repo

Generated 2026-05-22 · Model: sonnet-4-6 · Verify against the repo before relying on details.