jb_hn
It's very easy to churn out code that isn't particularly additive (or in some cases, actively destructive), so adjusting for that would be important.
I think the situation can both be "bad" and "better than it was before," but to your point, some of the recent actions (e.g., curating histories) definitely seem counterproductive.
Show HN: Open-source job search plugin for Claude Code
https://github.com/agent-data/job-search
Hey HN,I wanted to share an open source plugin + skills I put together that turn Claude Code into a job search assistant. The goal is to minimize the amount of time needed to find interesting and relevant jobs.How it works:1. Clone the repo, install the plugin, and run `/job-search`2. Claude will ask a few questions to understand the roles you’re interested in and save your preferences...
Progressive disclosure has obvious benefits, but I think it would be more valuable to address how agents using either approach can still know which MCP server to search through. Maybe each tool has a search interface, and agents kick off searches in parallel for any ‘yet to be discovered’ tools, but there may be downsides to that as well
Show HN: An open source job search plugin for Claude Code
https://github.com/agent-data/job-search
Hey HN,I wanted to share an open source plugin + skills I put together that turn Claude Code into a job search assistant. The goal is to minimize the amount of time needed to find interesting and relevant jobs.How it works: 1. Clone the repo, install the plugin, and run `/job-search` 2. Claude will ask a few questions to understand the roles you’re interested in and save your preferences...
Agents Just Need APIs
The title and content suggest that it's about AI-native distribution, and that MCP servers are the answer (i.e., the old world prioritized good docs; now, if you want to be discoverable by agents, you need an MCP server). But it assumes agents can just "discover" arbitrary MCP servers (as if Claude would "just know" that you have an MCP server).. which is not the case?
Show HN: Agent-data – a CLI for giving agents real-time, structured data
Hey HN, Justin here, and we’re building agent-data: a CLI tool that gives AI agents access to real-time, structured data without requiring them to use browser automation.The idea came from trying to get agents (e.g., OpenClaw, Hermes Agent) to perform more useful tasks than simply organizing our calendars or monitoring our emails. We wanted them to answer questions and take actions that depend...
That said, I think this article demonstrates that focusing on whether or not an article used AI might be focusing on the wrong “problem.” I appreciate being sensitive to the "smell" (the number of low-effort, AI posts flying around these days has made me sensitive too), but personally, I found this article both (1) easy to read and (2) insightful. I think the number of AI-written content lacking (2) is the problem.
Curious if you’ve noticed any particularly well defined, obscure websites? Would love to take a look if so.
Show HN: Motie – Replit for Web Scraping
Hey HN, Justin here. We’re building Motie (https://app.motie.dev), an AI agent that extracts structured data from the web and generates web scraping code, using natural language.We started building Motie a few months back with the goal of creating an “AI Data Engineer.” We took a ‘forward deployed engineer’-style approach to refine our scope (and to avoid "boiling the ocean”) and noticed...