AI Signal Radar

    1

    Automated AI news aggregator that fetches arXiv/HN signals and generates platform-validated content drafts.

    $3.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Signal Radar

    Example session with this skill installed

    Fetch the top 3 AI stories from Hacker News and arXiv, give me a brief for each, and then draft a LinkedIn post about them.

    • Read your context and instructions
    • Compiled the ai signal radar

    I have fetched the latest signals and prepared the briefs and LinkedIn draft.

    AI News Briefs

    TitleSourceImpactURL
    Scaling Laws for PrecisionarXivAnalyzes how quantization affects model performance at scale.https://arxiv.org/abs/2405.00001
    LLM-based Agentic WorkflowsHacker NewsCommunity discussion on the shift from prompt engineering to agent loops.https://news.ycombinator.com/item?id=40200000
    New Sparse Autoencoder DiscoveryarXivResearch into interpreting hidden layers of frontier models.https://arxiv.org/abs/2405.00002

    LinkedIn Draft

    The landscape of AI is shifting from static prompts to agentic workflows. Recent discussions on Hacker News highlight a significant trend: developers are moving away from simple one-shot prompts toward iterative loops where models use tools and self-correct.

    Complementing this, new research from arXiv explores the scaling laws for precision, providing a roadmap for how we can maintain performance while reducing compute through smarter quantization. Finally, the quest for interpretability continues with breakthroughs in sparse autoencoders, helping us peek inside the "black box" of frontier models.

    Stay updated on these technical shifts to keep your deployment strategies relevant.

    #AI #MachineLearning #LLMs #Research

    Next steps

    • Copy the LinkedIn draft to your clipboard.
    • Run python scripts/check_format.py --platform linkedin draft.txt to verify no illegal Markdown remains.
    • Review the source links to add personal commentary before posting manually.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Keeping up with the firehose of AI research and community trends is a full-time job. This skill automates the discovery and synthesis of AI developments, turning raw feeds into structured briefs and platform-ready content drafts without requiring manual web searching or API keys.

    What it does

    • Fetch signals through a Python script that and optionally GitHub Trending (off by default).
    • Synthesize briefs using a JSON schema to ensure every update includes technical impact, source URLs.
    • Draft content for X (Twitter), LinkedIn, or blogs based on specific platform formatting constraints.
    • Validate formatting by running drafts through a checker that flags character-count and link-placement violations; --fix strips Markdown for LinkedIn before you post.
    • Handle untrusted data by treating all external titles and summaries as raw material, instructs the agent to treat fetched titles and summaries as data, never as instructions within news titles.

    How it works

    1. Run scripts/fetch_signals.py to retrieve a JSON array of the latest AI-related papers and stories.
    2. Generate structured briefs for each item following the brief_schema.json specifications.
    3. Create draft posts for a requested platform (X, LinkedIn, or Blog) using the platform_rules.md and style_guide.md.
    4. Execute scripts/check_format.py on the draft to verify it meets platform-specific character and formatting limits.

    Frameworks & tools

    This skill requires Python 3.9+ and the requests library. It interacts with the arXiv API, Hacker News API, and GitHub Trending.

    Why this beats prompting it yourself

    Manual prompting often results in hallucinated links or posts that exceed platform character limits. This skill uses dedicated scripts to fetch real-time data and a validation loop to ensure drafts actually fit their target platform without manual editing.

    Use cases

    • Generate a daily summary of the latest cs.AI submissions from arXiv.
    • Monitor Hacker News for trending AI discussions and GitHub for new repositories.
    • Draft a validated X thread summarizing the top one or two AI news items of the day.
    • Create a LinkedIn-safe technical update that removes unsupported Markdown formatting.

    Known limitations

    Facts are not independently verified. X character counts use strict string length. arXiv coverage is limited to the last four days of submissions. GitHub scraping is disabled by default.

    Does not verify facts. X counts use plain string length. arXiv limited to last 4 days. GitHub scraping off by default. No publishing capability; drafts only.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Requires

    GitHub
    Arxiv
    Firebaseio
    Python
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Allowed Hosts

    export.arxiv.org
    github.com
    hacker-news.firebaseio.com
    Listed23 days ago

    What's inside

    Frequently Asked Questions

    The included check_format.py script checks each draft against platform rules: 2–3 tweets of up to 280 characters each with no link in the first tweet for X, a 3,000-character limit for LinkedIn, and frontmatter for blog posts. It reports exactly which rule failed so your assistant can rewrite the draft, and its --fix option can strip Markdown from LinkedIn drafts. Always review drafts before posting.

    Two Python scripts (a news fetcher and a format checker), a brief template that defines the fields of each news brief, platform rules for X, LinkedIn and blogs, a writing style guide, sample briefs and drafts, a README with setup steps, and the MIT license.

    Tested in Claude Code. It should also work in other assistants that support agent skills (SKILL.md) and can run Python 3.9+ scripts with internet access, but Cursor, GitHub Copilot and the Claude.ai apps have not been tested yet.

    No, the skill is designed to work out of the box using public APIs for arXiv and Hacker News, meaning you don't need to manage your own API keys for these primary data sources.

    AI Signal Radar pulls recent AI research from arXiv and AI stories from Hacker News, writes a structured brief for each, and can turn them into X, LinkedIn or blog drafts checked against each platform's format rules. You review the drafts and publish them yourself.

    New in Research & Analysis