New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

X Agent Intelligence Feed

by dair-ai in dair-ai/dair-academy-plugins

Builds a self-contained HTML digest of AI and agent news pulled from chosen X accounts through the official X MCP server, grouped into categories like Coding Agents and Agent Research.

MITAuto-check passedFrontend & Design

Install X Agent Intelligence Feed

skills CLI
$ npx skills add dair-ai/dair-academy-plugins --skill x-agent-intelligence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dair-ai/dair-academy-plugins x-agent-intelligence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dair-ai/dair-academy-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/x-agent-intelligence/skills/x-agent-intelligence .claude/skills/x-agent-intelligence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
x-agent-intelligence
GitHub stars
614
Token cost
~1.5k tokens
SKILL.md length
742 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Builds a self-contained HTML digest of AI and agent news pulled from chosen X accounts through the official X MCP server, grouped into categories like Coding Agents and Agent Research.

  • Works in 5 steps: Resolve handles with… → Fetch posts with get_users_posts for… → If account feeds are unavailable, use… → …
  • Building a daily HTML digest of AI news from a chosen list of X accounts
  • SKILL.md covers First check, Source configuration, Collect with X MCP and Normalize and select, plus 2 more sections
  • Reaches api.x.com and x.com

What it does

The skill first confirms that an X MCP server, expected at https://api.x.com/mcp, is actually visible to the agent; if no X tools are available it stops and points to a setup reference rather than inventing API responses or quietly switching to scraping. Source configuration is then gathered or inferred separately from story content so it stays editable later: source handles without the @ sign, a lookback window of 24 hours for a daily feed or 7 days for a backlog, categories such as Coding Agents, Frameworks, Agent Research, Papers, Models and Meta, a cap of 10 to 25 stories per day, and whether the output should be a static snapshot or a refreshable data-backed shell.

Collection goes strictly through read-only official X MCP tools: resolving handles to user records, fetching each user's posts with fields like created_at, text and public_metrics, falling back to a from:handle search with explicit time windows when a direct feed is unavailable, and filling in missing post or author details with separate lookup calls. Bookmark writes, Article publishing, likes, reposts and other write tools are explicitly off-limits for this read-only workflow. Collected posts are normalized into a fixed JSON schema before being selected and laid out in the final HTML artifact.

When your agent uses it

  • Building a daily HTML digest of AI news from a chosen list of X accounts
  • Creating a source-account timeline grouped into categories like Agent Research or Papers
  • Refreshing an existing X-based intelligence feed with a new lookback window

Example prompts

  • “Build a daily AI agent news digest from these 10 X accounts.”
  • “Create a 7-day backlog feed grouped by Coding Agents, Models and Meta.”
  • “Refresh my X intelligence feed with the last 24 hours of posts.”

Requirements

  • An official X API MCP server connected to the agent's client

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Resolve handles with get_users_by_usernames, requesting id, name, username, profile_image_url, and verified.
  2. Fetch posts with get_users_posts for each resolved user. Use post.fields including created_at, text, author_id, public_metrics, entities…
  3. If account feeds are unavailable, use search_posts_all with from:handle queries and explicit start_time/end_time windows.
  4. Fetch missing post details with get_posts_by_ids or get_posts_by_id.
  5. Use get_users_by_id only when an expanded author record is missing.

What it can do on your machine

Read from SKILL.md and the folder at commit 0abffdc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.x.com
    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

X Agent Intelligence Feed loads about 1.5k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 742 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dair-ai/dair-academy-plugins at commit 0abffdc, republished under its MIT licence (© dair-ai). 742 words, ~1,513 tokens.

Download SKILL.mdSave it as .claude/skills/x-agent-intelligence/SKILL.md (or your agent's skills folder).
name
x-agent-intelligence
description
Build or refresh a readable local AI and agent intelligence feed from the official X MCP server. Use when the user asks for an X-based digest, monitoring dashboard, daily AI feed, source-account timeline, or a self-contained HTML artifact backed by X posts.

X Agent Intelligence

Create a local, readable HTML intelligence feed from X posts retrieved through the official X API MCP server. The feed is a presentation artifact, not a hosted application.

First check

Confirm that the agent can see an X MCP server. The expected official server is https://api.x.com/mcp. If no X tools are available, stop and point the user to references/x-mcp-setup.md; do not invent API responses or silently substitute scraping.

Read ../../references/x-mcp-setup.md when setup, authentication, client configuration, or portability matters.

Source configuration

Ask for or infer:

  • Source handles, without @.
  • Lookback window, normally 24 hours for a daily feed or 7 days for a backlog.
  • Categories such as Coding Agents, Frameworks, Agent Research, Papers, Models, and Meta.
  • Maximum stories per day, normally 10 to 25.
  • Output path and whether the user wants a static snapshot or a refreshable data-backed shell.

Keep source configuration separate from story content so users can edit it later.

If the user asks to begin with the shared public list, read ../../references/starter-sources.md. It is an optional starting point, not a requirement or a hidden default; users may edit or replace it.

Collect with X MCP

Use the official X MCP tools exposed by the user's client. Tool names may be namespaced by the client, but the expected operations are:

  1. Resolve handles with get_users_by_usernames, requesting id, name, username, profile_image_url, and verified.
  2. Fetch posts with get_users_posts for each resolved user. Use post.fields including created_at, text, author_id, public_metrics, entities, and attachments when supported. Use expansions for author_id, attachments.media_keys, and referenced_tweets.id when supported.
  3. If account feeds are unavailable, use search_posts_all with from:handle queries and explicit start_time/end_time windows.
  4. Fetch missing post details with get_posts_by_ids or get_posts_by_id.
  5. Use get_users_by_id only when an expanded author record is missing.

Do not use bookmark writes, Article publishing, likes, reposts, or other write tools for this skill. This workflow is read-only.

Normalize and select

Convert each post into this schema:

json
{
  "id": "post-id",
  "date": "YYYY-MM-DD",
  "created_at": "ISO timestamp",
  "category": "Models",
  "handle": "OpenAI",
  "author_name": "OpenAI",
  "verified": true,
  "profile_image_url": "https://...",
  "tweet_url": "https://x.com/OpenAI/status/post-id",
  "text": "raw text only when the user wants it retained",
  "title": "Short factual headline",
  "summary": "One or two sentences explaining why it matters.",
  "media_url": null,
  "media_type": null
}

Deduplicate by post ID. Exclude replies and reposts unless explicitly requested. Defensively remove any item with in_reply_to_user_id or a referenced_tweets entry of type replied_to or retweeted, even when the X MCP response ignored the requested exclusion. Prefer original announcements, papers, releases, benchmarks, demos, and concrete engineering reports. Rank using relevance, source quality, recency, engagement, and diversity across accounts. Do not let engagement alone determine importance.

Write titles and summaries as faithful paraphrases. Do not fabricate benchmarks, product capabilities, paper claims, or dates. Preserve the original post URL on every story.

Show full SKILL.md (333 more words)Show less

Render the artifact

Build one self-contained feed.html, using ../../assets/reference-artifact.html as the design reference. Match its editorial reading-list layout closely: warm off-white canvas with a thin dark top rule; compact serif masthead; segmented story stats; a sticky, borderless category-chip toolbar; a narrow left date rail; and reading-list items with the title and "Why it matters" copy on the left and a fixed-size image or video preview on the right. Make the first story of the newest day the lead, with a larger thumbnail and headline.

Requirements:

  • Inline all normalized story data in the artifact. No backend, build step, scheduler controls, or external runtime dependencies; plain HTML, CSS, and JavaScript unless a framework is requested.
  • Include search, category filters, date grouping, source handles, avatars, original-post links, a clear updated timestamp, and image or video previews when media_url is available.
  • Include the source-settings control: it opens a panel where the user can add, remove, copy, and reset X handles. Persist handles only in browser local storage.
  • Use profile_image_url from X when available. Do not require unavatar.io.
  • Use X widget embeds only as an optional enhancement. The feed must remain readable if X widgets fail to load.
  • Seed the handle list from the adopter's own source configuration. The reference may seed the public handles from references/starter-sources.md, but never include credentials, private handles, automation identifiers, or orchestration configuration.
  • Do not expose MCP credentials in the artifact or browser JavaScript.

Validate before handing off

Check:

  • The output opens locally without a backend.
  • Every story has a valid X URL and handle.
  • Dates sort newest first.
  • Filters and search work with zero matching results.
  • Missing avatars, media, and embeds degrade gracefully.
  • No API key, bearer token, client secret, OAuth token, home-directory path, or private MCP URL appears in the output.
  • The artifact labels generated summaries as summaries and links to the original post.

If recurring updates are requested, explain that the user may run the same prompt from any scheduler or orchestrator they choose. X MCP remains the source-access layer.

© dair-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/x-agent-intelligence/skills/x-agent-intelligence of dair-ai/dair-academy-plugins.

Open the folder on GitHubat commit 0abffdc

Compare with similar skills

X Agent Intelligence Feed next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

X Agent Intelligence Feed compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
X Agent Intelligence Feed this skilldair-ai/dair-academy-plugins614—~1.5kAutomated safety check: PassMIT
DocsPrefectHQ/fastmcp28k—~1kAutomated safety check: PassApache-2.0
Typeuibergside/typeui2k—~474Automated safety check: PassMIT
Fast Agent Designevalstate/fast-agent3.9k—~220Automated safety check: PassApache-2.0
Typeuibergside/typeui2k—~473Automated safety check: PassMIT
Xquik MCPXquik-dev/x-twitter-scraper2101 repos~997Automated safety check: PassMIT

Similar skills

  • Docs

    PrefectHQ/fastmcp

    Write or revise a page under docs/ for gofastmcp.com. An agent skill from PrefectHQ/fastmcp.

    28k GitHub stars~1k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Typeui

    bergside/typeui

    Use TypeUI with Hermes Agent to access project design skills, brand kits, UI prompts, and layout variations through the TypeUI MCP server when creating or refining user interfaces.

    2k GitHub stars~474 tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed

  • Fast Agent Design

    evalstate/fast-agent

    A skill your agent uses to generate well-branded interfaces and assets for fast-agent, either for production or throwaway prototypes/mocks/etc.

    3.9k GitHub stars~220 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Typeui

    bergside/typeui

    Use TypeUI with OpenClaw to access project design skills, brand kits, UI prompts, and layout variations through the TypeUI MCP server when creating or refining user interfaces.

    2k GitHub stars~473 tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed

  • Xquik MCP

    Xquik-dev/x-twitter-scraper

    Connect, verify, and troubleshoot Xquik's remote MCP server.

    210 GitHub starsUsed in 1 repo~997 tokens
    Backend & APIsAuto-check passed

  • X Use

    ihuzaifashoukat/x-use

    Install, register, and configure x-use, the browser-native MCP server for X (Twitter) automation that needs no X API key.

    171 GitHub stars~1.7k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from dair-ai/dair-academy-plugins

All 8 skills in this repo

  • Research Wiki Builder

    dair-ai/dair-academy-plugins

    Creates and maintains configurable research wikis: scaffold a folder, add sources, compile pages and indexes, and file query answers back.

    614 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed

  • Gemini Image Generator

    dair-ai/dair-academy-plugins

    Generates and edits images with Google's Gemini Nano Banana Pro model through the Gemini API, including photo edits and multi-image composition.

    614 GitHub starsUsed in 2 repos~3.5k tokens
    Auto-check: notes

  • Survey Paper Generator

    dair-ai/dair-academy-plugins

    Builds a single-file HTML survey paper on an AI or ML topic from a research bundle the agent curates, with prose and SVG figures written by Kimi K2.6.

    614 GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check: notes

  • YouTube Talk Notetaker

    dair-ai/dair-academy-plugins

    Converts a YouTube talk into a markdown study note with slide images, a timestamped transcript and editable notes, browsable through a small local server.

    614 GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check passed

  • Learn

    dair-ai/dair-academy-plugins

    Help a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study guides, or exercises.

    614 GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

  • LLM Council on Fireworks AI

    dair-ai/dair-academy-plugins

    Has several open-weight models answer a question, rank each other's anonymized answers, then lets a chairman model write the final response through Fireworks AI.

    614 GitHub stars~5k tokensUpdated 2 mo ago
    Auto-check: notes

Works with

Categories

Questions about X Agent Intelligence Feed

What does X Agent Intelligence Feed do?

Builds a self-contained HTML digest of AI and agent news pulled from chosen X accounts through the official X MCP server, grouped into categories like Coding Agents and Agent Research. com/mcp, is actually visible to the agent; if no X tools are available it stops and points to a setup reference rather than inventing API responses or quietly switching to scraping. Source configuration is then gathered or inferred separately from story content so it stays editable later: source handles without the @ sign, a lookback window of 24 hours for a daily feed or 7 days for a backlog, categories such as Coding Agents, Frameworks, Agent Research, Papers, Models and Meta, a cap of 10 to 25 stories per day, and whether the output should be a static snapshot or a refreshable data-backed shell.

When should I use X Agent Intelligence Feed?

X Agent Intelligence Feed fits situations like: building a daily HTML digest of AI news from a chosen list of X accounts; creating a source-account timeline grouped into categories like Agent Research or Papers; refreshing an existing X-based intelligence feed with a new lookback window.

How do I install X Agent Intelligence Feed in Claude Code?

Run `npx skills add dair-ai/dair-academy-plugins --skill x-agent-intelligence -a claude-code`. Or copy the skill folder (plugins/x-agent-intelligence/skills/x-agent-intelligence in dair-ai/dair-academy-plugins) into .claude/skills/x-agent-intelligence in your project. Claude Code loads it when a task matches its description.

How do I install X Agent Intelligence Feed in Codex?

Run `npx skills add dair-ai/dair-academy-plugins --skill x-agent-intelligence -a codex`. Or copy the skill folder (plugins/x-agent-intelligence/skills/x-agent-intelligence in dair-ai/dair-academy-plugins) into .agents/skills/x-agent-intelligence in your project. Codex loads it when a task matches its description.

Can I use X Agent Intelligence Feed in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dair-ai/dair-academy-plugins --skill x-agent-intelligence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/x-agent-intelligence, .gemini/skills/x-agent-intelligence, .github/skills/x-agent-intelligence and .opencode/skills/x-agent-intelligence in your project.

What does X Agent Intelligence Feed need to run?

SKILL.md names no scripts, command-line tools or credentials: X Agent Intelligence Feed is instructions for the agent only. Our summary lists: An official X API MCP server connected to the agent's client.

Does X Agent Intelligence Feed access the network?

SKILL.md names 2 domains. In commands or code: api.x.com and x.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is X Agent Intelligence Feed safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does X Agent Intelligence Feed use?

X Agent Intelligence Feed is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does X Agent Intelligence Feed use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to X Agent Intelligence Feed?

Skills that share tags, products or a category with X Agent Intelligence Feed: Docs (PrefectHQ/fastmcp, 28k stars), Typeui (bergside/typeui, 2k stars), Fast Agent Design (evalstate/fast-agent, 3.9k stars) and Typeui (bergside/typeui, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains X Agent Intelligence Feed?

dair-ai (a GitHub organization) maintains it in dair-ai/dair-academy-plugins, which has 614 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on July 21, 2026.

Source: dair-ai/dair-academy-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.