twitter-reader

An agent skill by daymade, from daymade/claude-code-skills. Tags: download, image, markdown, social-listening, web.

What it does

Fetch Twitter/X post content including long-form Articles with full images and metadata. Use when Claude needs to retrieve tweet/article content, author info, engagement metrics, and embedded media. Supports individual posts and X Articles (long-form content). Automatically downloads all images to local attachments folder and generates complete Markdown with proper image references. Preferred over Jina for X Articles with images.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill twitter-reader

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/twitter-reader ~/.claude/skills/twitter-reader

Safety box score

Grade C, moderate risk: 35 of 100 risk points, rated 2026-09-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill fetches Twitter/X post and article content from third-party services, then writes Markdown plus downloaded images to a local output directory. The main risks are network exposure to external APIs, bearer-token handling for `JINA_API_KEY`, and runtime execution of externally fetched Python packages via `uv run`.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It runs external commands directly (`curl`, `uv run`, `twitter`) via `subprocess.run` and a shell script, so you are granting the skill real command execution even though the commands are mostly fixed.
Network access	2 (moderate)	It sends X URLs to `api.fxtwitter.com` and `r.jina.ai`, and `fetch_article.py` also downloads every referenced image from `pbs.twimg.com`.
Filesystem reach	1 (low)	The scripts write Markdown files and an `attachments/` tree under the chosen output directory, but they do not edit system paths or delete outside the target folder.
Secrets & credentials	2 (moderate)	Both Jina-based scripts require `JINA_API_KEY` and pass it as `Authorization: Bearer ...` to `r.jina.ai`, which exposes a bearer token to a remote service and local process arguments.
Privilege & persistence	0 (none)	There is no sudo use, global install, service registration, or shell/OS configuration change.
Instruction hijack surface	0 (none)	The files contain explanatory text about refusals and markers, but nothing that tells the agent to ignore its instructions or hide behavior.
Irreversible actions	0 (none)	It only retrieves content and saves files locally; it does not post, merge, pay, book, or delete on the person's behalf.
Transparency	2 (moderate)	`uv run --with twitter-cli` and `uv run --with pyyaml` fetch and execute external packages at runtime, and the skill does not pin versions, so not all executed code is present in the repository.

Before installing

Confirm you are okay sending the target X URL and `JINA_API_KEY` to `r.jina.ai`.
Inspect `scripts/fetch_article.py` and decide whether on-demand `uv run --with twitter-cli` package downloads are acceptable.
Test in a scratch directory and verify it only creates files under the chosen `output_dir`.
If process-list exposure matters, avoid the Bash wrapper and rotate the Jina key after use.

Rated 2026-09-20 by an automated review of 4 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: twitter-reader/SKILL.md
Branch: main
Updated: 2026-09-20

download-gemini-images — Download, export, save, or package images from a Google Gemini conversation/chat/app page.
llm-icon-finder — Finding and accessing AI/LLM model brand icons from lobe-icons library.
wps-doc-scraper — Faithfully archive public WPS/KDocs/金山文档 links, especially embedded ProcessOn .pof mind maps and canvases, as raw source data, original SVG/PNG.
scrapling-skill — Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages.
last30days — Research what people actually say about any topic in the last 30 days.
vitepress — VitePress static site generator powered by Vite and Vue. Use when building documentation sites, configuring themes, or writing Markdown with Vue components.