himself65/finance-skills

twitter-reader

Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications.

ソースを見る
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Twitter Skill (Read-Only)

Reads Twitter/X for financial research using opencli, a universal CLI tool that bridges web services to the terminal via browser session reuse.

This skill is read-only. It is designed for financial research: searching market discussions, reading analyst tweets, tracking sentiment, and monitoring financial news on Twitter/X. It does NOT support posting, liking, retweeting, replying, or any write operations.

Important: opencli reuses your existing Chrome login session — no API keys or cookie extraction needed. Just be logged into x.com in Chrome and have the Browser Bridge extension installed.


Step 1: Ensure opencli Is Installed and Ready

Current environment status:

!`(command -v opencli && opencli doctor 2>&1 | head -5 && echo "READY" || echo "SETUP_NEEDED") 2>/dev/null || echo "NOT_INSTALLED"`

If the status above shows READY, skip to Step 2. If NOT_INSTALLED, install first:

bash
# Install opencli globally
npm install -g @jackwener/opencli

If SETUP_NEEDED, guide the user through setup:

Setup

opencli requires Node.js >= 20 and a Chrome browser with the Browser Bridge extension:

  1. Install the Browser Bridge extension:
  • Download the latest opencli-extension-v{version}.zip from the GitHub Releases page
  • Unzip it, open chrome://extensions in Chrome, and enable Developer mode
  • Click Load unpacked and select the unzipped folder
  1. Login to x.com in Chrome — opencli reuses your existing browser session
  2. Verify connectivity:
bash
opencli doctor

This auto-starts the daemon, verifies the extension is connected, and checks session health.

Common setup issues

SymptomFix
Extension not connectedInstall Browser Bridge extension in Chrome and ensure it's enabled
Daemon not runningRun opencli doctor — it auto-starts the daemon
No session for twitter.comLogin to x.com in Chrome, then retry
CSRF token missingRefresh x.com in Chrome to regenerate the ct0 cookie

Step 2: Identify What the User Needs

Match the user's request to one of the read commands below, then use the corresponding command from references/commands.md.

User RequestCommandKey Flags
Setup checkopencli doctor—
Home feed / timelineopencli twitter timeline`--type for-you\following, --limit N` (default 20)
Search tweetsopencli twitter search "QUERY"`--filter top\live, --limit N` (default 15)
Trending topicsopencli twitter trending--limit N (default 20)
Bookmarksopencli twitter bookmarks--limit N (default 20)
Recent tweets from a useropencli twitter tweets USERNAME--limit N (default 20)
View a specific threadopencli twitter thread TWEET_ID--limit N (default 50)
Twitter articleopencli twitter article TWEET_ID—
User profileopencli twitter profile USERNAME— (defaults to logged-in user)
Followersopencli twitter followers USERNAME--limit N (default 50)
Followingopencli twitter following USERNAME--limit N (default 50)
Notificationsopencli twitter notifications--limit N (default 20)

Step 3: Execute the Command

General pattern

bash
# Use -f json or -f yaml for structured output
opencli twitter timeline -f json --limit 20
opencli twitter timeline --type following --limit 20

# Recent tweets from a specific user
opencli twitter tweets elonmusk --limit 20 -f json

# Searching for financial topics
opencli twitter search "$AAPL earnings" --filter live --limit 10 -f json
opencli twitter search "Fed rate decision" --limit 20 -f yaml

# Trending topics
opencli twitter trending --limit 20 -f json

Key rules

  1. Check setup first — run opencli doctor before any other command if unsure about connectivity
  2. Use `-f json` or `-f yaml` for structured output when processing data programmatically
  3. Use `-f csv` when the user wants spreadsheet-compatible output
  4. Use `--limit N` to control result count — start with 10-20 unless the user asks for more
  5. For search, use `--filter` — top (default) for relevance, live for latest tweets
  6. Read-only — don't post, like, retweet, reply, quote, follow, or delete, even though opencli exposes some of these commands

Output format flag (-f)

FormatFlagBest for
Table-f table (default)Human-readable terminal output
JSON-f jsonProgrammatic processing, LLM context
YAML-f yamlStructured output, readable
Markdown-f mdDocumentation, reports
CSV-f csvSpreadsheet export

Output columns

Tweet-listing commands (timeline, search, thread) include: id, author, text, created_at, likes, retweets, replies, views, url, has_media, media_urls.

tweets (per-user posts) also includes is_retweet.

bookmarks columns: author, text, likes, retweets, bookmarks, url.

trending columns: rank, topic, tweets, category.

Profile (profile) columns: screen_name, name, bio, location, url, followers, following, tweets, likes, verified, created_at.

followers / following columns: screen_name, name, bio, followers.

notifications columns: id, action, author, text, url.


Step 4: Present the Results

Lead with what matters for the user's research question rather than a raw dump. Attribute each tweet (@handle, text, engagement such as likes and views, and the URL when the user may want the full thread), group search results by theme, and note the bullish or bearish lean and where views are consensus or contrarian. For profiles, give follower count, bio, and notable recent activity. Keep browser session details private.


Step 5: Diagnostics

If something isn't working, run:

bash
opencli doctor

This checks daemon status, extension connectivity, and browser session health.


Error Reference

ErrorCauseFix
Extension not connectedBrowser Bridge not installed/enabledInstall extension and enable it in Chrome
No sessionNot logged into x.comLogin to x.com in Chrome
CSRF token missingCookie expired or page needs refreshRefresh x.com in Chrome
Rate limitedToo many requestsWait a few minutes, then retry

Reference Files

  • references/commands.md — Complete read command reference with all flags, research workflows, and usage examples
  • references/schema.md — Output format documentation and column definitions

Read the reference files when you need exact command syntax, research workflow patterns, or output details.

同じリポジトリから

関連する Skills

すべての Skills
himself65
コミュニティ

company-valuation

Estimate a public company's intrinsic value with DCF, relative (peer multiple), and sum-of-the-parts (SOTP) methods, then blend them into an implied share price with upside/downside vs the market price, a WACC and terminal-growth sensitivity grid, and bull/base/bear scenarios. Use this skill whenever the user asks what a company or ticker is worth: fair value, intrinsic value, implied share price, a price target from fundamentals, whether it is overvalued or undervalued, building a DCF (WACC, te

導入数
4
GitHub Stars
3388
更新日
10月5日
himself65
コミュニティ

earnings-preview

Build a pre-earnings briefing for a stock from Yahoo Finance data (yfinance): the upcoming report date and timing, consensus EPS and revenue estimates with their range, the beat/miss track record, analyst ratings and price targets, and what to watch in the print. Use this skill whenever the user is preparing for an upcoming earnings report or asks what the street expects — consensus or whisper numbers, EPS expectations, whether a company will beat, an earnings setup, or an earnings-season previe

導入数
4
GitHub Stars
3388
更新日
10月5日
himself65
コミュニティ

earnings-recap

Analyze a company's most recent (or a specified past) earnings report from Yahoo Finance data (yfinance): actual vs estimated EPS, surprise size, revenue and margin trends, and the stock's price reaction. Use this skill whenever the user asks how earnings went — beat or miss, earnings surprise, quarterly results, the post-earnings move, or an earnings call recap — including casual references to a past report such as "AMZN reported last night" or "how did they do". For an upcoming report, use ear

導入数
4
GitHub Stars
3388
更新日
10月5日
himself65
コミュニティ

estimate-analysis

Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over 7/30/60/90 days and up/down revision breadth, growth estimates vs industry, sector, and the S&P 500, and historical estimate accuracy. Use this skill when the user wants more than a single estimate lookup: estimate revisions or momentum, EPS trend, consensus changes, forward or next-quarter and annual estimat

導入数
4
GitHub Stars
3388
更新日
10月5日