Agent skill

Twitter Hand Skill

by RightNow-AI in RightNow-AI/openfang

Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

Apache-2.0Auto-check passedWriting & Content

Install Twitter Hand Skill

skills CLI
$ npx skills add RightNow-AI/openfang --skill twitter-hand-skill -a claude-code

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

GitHub CLI
$ gh skill install RightNow-AI/openfang twitter-hand-skill --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/RightNow-AI/openfang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/openfang-hands/bundled/twitter .claude/skills/twitter-hand-skill && 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
twitter-hand-skill
GitHub stars
18k
Token cost
~2.9k tokens
SKILL.md length
959 words
Files
2
Skills in repo
68
Repo updated
First seen
Licence
Apache-2.0

At a glance

Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

  • Works in 3 steps: Post first tweet → get tweet_id → Post second tweet with… → Repeat for each tweet in thread
  • Tasks that involve Content strategy
  • SKILL.md covers Twitter API v2 Reference, Content Strategy Framework, Tweet Writing Best Practices and Engagement Playbook, plus 4 more sections
  • Calls curl; reaches api.twitter.com; needs TWITTER_BEARER_TOKEN

What it does

Twitter Hand Skill is an agent skill from RightNow-AI/openfang. Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Writing & Content, covering Content strategy and Social media posts. It works with X (Twitter). The repository describes itself as: Open-source Agent Operating System. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Content strategy
  • Tasks that involve Social media posts

Example prompts

  • “/twitter-hand-skill”

Requirements

  • A credential in TWITTER_BEARER_TOKEN

Workflow steps

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

  1. Post first tweet → get tweet_id
  2. Post second tweet with reply.in_reply_to_tweet_id = first tweet_id
  3. Repeat for each tweet in thread

What it can do on your machine

Read from SKILL.md and the folder at commit acf2587. 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

    Shell commands in SKILL.md call:

    • curl

    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.twitter.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • TWITTER_BEARER_TOKEN

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

Context cost

Twitter Hand Skill loads about 2.9k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 959 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 RightNow-AI/openfang at commit acf2587, republished under its Apache-2.0 licence (© RightNow-AI). 959 words, ~2,939 tokens.

Download SKILL.mdSave it as .claude/skills/twitter-hand-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
twitter-hand-skill
description
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking
version
1.0.0
runtime
prompt_only

Twitter/X Management Expert Knowledge

Twitter API v2 Reference

Authentication

Twitter API v2 uses OAuth 2.0 Bearer Token for app-level access and OAuth 1.0a for user-level actions.

Bearer Token (read-only access + tweet creation):

Authorization: Bearer $TWITTER_BEARER_TOKEN

Environment variable: TWITTER_BEARER_TOKEN

Core Endpoints

Get authenticated user info:

bash
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  "https://api.twitter.com/2/users/me"

Response: {"data": {"id": "123", "name": "User", "username": "user"}}

Post a tweet:

bash
curl -s -X POST "https://api.twitter.com/2/tweets" \
  -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello world!"}'

Response: {"data": {"id": "tweet_id", "text": "Hello world!"}}

Post a reply:

bash
curl -s -X POST "https://api.twitter.com/2/tweets" \
  -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Great point!", "reply": {"in_reply_to_tweet_id": "PARENT_TWEET_ID"}}'

Post a thread (chain of replies to yourself):

  1. Post first tweet → get tweet_id
  2. Post second tweet with reply.in_reply_to_tweet_id = first tweet_id
  3. Repeat for each tweet in thread

Delete a tweet:

bash
curl -s -X DELETE "https://api.twitter.com/2/tweets/TWEET_ID" \
  -H "Authorization: Bearer $TWITTER_BEARER_TOKEN"

Like a tweet:

bash
curl -s -X POST "https://api.twitter.com/2/users/USER_ID/likes" \
  -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"tweet_id": "TARGET_TWEET_ID"}'

Get mentions:

bash
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  "https://api.twitter.com/2/users/USER_ID/mentions?max_results=10&tweet.fields=public_metrics,created_at,author_id"

Search recent tweets:

bash
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  "https://api.twitter.com/2/tweets/search/recent?query=QUERY&max_results=10&tweet.fields=public_metrics"

Get tweet metrics:

bash
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
  "https://api.twitter.com/2/tweets?ids=ID1,ID2,ID3&tweet.fields=public_metrics"

Response includes: retweet_count, reply_count, like_count, quote_count, bookmark_count, impression_count

Rate Limits
EndpointLimitWindow
POST /tweets300 tweets3 hours
DELETE /tweets50 deletes15 minutes
POST /likes50 likes15 minutes
GET /mentions180 requests15 minutes
GET /search/recent180 requests15 minutes

Always check response headers:

  • x-rate-limit-limit: Total requests allowed
  • x-rate-limit-remaining: Requests remaining
  • x-rate-limit-reset: Unix timestamp when limit resets

Content Strategy Framework

Content Pillars

Define 3-5 core topics ("pillars") that all content revolves around:

Example for a tech founder:
  Pillar 1: AI & Machine Learning (40% of content)
  Pillar 2: Startup Building (30% of content)
  Pillar 3: Engineering Culture (20% of content)
  Pillar 4: Personal Growth (10% of content)
Content Mix (7 types)
TypeFrequencyPurposeTemplate
Hot take2-3/weekEngagement"Unpopular opinion: [contrarian view]"
Thread1-2/weekAuthority"I spent X hours researching Y. Here's what I found:"
Tip/How-to2-3/weekValue"How to [solve problem] in [N] steps:"
Question1-2/weekEngagement"[Interesting question]? I'll go first:"
Curated share1-2/weekCuration"This [article/tool/repo] is a game changer for [audience]:"
Story1/weekConnection"3 years ago I [relatable experience]. Here's what happened:"
Data/Stat1/weekAuthority"[Surprising statistic]. Here's why it matters:"
Optimal Posting Times (UTC-based, adjust to audience timezone)
DayBest TimesWhy
Monday8-10 AMStart of work week, checking feeds
Tuesday10 AM, 1 PMPeak engagement day
Wednesday9 AM, 12 PMMid-week focus
Thursday10 AM, 2 PMSecond-highest engagement day
Friday9-11 AMMorning only, engagement drops PM
Saturday10 AMCasual browsing
Sunday4-6 PMPre-work-week planning

Tweet Writing Best Practices

The Hook (first line is everything)

Hooks that work:

  • Contrarian: "Most people think X. They're wrong."
  • Number: "I analyzed 500 [things]. Here's what I found:"
  • Question: "Why do 90% of [things] fail?"
  • Story: "In 2019, I almost [dramatic thing]."
  • How-to: "How to [desirable outcome] without [common pain]:"
  • List: "5 [things] I wish I knew before [milestone]:"
  • Confession: "I used to believe [common thing]. Then I learned..."
Writing Rules
  1. One idea per tweet — don't try to cover everything
  2. Front-load value — the hook must deliver or promise value
  3. Use line breaks — no wall of text, 1-2 sentences per line
  4. 280 character limit — every word must earn its place
  5. Active voice — "We shipped X" not "X was shipped by us"
  6. Specific > vague — "3x faster" not "much faster"
  7. End with a call to action — "Agree? RT" or "What would you add?"
Thread Structure
Tweet 1 (HOOK): Compelling opening that makes people click "Show this thread"
  - Must stand alone as a great tweet
  - End with "A thread:" or "Here's what I found:"

Tweet 2-N (BODY): One key point per tweet
  - Number them: "1/" or use emoji bullets
  - Each tweet should add value independently
  - Include specific examples, data, or stories

Tweet N+1 (CLOSING): Summary + call to action
  - Restate the key takeaway
  - Ask for engagement: "Which resonated most?"
  - Self-reference: "If this was useful, follow @handle for more"
Hashtag Strategy
  • 0-2 hashtags per tweet (more looks spammy)
  • Use hashtags for discovery, not decoration
  • Mix broad (#AI) and specific (#LangChain)
  • Never use hashtags in threads (except maybe tweet 1)
  • Research trending hashtags in your niche before using them

Engagement Playbook

Replying to Mentions

Rules:

  1. Respond within 2 hours during engagement_hours
  2. Add value — don't just say "thanks!" — expand on their point
  3. Ask a follow-up question — drives conversation
  4. Be genuine — match their energy and tone
  5. Never argue — if someone is hostile, ignore or block

Reply templates:

  • Agreement: "Great point! I'd also add [related insight]"
  • Question: "Interesting question. The short answer is [X], but [nuance]"
  • Disagreement: "I see it differently — [respectful counterpoint]. What's your experience?"
  • Gratitude: "Appreciate you sharing this! [Specific thing you liked about their tweet]"
Show full SKILL.md (357 more words)Show less
When NOT to Engage
  • Trolls or obviously bad-faith arguments
  • Political flame wars (unless that's your content pillar)
  • Personal attacks (block immediately)
  • Spam or bot accounts
  • Tweets that could create legal liability
Auto-Like Strategy

Like tweets from:

  1. People who regularly engage with your content (reciprocity)
  2. Influencers in your niche (visibility)
  3. Thoughtful content related to your pillars (curation signal)
  4. Replies to your tweets (encourages more replies)

Do NOT auto-like:

  • Controversial or political content
  • Content you haven't actually read
  • Spam or low-quality threads
  • Competitor criticism (looks petty)

Content Calendar Template

WEEK OF [DATE]

Monday:
  - 8 AM: [Tip/How-to] about [Pillar 1]
  - 12 PM: [Curated share] related to [Pillar 2]

Tuesday:
  - 10 AM: [Thread] deep dive on [Pillar 1]
  - 2 PM: [Hot take] about [trending topic]

Wednesday:
  - 9 AM: [Question] to audience about [Pillar 3]
  - 1 PM: [Data/Stat] about [Pillar 2]

Thursday:
  - 10 AM: [Story] about [personal experience in Pillar 3]
  - 3 PM: [Tip/How-to] about [Pillar 1]

Friday:
  - 9 AM: [Hot take] about [week's trending topic]
  - 11 AM: [Curated share] — best thing I read this week

Performance Metrics

Key Metrics
MetricWhat It MeasuresGood Benchmark
ImpressionsHow many people saw the tweetVaries by follower count
Engagement rate(likes+RTs+replies)/impressions>2% is good, >5% is great
Reply ratereplies/impressions>0.5% is good
Retweet rateRTs/impressions>1% is good
Profile visitsPeople checking your profile after tweetTrack trend
Follower growthNet new followers per periodTrack trend
Engagement Rate Formula
engagement_rate = (likes + retweets + replies + quotes) / impressions * 100

Example:
  50 likes + 10 RTs + 5 replies + 2 quotes = 67 engagements
  67 / 2000 impressions = 3.35% engagement rate
Content Performance Analysis

Track which content types and topics perform best:

| Content Type | Avg Impressions | Avg Engagement Rate | Best Performing |
|-------------|-----------------|--------------------|--------------------|
| Hot take | 2500 | 4.2% | "Unpopular opinion: ..." |
| Thread | 5000 | 3.1% | "I analyzed 500 ..." |
| Tip | 1800 | 5.5% | "How to ... in 3 steps" |

Use this data to optimize future content mix.


Brand Voice Guide

Voice Dimensions
DimensionRangeDescription
Formal ↔ Casual1-51=corporate, 5=texting a friend
Serious ↔ Humorous1-51=all business, 5=comedy account
Reserved ↔ Bold1-51=diplomatic, 5=no-filter
General ↔ Technical1-51=anyone can understand, 5=deep expert
Consistency Rules
  • Use the same voice across ALL tweets (hot takes and how-tos)
  • Develop 3-5 "signature phrases" you reuse naturally
  • If the brand voice says "casual," don't suddenly write a formal thread
  • Read tweets aloud — does it sound like the same person?

Safety & Compliance

Content Guidelines

NEVER post:

  • Discriminatory content (race, gender, religion, sexuality, disability)
  • Defamatory claims about real people or companies
  • Private or confidential information
  • Threats, harassment, or incitement to violence
  • Impersonation of other accounts
  • Misleading claims presented as fact
  • Content that violates Twitter Terms of Service
Approval Mode Queue Format
json
[
  {
    "id": "q_001",
    "content": "Tweet text here",
    "type": "hot_take",
    "pillar": "AI",
    "scheduled_for": "2025-01-15T10:00:00Z",
    "created": "2025-01-14T20:00:00Z",
    "status": "pending",
    "notes": "Based on trending discussion about LLM pricing"
  }
]

Preview file for human review:

markdown
# Tweet Queue Preview
Generated: YYYY-MM-DD

## Pending Tweets (N total)

### 1. [Hot Take] — Scheduled: Mon 10 AM
> Tweet text here

**Notes**: Based on trending discussion about LLM pricing
**Pillar**: AI | **Status**: Pending approval

---

### 2. [Thread] — Scheduled: Tue 10 AM
> Tweet 1/5: Hook text here
> Tweet 2/5: Point one
> ...

**Notes**: Deep dive on new benchmark results
**Pillar**: AI | **Status**: Pending approval
Risk Assessment

Before posting, evaluate each tweet:

  • Could this be misinterpreted? → Rephrase for clarity
  • Does this punch down? → Don't post
  • Would you be comfortable seeing this attributed to the user in a news article? → If no, don't post
  • Is this verifiably true? → If not sure, add hedging language or don't post

© RightNow-AI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in crates/openfang-hands/bundled/twitter of RightNow-AI/openfang.

  • SKILL.md
  • HAND.toml

Open the folder on GitHubat commit acf2587

Compare with similar skills

Twitter Hand Skill 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.

Twitter Hand Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Twitter Hand Skill this skillRightNow-AI/openfang18k—~2.9kAutomated safety check: PassApache-2.0
X Content Plannersergebulaev/x-skills1241 repos~1.4kAutomated safety check: PassMIT
X Algorithm Post Writingcarson2222/skills113—~3.8kAutomated safety check: PassApache-2.0
Podcast Pipelineericosiu/ai-marketing-skills3.6k1 repos~2.6kAutomated safety check: PassMIT
Social Media Managementmanojbajaj95/claude-gtm-plugin1051 repos~3.9kAutomated safety check: PassMIT
Platform Strategy Smsblacktwist/social-media-skills560—~3.8kAutomated safety check: PassMIT

Similar skills

  • X Content Planner

    sergebulaev/x-skills

    Generate a weekly X (Twitter) content plan from a theme, audience, and content pillars.

    124 GitHub starsUsed in 1 repo~1.4k tokens
    Writing & ContentAuto-check passed
  • X Algorithm Post Writing

    carson2222/skills

    Writes and reviews X posts, threads and replies using what the open-sourced For You ranking system rewards, and explains why a post may have underperformed.

    113 GitHub stars~3.8k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Podcast Pipeline

    ericosiu/ai-marketing-skills

    Podcast-to-Everything content pipeline. An agent skill from ericosiu/ai-marketing-skills.

    3.6k GitHub starsUsed in 1 repo~2.6k tokens
    Writing & ContentAuto-check passed
  • Social Media Management

    manojbajaj95/claude-gtm-plugin

    Comprehensive social media management for all platforms (LinkedIn, Twitter/X, Instagram, TikTok, Facebook, Pinterest, YouTube).

    105 GitHub starsUsed in 1 repo~3.9k tokens
    Writing & ContentAuto-check passed
  • Platform Strategy Sms

    blacktwist/social-media-skills

    When the user wants platform-specific tactical guidance for LinkedIn, Twitter/X, Threads, or Bluesky.

    560 GitHub stars~3.8k tokensUpdated 5 mo ago
    Writing & ContentAuto-check passed
  • X Writer

    stevenflanagan1/social-ai-team

    X/Twitter Content Specialist. An agent skill from stevenflanagan1/social-ai-team.

    244 GitHub stars~2.9k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

More from RightNow-AI/openfang

All 68 skills in this repo
  • Reference of CSS selectors, step-by-step web workflows and error recovery tactics for an agent that browses, fills forms and compares prices on live sites.

    18k GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed
  • Reference knowledge for open-source intelligence collection: the collection cycle, source reliability tiers, search query patterns and entity extraction.

    18k GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Lead Generation Research Guide

    RightNow-AI/openfang

    Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.

    18k GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Video Clipping Reference

    RightNow-AI/openfang

    Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.

    18k GitHub stars~4.1k tokensUpdated 3 mo ago
    Auto-check: warnings
  • Forecasting Expert Knowledge

    RightNow-AI/openfang

    Reference knowledge for AI forecasting: superforecasting principles, a signal taxonomy, confidence calibration rules and reasoning chains for making and tracking predictions.

    18k GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Deep Research Methodology

    RightNow-AI/openfang

    Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

    18k GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Twitter Hand Skill

What does Twitter Hand Skill do?

Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking. Twitter Hand Skill is an agent skill from RightNow-AI/openfang.

When should I use Twitter Hand Skill?

Twitter Hand Skill fits situations like: tasks that involve Content strategy; tasks that involve Social media posts.

How do I install Twitter Hand Skill in Claude Code?

Run `npx skills add RightNow-AI/openfang --skill twitter-hand-skill -a claude-code`. Or copy the skill folder (crates/openfang-hands/bundled/twitter in RightNow-AI/openfang) into .claude/skills/twitter-hand-skill in your project. Claude Code loads it when a task matches its description.

How do I install Twitter Hand Skill in Codex?

Run `npx skills add RightNow-AI/openfang --skill twitter-hand-skill -a codex`. Or copy the skill folder (crates/openfang-hands/bundled/twitter in RightNow-AI/openfang) into .agents/skills/twitter-hand-skill in your project. Codex loads it when a task matches its description.

Can I use Twitter Hand Skill 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 RightNow-AI/openfang --skill twitter-hand-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/twitter-hand-skill, .gemini/skills/twitter-hand-skill, .github/skills/twitter-hand-skill and .opencode/skills/twitter-hand-skill in your project.

What does Twitter Hand Skill need to run?

Going by SKILL.md and its folder, Twitter Hand Skill needs the command-line tools its instructions call (curl) and credentials named TWITTER_BEARER_TOKEN. Our summary lists: A credential in TWITTER_BEARER_TOKEN.

Does Twitter Hand Skill access the network?

SKILL.md names 1 domain. In commands or code: api.twitter.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Twitter Hand Skill 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 Twitter Hand Skill use?

Twitter Hand Skill is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Twitter Hand Skill use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Twitter Hand Skill?

Skills that share tags, products or a category with Twitter Hand Skill: X Content Planner (sergebulaev/x-skills, 124 stars), X Algorithm Post Writing (carson2222/skills, 113 stars), Podcast Pipeline (ericosiu/ai-marketing-skills, 3.6k stars) and Social Media Management (manojbajaj95/claude-gtm-plugin, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Twitter Hand Skill?

RightNow-AI (a GitHub organization) maintains it in RightNow-AI/openfang, which has 18,214 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on July 2, 2026.

Source: RightNow-AI/openfang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.