Executes an automated pipeline that turns social media requests into GitHub PRs.

Install

mkdir -p .claude/skills/monitor-tweet && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14576" && unzip -o skill.zip -d .claude/skills/monitor-tweet && rm skill.zip

Installs to .claude/skills/monitor-tweet

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run the tweet-to-toolkit pipeline on a tweet. Flow: (1) triage+feasibility, (2) ALWAYS show findings and BOTH repo options to user, (3) user approves target + direction, (4) build auto-starts, (5) review auto-starts, (6) if APPROVED, gh pr create auto-runs. The ONLY human gate is step 2 — everything after approval is automatic. Usage: /monitor-tweet <tweet-text> [--dry-run]
376 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Triage tweet requests for relevance and feasibility
  • Audit target repositories for existing overlap
  • Present feasibility findings and repository options to the user
  • Trigger builder agent for architecture analysis and implementation
  • Trigger reviewer agent for QA and regression checks
  • Create GitHub pull requests automatically

How it works

This skill processes a tweet by first triaging its relevance and feasibility, then presenting findings and repository options for human approval. Once approved, it automatically spawns builder and reviewer agents to implement and verify the feature, finally creating a GitHub pull request.

Inputs & outputs

You give it
A tweet text describing a feature request
You get back
A GitHub pull request with the implemented feature or a report on why it was blocked

When to use monitor-tweet

  • Turning feature-request tweets into code
  • Automating repo audits
  • Prototyping based on social feedback

About monitor-tweet

Triage tweet requests, audits relevant repositories for feasibility, and automatically triggers build and review agents once human approval is granted.

Run the tweet-to-toolkit pipeline on a tweet. Flow: (1) triage+feasibility, (2) ALWAYS show findings and BOTH repo options to user, (3) user approves target + direction, (4) build auto-starts, (5) review auto-starts, (6) if APPROVED, gh pr create auto-runs. The ONLY human gate is step 2 — everything

When not to use it

  • When the tweet is not relevant to the project
  • When the feature described in the tweet is infeasible
  • When the feature already exists in the codebase

Limitations

  • Requires explicit human approval before building
  • Relies on sub-agents for building and reviewing
  • Pipeline stops if triage finds the tweet irrelevant or infeasible

How it compares

This workflow automates the entire process from a tweet idea to a pull request, with a single human approval gate, significantly accelerating development compared to manual triage, implementation, and PR creation.

Compared to similar skills

monitor-tweet side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
monitor-tweet (this skill)04moReviewAdvanced
skillshare12moReviewIntermediate
subtask36moReviewAdvanced
agentic-jujutsu34moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

skillshare

runkids

Syncs skills across AI CLI tools (Claude, Cursor, Windsurf, etc.) from a single source of truth. Use when: "sync skills", "install skill", "search skills", "list skills", "show skill status", "backup skills", "restore skills", "update skills", "new skill", "collect skills", "push/pull skills", "add/remove target", "find a skill for X", "is there a skill that can...", "how do I do X with skills", "skillshare init", "skillshare upgrade", "skill not syncing", "diagnose skillshare", "doctor", or any skill/target management across AI tools.

116

subtask

zippoxer

Parallel task orchestration CLI that dispatches work to AI workers (via Claude Code) in isolated git workspaces. Use when the user wants to draft, create, run, or manage tasks, delegate tasks to workers/subagents, or mentions subtask or Subtask.

31

agentic-jujutsu

ruvnet

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

328

moai

modu-ai

MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.

14

build-with-agent-team

coleam00

Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.

13

swarm-coordination

joelhooks

Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.

04

Search skills

Search the agent skills registry