lennoxsaint/Threadify-workflows / plugins/claude/skills/threadify-first-followers
threadify-first-followers
VerifiedGet your first Threads followers from zero, one person at a time. Find 10 newcomers and small active creators in your niche, then your agent stages each comment in the Threads reply box and follows at the right step while you just press Post. Comments are written in your voice from your Threadify Brain, your edits are compared with what was staged so the agent learns your voice, and the progress is tracked on a local scoreboard. Works with no post history, in any agent, with copy mode when there is no browser control. Use when someone has few or zero followers, a brand-new Threads account, or asks how to get their first followers.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.5 KB |
| references/generation-models.json | config | 753 B |
| references/posts.md | markdown | 3.0 KB |
| references/schedule.md | markdown | 2.4 KB |
| references/threadify-001.md | markdown | 3.7 KB |
| references/workflow-manifest.json | config | 5.9 KB |
| references/workflow-readme.md | markdown | 2.4 KB |
| scripts/casing-guard.mjs | script | 7.1 KB |
| scripts/first-followers.mjs | script | 27.5 KB |
references/schedule.md
View on GitHub# First Followers on a schedule
Asked once at the end of a run: "Want me to run this for you on a schedule?" Create a schedule only after the owner says yes and picks the days and time. Never create one silently, never create a second one, and never add an hourly or repeating check.
## What a scheduled run does
A scheduled run starts the workflow and stops at the batch approval: it checks the account, finds up to 10 people, drafts and checks the comments, and shows the list. Nothing is staged or followed until the owner replies "yes" in that run, and the owner still presses Post on every comment. The schedule's own prompt is never approval.
Staged mode needs the browser that is signed in to Threads on the owner's computer, so prefer a scheduler that runs on this computer while it is awake. A cloud run cannot see that browser; it can only run copy mode.
## Find before you create
List the host's existing schedules first and look for one named "First Followers" or whose prompt runs `threadify-first-followers`. One found: reuse it and change its time in place only when the owner asks. More than one: show them and ask which to keep. None: create one, then read it back.
## The prompt
> Run the installed threadify-first-followers skill. Account: @HANDLE. Timezone: AREA/CITY. People: 10. Read the installed SKILL.md on each run. Stop at the batch approval and wait for my "yes" in this conversation; never stage, follow or post without it.
## Create it with the host's own scheduler
- **Claude Desktop / Claude Code:** a local scheduled task (Desktop: Routines, New routine, Local, at the chosen time), so it can reach this computer's browser. A cloud routine (`/schedule` or claude.ai/code/routines) runs copy mode only. Do not use `/loop`; it needs an open session and expires.
- **ChatGPT:** a scheduled task in ChatGPT at the chosen time.
- **Codex:** an automation from Codex's own automation controls (ask in this thread, or the Automations view), preferably attached to this thread. Do not hand-write Codex state files.
- **Other hosts:** the host's one native scheduler (Cursor Automations, Gemini CLI, OpenClaw or Hermes cron).
- **Last resort:** an OS schedule (cron or launchd) that runs the agent's non-interactive command. Show the exact command, time and timezone and get the owner's consent before registering it.
Read back the name, days, time, timezone, next run and how to pause it. If the host has no scheduler, say so and offer to run it whenever the owner asks.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |