lennoxsaint/Threadify-workflows / plugins/claude/skills/threadify-run-my-threads
threadify-run-my-threads
VerifiedSet up one daily schedule so your agent prepares five Threadify-written Threads posts every morning from a weekly plan (one long-form thread on six days, one greatest-hit repost a day, hook-first structures and a chosen CTA level), shows them in this thread, and schedules them only after you reply "yes". Use when someone asks Threadify to run their Threads, prepare posts every morning for approval, or says "I want to approve posts, not write them".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 21.0 KB |
| references/daily-schedule.md | markdown | 6.0 KB |
| references/generation-models.json | config | 932 B |
| references/hook-bank.md | markdown | 976 B |
| references/state-and-recovery.md | markdown | 3.5 KB |
| references/threadify-001.md | markdown | 3.7 KB |
| references/threads-playbook.md | markdown | 2.7 KB |
| references/workflow-manifest.json | config | 4.4 KB |
| references/workflow-readme.md | markdown | 1.0 KB |
| scripts/casing-guard.mjs | script | 6.6 KB |
| scripts/hook-check.mjs | script | 7.2 KB |
| scripts/run-state.mjs | script | 9.5 KB |
| scripts/week-plan.mjs | script | 14.2 KB |
references/threads-playbook.md
View on GitHub# Threads generation playbook
These are generation instructions. Do not run editorial audits or automatic rewrite loops after generation. Use the owner's voice, casing choice and approved destination.
## Hook
Short-form: exactly one curiosity-opening sentence, then directly into the body. Allude to something the body answers. One-liners may stand alone without a forced explanation. Use a number only if it really happened.
## Hold
Pay off the opening curiosity with concrete, grounded information. Remove filler hedging without hiding uncertainty. Use specific stakes and a clear sequence rather than repeated proof.
## Help
Give a specific usable payoff. Hook/hold/help and proof/promise/plan apply where grounded; never invent proof to complete a formula.
## CTA
Place a relevant CTA after value, using the owner's approved destination. The RSS test: is it relevant, specific and a sensible next step? Respect an explicit workflow-specific clean link over broader attribution instructions. Do not add tracking parameters without approval or change account settings.
## Structures
Read an actual successful source post in full, extract its mechanics, and adapt those mechanics to the creator's facts. The Rule of Two for long-form means two open loops, both resolved by the body. Assign a distinct angle, hook mechanism and evidence before generating each slot. Generic examples are not proof of performance.
## Short-form types
Listicles go directly from the one-sentence hook into the numbered list. No analogy, setup paragraph, second intro or “here are the five” transition. Other short posts go straight into the body. A standalone one-liner needs no appended explanation.
## Long-form
The opening post is exactly three sentences. Sentence one is short and opens a story or curiosity loop. Sentence two supplies stakes or context without resolving it. Sentence three opens the deliverable loop, promises a specific reason to reveal the next post, and ends with a colon. The body resolves both loops.
Choose a genuinely new subject or refresh an existing published thread with verified current facts and preserved provenance. Never invent updated metrics. When revising an existing thread, aim for approximately 30% shorter body parts against the recorded original. For a new thread, aim for 22–48 words per body part; do not claim an unmeasured reduction.
## Generation input
Include: owner voice; assigned topic and unique angle; actual source template and relevant adaptation; assigned proof and its source; planned content type; the hook format above; specific payoff; approved CTA destination after value; strict facts; and unique attempt marker. Read current brand doctrine when available. Retain the original response unchanged except for chosen casing or an explicit owner edit.
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |