Turn Claude Into a Repeatable Content Writing System in 11 Steps
nikola_mr64990 · x · 2026-11-10
An 11-step workflow that turns Claude from a scratch-every-time tool into a writing system that learns your voice:
- Enable Memory: store persona/audience in User Preferences; update weekly — stale memory = stale voice.
- Create a Project: one per content series, with tone guides and top posts as standing context.
- Build a prompt library: style notes as PDF/text; have Claude check it before every draft; include good AND bad examples.
- Upload a style guide so output uses your voice, not generic AI voice.
- Toggle Extended Thinking only for strategy/brief work, skip for captions.
- Critique before writing: fix weak angles and vague framing in the brief first — order matters.
- RTCO structure: Role (content strategist) + Task (5 viral hooks) + Context (audience) + Output (3 options, critique the best).
- Output via Artifacts for carousels, posts, checklists — batch-friendly.
- Repurpose top posts into 3 format variants with audience pain points baked in.
- Run a friction check: ask what patterns Claude noticed in your feedback; write insights back to memory.
- Pre-publish review: a saved prompt scoring hook, value, and CTA separately.
The goal: a repeatable content system that compounds over time.
More from coding & agent
- Local Qwen judges stream clips for free: a zero-token auto-clipping pipeline — TangeloOk9486 · 2026-11-10
- Ex-Meta engineer: AI usage generates a fragile codebase blind to issues beyond its context window — vboykis · 2026-11-10
- Matt Pocock shows 'decision ticket' board to align teams on AI coding before implementation — mattpocockuk · 2026-11-10
- Hands-on: Tencent's Hy4 matches or beats rivals across five agentic coding tests — CodeByPoonam · 2026-11-10
- How would you test whether an AI assistant's interruption is actually justified? — AlexWorkGuru · 2026-11-10
- One folder, 39 agents, 8 departments: what a 2026 data science team looks like — mdancho84 · 2026-11-10