AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Journalism Writing

A craft rubric for writing and reviewing news, explainers, and issue analyses using the inverted pyramid, Toulmin argument, dialectical structure, and BBC due impartiality.

Content & WritingIntermediate★ 173⑂ 27AI score 8/10Last updated: Oct 13, 2026

What it does

Turns newsroom and argumentation craft into concrete rules Claude applies both when drafting and when reviewing.

  • Opening: Lede (concrete conclusion, 2–4 sentences) → Nut graph (why it matters, 4W1H) → Kicker (forward-looking tension)
  • Structure: inverted pyramid (conclusion first, background later), PAGE framing (Problem · Analyze cause · Gauge responsibility · Examine solutions), Vox-style explainer units answering How/Why
  • Handling debates: Hegelian thesis–antithesis–synthesis with explicit Position A / Position B / C — Mediation labels, and a rule that C may not run longer than A or B
  • Argument quality: Toulmin model (claim · grounds · warrant · qualifier · rebuttal) to catch ungrounded assertions, over-generalization, and sides left perfectly defended
  • Fairness: BBC due impartiality — proportionate to weight rather than a mechanical 50:50, with a reference-ratio ceiling as a signal

Every criterion ships with ✅ good / ❌ bad examples, so judgments aren't vague.

Who it's for

  • Newsletter writers, tech bloggers, and industry-report authors
  • Researchers and analysts who must present contested topics without tipping the scale
  • Anyone who wants a systematic edit pass when an AI draft has a flat opening or thin reasoning
  • Teams producing wiki-style documents that need editorial consistency

Examples

  1. Fix the opening — "Rewrite this intro as Lede → Nut graph → Kicker; the lede needs specific numbers and must fit in 2–4 sentences."
  2. Review an issue analysis — "Restructure this regulation piece into Position A / Position B / C — Mediation, and give each side one self-admitted weakness as a rebuttal."
  3. Bias check — "Audit citation and length balance against BBC due impartiality, and make the monitoring points for both sides symmetric."

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alfadur7/llm-wiki-newsroom/HEAD/.claude/skills/journalism-writing/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the .claude/skills/journalism-writing folder from the GitHub repo alfadur7/llm-wiki-newsroom into my ~/.claude/skills/journalism-writing/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alfadur7/llm-wiki-newsroom.git && mkdir -p ~/.claude/skills && cp -r llm-wiki-newsroom/.claude/skills/journalism-writing ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (macOS Terminal, or WSL/Git Bash on Windows).
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Clone the repository: git clone https://github.com/alfadur7/llm-wiki-newsroom.git
  4. Copy the skill folder: cp -r llm-wiki-newsroom/.claude/skills/journalism-writing ~/.claude/skills/
  5. (Recommended) The skill references criteria.json and the repo's .claude/layers/ content-type guides. For the full deterministic checks, open the whole repository as your project.
  6. Restart Claude Code, then run /skills or ask something like "rewrite this intro as lede → nut graph → kicker" to confirm it loads.
View source on GitHub ↗License: MIT