article-strategy

Turn a raw idea into a structured article brief — defines audience, angle, core argument, competitive gap, and voice. Use before writing an outline or draft. The output of this skill is a brief that feeds directly into article-writing.

8 stars

Best use case

article-strategy is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Turn a raw idea into a structured article brief — defines audience, angle, core argument, competitive gap, and voice. Use before writing an outline or draft. The output of this skill is a brief that feeds directly into article-writing.

Teams using article-strategy should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/article-strategy/SKILL.md --create-dirs "https://raw.githubusercontent.com/marvinrichter/clarc/main/skills/article-strategy/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/article-strategy/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How article-strategy Compares

Feature / Agentarticle-strategyStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Turn a raw idea into a structured article brief — defines audience, angle, core argument, competitive gap, and voice. Use before writing an outline or draft. The output of this skill is a brief that feeds directly into article-writing.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Article Strategy

Turn a raw topic, note dump, or vague idea into a sharp brief before writing begins. Good briefs prevent rewrites.

## When to Activate

- user has a topic but hasn't defined the audience or angle yet
- user wants to write a blog post, essay, or guide but isn't sure what the core argument is
- user wants to avoid writing something that already exists (competitive gap check)
- turning internal notes, a talk, or a conversation into a publishable article

## First Questions (always ask — do not skip)

Collect these before producing the brief. If the user has already answered some in their message, do not re-ask:

1. **Audience** — Who reads this? (role, experience level, what they care about)
2. **Platform** — Where will it be published? (personal blog, company blog, dev.to, Substack, LinkedIn, HN)
3. **Voice** — Should it match a specific voice? If yes, ask for 1–3 examples (published articles, posts, memos)
4. **Goal** — What should the reader do or think differently after reading?
5. **Source material** — Are there notes, transcripts, research, or prior drafts to draw from?

If the user says they have no voice preference, default to: direct, operator-style — concrete, practical, no hype.

## Brief Structure

Produce the brief in this exact format:

```markdown
## Article Brief

**Working title:** [Specific, not generic. Should signal the angle, not just the topic]
**Audience:** [Role + experience level + what they already know]
**Platform:** [Where it will be published — affects tone, length, formatting norms]
**Goal:** [One sentence: what the reader thinks or does differently after reading]
**Core argument:** [One declarative sentence. Not a question. Not "this article explores..."]
**Competitive gap:** [What existing articles on this topic get wrong, skip, or miss — why this one is worth reading]
**Voice:** [2–3 adjectives + one example sentence in that voice]
**Suggested length:** [Word count range based on platform and depth]
**Source material:** [File paths or "none"]
```

## Angle Selection

If the user hasn't landed on a specific angle, offer 3 options with a recommendation:

| Option | Angle | Core argument | Best for |
|---|---|---|---|
| A | [e.g., Tutorial] | [One sentence] | [Audience segment] |
| B | [e.g., Opinion] | [One sentence] | [Audience segment] |
| C | [e.g., Case study] | [One sentence] | [Audience segment] |

Recommend one and explain why in one sentence.

## Competitive Gap Analysis

Before finalizing the brief, identify what makes this article worth reading:

- What's the most common framing of this topic? (so we can differentiate)
- What do existing articles assume that isn't true for this audience?
- What's the insight or evidence that others don't have?

If the user doesn't know, ask: "What do you know about this topic that most articles don't cover?"

## Working Title Formula

Strong working titles follow one of these patterns:

- **The Reversal**: "Why [common belief] is wrong — and what to do instead"
- **The Concrete Promise**: "How we [specific outcome] in [timeframe]"
- **The Counterintuitive Fact**: "[Surprising number or observation] about [topic]"
- **The Named Problem**: "The [specific failure mode] trap — and how to avoid it"

Avoid: "A guide to...", "Everything you need to know about...", "Introduction to..."

## Voice Capture (if examples provided)

Extract from the provided examples:

- sentence length and rhythm (short/punchy vs. long/layered)
- formal / conversational / sharp
- favored devices: parentheses, fragments, lists, rhetorical questions, em-dashes
- tolerance for humor, strong opinion, contrarian framing
- formatting habits: headers, bullets, code blocks, pull quotes

Produce one example sentence in the captured voice to confirm with the user.

## Output

After collecting answers to the First Questions, produce:
1. The completed brief
2. (If angle not fixed) Three angle options with a recommendation
3. A confirmation question: "Does this brief match what you had in mind, or should we adjust the angle/audience?"

Do not proceed to outlining until the user confirms the brief.

Related Skills

pricing-strategy

8
from marvinrichter/clarc

SaaS pricing strategy patterns: value metric selection, usage-based vs. seat-based vs. flat-rate models, freemium conversion, pricing page design, packaging tiers, and the analytics to improve pricing. For product and technical founders.

article-writing

8
from marvinrichter/clarc

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

zero-trust-patterns

8
from marvinrichter/clarc

Zero-Trust security patterns — mTLS between microservices (Istio/SPIFFE), SPIRE workload identity, OPA/Envoy authorization, NetworkPolicy default-deny-all, short-lived credentials, service mesh security, and Kubernetes RBAC hardening.

wireframing

8
from marvinrichter/clarc

Wireframing and prototyping workflow: fidelity levels (lo-fi sketch → mid-fi wireframe → hi-fi prototype), tool selection (Figma, Excalidraw, Balsamiq), user flow diagrams, wireframe annotation standards, information architecture (IA) mapping, and the handoff from wireframe to visual design. For developers who need to communicate UI structure before writing code.

webrtc-patterns

8
from marvinrichter/clarc

WebRTC patterns — peer connection setup, ICE/STUN/TURN configuration, signaling server design, SFU vs mesh topology, screen sharing, media track management, and reconnect/ICE restart handling.

webhook-patterns

8
from marvinrichter/clarc

Webhook patterns for receiving, verifying (HMAC), and idempotently processing third-party events. Covers Stripe, GitHub, and generic webhook patterns, delivery guarantees, retry handling, and testing.

web-performance

8
from marvinrichter/clarc

Web performance optimization: Core Web Vitals (LCP, CLS, INP), Lighthouse CI with budget configuration, bundle analysis (webpack-bundle-analyzer, vite-bundle-visualizer), hydration performance, network waterfall reading, image optimization (WebP/AVIF, srcset), and font performance.

wasm-performance

8
from marvinrichter/clarc

WebAssembly performance: wasm-opt binary optimization, size reduction (panic=abort, LTO, strip), profiling WASM in Chrome DevTools, memory management (linear memory, avoiding GC pressure), SIMD, and multi-threading with SharedArrayBuffer.

wasm-patterns

8
from marvinrichter/clarc

WebAssembly patterns: wasm-pack, wasm-bindgen (JS↔Wasm interop), WASI, Component Model, wasm-opt, Rust-to-WASM compilation, JS integration (web workers, streaming instantiation), and production deployment (CDN, Content-Type headers).

visual-testing

8
from marvinrichter/clarc

Visual Regression Testing: tool comparison (Chromatic/Percy/Playwright screenshots/BackstopJS), pixel-diff vs AI-based comparison, baseline management, flakiness strategies (masks, tolerances, waitForLoadState), CI integration with GitHub Actions, and Storybook integration.

visual-identity

8
from marvinrichter/clarc

Brand identity development: color palette construction (primary/secondary/semantic/neutral), logo concept brief writing, typeface pairings, brand voice definition, mood board direction, and Brand Guidelines document structure. Use when establishing or evolving a visual brand — not for implementing existing tokens.

ux-micro-patterns

8
from marvinrichter/clarc

UX micro-patterns for every product state: Empty States, Loading States (skeleton screens, spinners, optimistic UI), Error States, Success States, Confirmation Dialogs, Onboarding Flows, and Progressive Disclosure. These patterns apply to every feature — done wrong, they're the biggest source of user confusion.