Content Workflow

Content Workflow

End-to-end content creation pipeline: research, draft, review, distribute.

Install

git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/content-workflow ~/.claude/skills/

Pipeline Stages

Stage 1: Research

Gather raw material for the content piece.

1. Topic research — web search, RSS feeds, industry sources 2. Source assessment — credibility, recency, relevance 3. Data extraction — key statistics, quotes, data points 4. Counter-arguments — opposing views, nuance, caveats 5. Angle development — what makes this piece unique

Output: Research brief with sources, data points, and recommended angle.

Stage 2: Draft & Edit

Create and refine the content.

1. Draft — write following the content type framework and brand voice 2. Editorial review against quality criteria:

• Voice consistency
• Structural quality (hook → body → CTA)
• SEO optimization (if applicable)
• Factual accuracy (all claims sourced)
• Readability (appropriate level for audience)

3. Revision — apply specific feedback 4. Final review — verify all issues addressed

Output: Polished draft ready for approval.

Stage 3: Distribute

Adapt the finished piece for cross-platform distribution.

1. LinkedIn post — hook, body, CTA, hashtags 2. Twitter/X thread — numbered tweets, hooks per tweet 3. Email subject lines — 3 options with preview text 4. Pull quotes — 3-5 shareable excerpts for social

Output: Distribution pack with platform-specific adaptations.

Usage Modes

Full Pipeline

/content-workflow [topic]

Runs all 3 stages: research → draft → review → distribute.

Start from Draft

/content-workflow --from-draft [file path]

Skips research. Takes an existing draft through editorial review and distribution.

Distribution Only

/content-workflow --distribute [file path]

Takes a finished, approved piece and creates the social distribution pack.

Content Types

Status Tracking

Content moves through these statuses:

stub → draft → reviewed → approved → published → measured
                                   ↘ rejected (terminal)

• stub: Topic identified, no content yet
• draft: First draft complete
• reviewed: Editorial review complete
• approved: Human approval gate passed
• published: Live on platform
• measured: Performance data collected
• rejected: Did not pass review, will not publish

Key Principles

1. Research before writing. Even short posts benefit from 10 minutes of source gathering. 2. One piece, many platforms. Write once, adapt to each platform's format. 3. Human approval gate. Never publish without explicit approval. 4. Measure everything. Track performance to inform future content decisions.

For editorial review criteria and platform templates, see REFERENCE.md.

Content Workflow — Examples

Example 1: Full Pipeline Run

Prompt:

Run the full content workflow on the topic: "Why most marketing teams waste their first 90 days with a new analytics tool."

Expected output:

Stage 1 (Research): Brief with 5-8 sources covering common analytics implementation mistakes, average time-to-value for marketing analytics tools, and expert opinions on onboarding best practices.

Stage 2 (Draft): 1,800-word blog post with:

• Hook: stat about analytics tool churn in year 1
• Body: 4-5 common mistakes with evidence
• Framework: "90-day activation plan"
• CTA: download a template

Stage 2 (Review): Editorial scorecard showing Voice: 4/5, Structure: 5/5, SEO: 4/5, Accuracy: 5/5, Readability: 4/5. One revision note: "Hook could be more specific."

Stage 3 (Distribute):

• LinkedIn post (250 words with the "90-day" angle)
• Twitter thread (8 tweets, one mistake per tweet)
• 3 email subject lines
• 4 pull quotes

---

Example 2: Review an Existing Draft

Prompt:

Review this draft LinkedIn post about Klaviyo's new AI features. [draft provided]

Expected output: Editorial review with scores:

• Voice: 3/5 — "Shifts from casual to formal in paragraph 3. Match the conversational tone of paragraphs 1-2 throughout."
• Structure: 4/5 — "Strong hook, but CTA is generic. Replace 'What do you think?' with a specific question."
• Readability: 5/5
• Decision: Revise — 2 specific edits listed

---

Example 3: Distribution Pack from Finished Article

Prompt:

Create a distribution pack for this published blog post about Google Ads wasted spend. [article provided]

Expected output:

• LinkedIn post: 220 words, opens with "Most companies are burning 30% of their Google Ads budget on irrelevant search terms." CTA asks for reactions.
• Twitter thread: 7 tweets. Hook: the 30% stat. Body: one wasted-spend category per tweet with example. Close: link to full article.
• Email subject lines:

1. "Your Google Ads account is leaking money" 2. "How to find the 30% waste in your ad budget" 3. "The search term report your agency isn't showing you"

• Pull quotes: 4 excerpts under 280 chars each, covering the key stats and recommendations.

Content Workflow — Reference

Editorial Review Criteria

Voice Consistency (Score 1-5)

Structural Quality (Score 1-5)

Structural checklist:

• [ ] Hook in first 2 sentences (not a generic intro)
• [ ] Clear thesis or promise early
• [ ] Body paragraphs each make one point
• [ ] Transitions between sections
• [ ] CTA aligned with content goal
• [ ] Appropriate length for format

SEO Quality (Score 1-5, if applicable)

• [ ] Primary keyword in title and H1
• [ ] Primary keyword in first 100 words
• [ ] Secondary keywords in H2 headings
• [ ] Meta description written (150-160 chars)
• [ ] Internal links included
• [ ] Header hierarchy logical

Factual Accuracy

• [ ] All statistics have sources
• [ ] Sources are credible and recent (<2 years)
• [ ] No unsupported claims
• [ ] Counter-arguments or caveats acknowledged
• [ ] Quotes are attributed

Readability

• [ ] Appropriate reading level for audience
• [ ] Paragraphs 2-4 sentences
• [ ] Active voice dominant (>80%)
• [ ] No jargon without explanation
• [ ] Scannable (headers, bullets, bold)

Quality Scoring Rubric

Platform Adaptation Templates

LinkedIn Post Template

[Hook — bold statement, surprising stat, or contrarian take]

[Paragraph 1 — expand on the hook with context]

[Paragraph 2 — the insight or framework]

[Paragraph 3 — practical takeaway or personal experience]

[CTA — specific question or invitation]

#hashtag1 #hashtag2 #hashtag3

Rules:

• First 2-3 lines appear before "see more" — make them count
• Use line breaks between paragraphs (LinkedIn collapses dense text)
• 3-5 hashtags, mix of broad (#marketing) and niche (#klaviyotips)
• 150-300 words optimal

Twitter/X Thread Template

Tweet 1 (Hook):
[Standalone insight that makes people want more. End with "A thread:" or similar]

Tweet 2-N (Body):
[One idea per tweet. Each should be valuable on its own if retweeted.]

Final Tweet (CTA):
[Summary + call to action. "Follow @handle for more on [topic]" or "Bookmark this thread for later."]

Rules:

• Hook tweet must work as a standalone post
• Number tweets (1/, 2/, etc.) for readability
• Each tweet: one idea, one example, or one stat
• 5-12 tweets optimal
• Quote-tweet the first tweet with a summary for engagement

Email Subject Lines

Option A (Number + Benefit): [X] Ways to [Achieve Result]
Option B (Question): Is Your [Thing] [Underperforming/Costing You]?
Option C (How-to): How to [Achieve Result] Without [Pain Point]

Preview text (40-90 chars):

[Expand on the subject line — add context or urgency]

Pull Quote Format

"[2-3 sentence excerpt that stands alone as an insight]"
— From: [Article Title]

Select quotes that:

• Contain a specific stat or bold claim
• Work without surrounding context
• Are under 280 characters (tweetable)

Follow-Up Cadence

After publishing: