Systems Lab

Agent skill

content-workflow

End-to-end content creation pipeline from research through editorial review to social distribution.

slowingSelf-containedActs undeclared495 words

Filed under Content and SEO.

From thatrebeccarae/claude-marketing · 42 skills · 119 · pushed 2026-05-14

What it does when it runs

End-to-end content creation pipeline from research through editorial review to social distribution. Orchestrates a 3-stage workflow: research, draft/edit, and distribute. Supports blog posts, LinkedIn, Twitter threads, newsletters, and essays.

Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about content-workflow

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/thatrebeccarae/claude-marketing.git /tmp/claude-marketing
git -C /tmp/claude-marketing sparse-checkout set "skills/content-workflow"
mkdir -p ~/.claude/skills/content-workflow
cp -R "/tmp/claude-marketing/skills/content-workflow/." ~/.claude/skills/content-workflow/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from thatrebeccarae/claude-marketing/blob/a8a63ec1341f05ec9c1e9cb52b4edeb14e3bdcba/skills/content-workflow/SKILL.md, which is licensed MIT (skill frontmatter). 495 words, 13 headings.

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

TypeResearch DepthDraft LengthDistribution
Blog postDeep (5+ sources)1,500-2,500 wordsLinkedIn + Twitter + Email
LinkedIn postLight (2-3 sources)150-300 wordsTwitter adaptation only
Twitter threadLight (1-2 sources)5-12 tweetsLinkedIn adaptation only
NewsletterMedium (3-5 sources)500-1,000 wordsTwitter + LinkedIn teasers
EssayDeep (8+ sources)2,000-4,000 wordsFull distribution pack

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.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what content-workflow does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.