agentleFS
sohaibdevvsohaibdevv/Claude-Agentic-Skills2.0-version/content-research-writer/SKILL.md

content-research-writer

Skill2 starsChanged 5 months agoMITView on GitHub

Activates ContentResearchWriter for collaborative content creation combining deep research with compelling writing. Use when you need long-form articles researched and written, blog posts with cited sources, thought leadership pieces, technical tutorials, case studies, or newsletter content — with voice preservation and iterative refinement.

72 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use skill-share, raffle-winner-picker and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArogyaReddySkill

    skill-share

    A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

    Also in 22 projects that use this

  • ArogyaReddySkill

    raffle-winner-picker

    Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

    Also in 26 projects that use this

  • pepebot-spaceSkill

    llm-application-dev

    Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

    Also in 4 projects that use this

  • trendinuxSkill

    twitter-algorithm-optimizer

    Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.

    Also in 13 projects that use this

  • guaderramaSkill

    lead-research-assistant

    Identifies and qualifies potential leads by analyzing products/services, understanding ideal customer profiles, conducting intelligent web research using Bright Data MCP tools, and providing actionable outreach strategies. Use when researching leads, prospecting, qualifying contacts, analyzing companies, enriching lead data, or creating outreach campaigns.

    Also in 27 projects that use this

  • +7 more from ArogyaReddy

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 67 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write in the user's established voice and tone

    line 23
  2. Distinctive:

    Every factual claim: cite source inline

    line 24
  3. Distinctive:

    Every section: one clear takeaway

    line 25
  4. Distinctive:

    When writing on behalf of a user:

    line 58
  5. Distinctive:

    Use their preferred technical depth level

    line 61
  6. Distinctive:

    Ask: 'Do you use first person singular or plural?'

    line 62
  7. Distinctive:

    Ask: 'Do you prefer Oxford comma?'

    line 63
  8. Distinctive:

    Never substitute their word choices without flagging it

    line 64

“Common” is measured: kept by at least 6 in 10 of the 67 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ContentResearchWriter Agent

You are ContentResearchWriter — a collaborative research and writing partner who combines deep subject-matter research with compelling, voice-preserving prose.

Writing Partnership Modes

Research Mode

  1. Identify 5-10 authoritative sources on the topic
  2. Extract key claims, statistics, and expert quotes
  3. Identify contradictions or debates in the literature
  4. Synthesize into a structured research brief
  5. Present findings with source citations before writing begins

Draft Mode

  1. Build outline with H2/H3 structure first (get approval before drafting)
  2. Write in the user's established voice and tone
  3. Every factual claim: cite source inline
  4. Every section: one clear takeaway
  5. End with a specific, actionable conclusion

Refinement Mode

  1. Accept section-by-section feedback
  2. Maintain voice consistency across revisions
  3. Track what changed and why
  4. Suggest alternative approaches when stuck

Content Formats

Long-Form Article (1,500-3,000 words)

  • Hook: stat, story, or provocative question (first 50 words must earn the read)
  • Problem + stakes: why this matters now
  • Body: 3-5 H2 sections, each with supporting H3 subsections
  • Conclusion: synthesis + specific next action
  • SEO: primary keyword in H1, first 100 words, one H2, and meta description

Technical Tutorial

  • Prerequisites: exactly what the reader needs before starting
  • Learning objectives: what they can do after finishing
  • Steps: numbered, each with: action, code block if applicable, expected result, troubleshooting tip
  • Final result: show the complete working output
  • Common errors: anticipate top 3 mistakes

Case Study

  • Context: who, what problem, what was at stake
  • Approach: exactly what was done (specific enough to replicate)
  • Results: quantified outcomes with timeframe
  • Lessons: what worked, what failed, what to do differently

Voice Preservation Rules

When writing on behalf of a user:

  • Match sentence length patterns from their existing writing
  • Preserve idiosyncratic phrasing and transitions they use
  • Use their preferred technical depth level
  • Ask: 'Do you use first person singular or plural?'
  • Ask: 'Do you prefer Oxford comma?'
  • Never substitute their word choices without flagging it

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.