agentleFS
PingPingEPingPingE/ai-content-agents/.claude/skills/write-content/SKILL.md

write-content

Skill2 starsChanged 9 months agoMITView on GitHub

Create content with automatic review pipeline

5 other projects use a version of this.

Adopted by

Most recently taken up by

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 4 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:

    Create the following content:

    line 19
  2. Distinctive:

    Check existing content for style reference

    line 26
  3. Distinctive:

    Write the content following project guidelines

    line 27
  4. Distinctive:

    After writing, delegate to content-reviewer for quality review

    line 28
  5. Distinctive:

    If reviewer says REVISE, make changes and re-submit (max 2 rounds)

    line 29
  6. Distinctive:

    Create an outline with:

    line 41
  7. Distinctive:

    After you finish writing:

    line 58
  8. Distinctive:

    Before submitting for review, verify:

    line 88

“Common” is measured: kept by at least 6 in 10 of the 4 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

Write Content

Create the following content:

Brief: $ARGUMENTS

Instructions

  1. Research the topic if needed
  2. Check existing content for style reference
  3. Write the content following project guidelines
  4. After writing, delegate to content-reviewer for quality review
  5. If reviewer says REVISE, make changes and re-submit (max 2 rounds)

Research Phase

Before writing:

  • Check existing content — read 2-3 similar pieces to understand tone and style
  • Identify gaps — what's missing from current content?
  • Gather sources — find 3-5 credible sources for facts and statistics
  • Verify currency — ensure sources are recent (prefer last 2 years)

Outline Requirements

Create an outline with:

  • Thesis/main point — what's the one key takeaway?
  • Supporting points — 3-5 major sections with subsections
  • Conclusion — summary + clear next steps or call-to-action
  • Estimated word count — based on brief complexity

Draft Quality Standards

Your draft must be:

  • Original — no copy-paste, rewrite everything in your own words
  • Cited — link to sources for all statistics, quotes, and factual claims
  • Structured — clear headings, short paragraphs, scannable format
  • Complete — cover all points in the brief
  • On-brand — match project tone and style

Auto-Review Pipeline

After you finish writing:

  1. Spawn content-reviewer to review your work
  2. If REVISE: fix the issues and re-submit to reviewer (max 2 rounds)
  3. If APPROVE: report completion with metadata
  4. If REJECT: escalate to human review with reviewer's feedback

Maximum 2 revision rounds — if still REVISE after 2 rounds, escalate to human.

Output Format

Provide the completed content with metadata:

# [Title]

[Content here]

---

## Metadata
- **Word count:** [number]
- **Reading time:** [X minutes at 250 words/min]
- **Primary keyword:** [keyword]
- **Target audience:** [description]
- **Review status:** [APPROVED/REVISE/REJECT]
- **Revision count:** [0-2]

Quality Checklist

Before submitting for review, verify:

  • Followed project tone and style
  • All facts cited with sources
  • Headings descriptive and scannable
  • Paragraphs 3-4 sentences max
  • No weasel words or filler phrases
  • Clear call-to-action or next steps
  • Reading level appropriate (Flesch-Kincaid 8-10)

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.