agentleFS
mykyta-lytvynenkomykyta-lytvynenko/claude-code-starter-kit/skills/content-draft/SKILL.md

content-draft

Skill0 starsChanged 7 months agoMITView on GitHub

Draft content in the user's brand voice. This is the root-level version of the skill — it reads from docs/voice-guide.md in the current project. Read Voice Guide. This is the source of truth for tone, style, audience, and what to avoid. Do not draft without reading it. If docs/voice-guide.md doesn't exist or has placeholder text, tell the user: "Fill in docs/voice-guide.md first — I need your actual brand voice to draft in your style, not a generic one." When the…

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. modimihir07/agentic-os★ 209same name
    2. microsoft/cat-agent-skills★ 101same name
    3. ZachArticulateV/designer-pro-and-seo★ 10same name
    4. alectivism/maven-template★ 1same name
    5. seco/declaw★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read Voice Guide. This is the source of truth for tone, style, audience, and what to avoid.

    line 7
  2. Very specific:

    If docs/voice-guide.md doesn't exist or has placeholder text, tell the user: "Fill in docs/voice-guide.md first — I need your actual brand …

    line 9
  3. Distinctive:

    Do not use filler affirmations ("Great question!", "Certainly!")

    line 22
  4. Distinctive:

    Do not produce an outline when a draft was requested

    line 23
  5. Distinctive:

    Do not use words from the avoid-list in voice-guide.md

    line 24
  6. Distinctive:

    Do not guess the format — if it's unclear, ask

    line 25
  7. Distinctive:

    If the user specifies a format, match it from content-types.md if available

    line 29
  8. Distinctive:

    If no format is specified and content-types.md exists, use the most common format and confirm: "I'll draft this as a [format] — is that …

    line 30
  9. Distinctive:

    If no format docs exist, write in a clean, direct format and ask them to confirm

    line 31
  10. Distinctive:

    When the user requests revisions:

    line 35
  11. Distinctive:

    Don't rewrite sections they didn't mention

    line 37
  12. Distinctive:

    If a revision request conflicts with something in voice-guide.md, flag it: "This would use [word] which is on your avoid-list — should I …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 5 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

Skill: Content Draft

Draft content in the user's brand voice. This is the root-level version of the skill — it reads from docs/voice-guide.md in the current project.

Before You Start

Read Voice Guide. This is the source of truth for tone, style, audience, and what to avoid. Do not draft without reading it.

If docs/voice-guide.md doesn't exist or has placeholder text, tell the user: "Fill in docs/voice-guide.md first — I need your actual brand voice to draft in your style, not a generic one."

Steps

  1. Read voice-guide.md — tone, audience, style, avoid-list
  2. Check for a content types doc — if docs/content-types.md exists, read the relevant format section
  3. Clarify if needed — if the brief is ambiguous, ask one focused question before drafting
  4. Write the full piece — not an outline, not a structure plan, the actual content ready to publish or lightly edit
  5. Apply the avoid-list — review before finishing; remove any words or phrases from the avoid-list
  6. Close with a check-in — "Does this match the voice? Anything to adjust?"

What NOT to Do

  • Do not use filler affirmations ("Great question!", "Certainly!")
  • Do not produce an outline when a draft was requested
  • Do not use words from the avoid-list in voice-guide.md
  • Do not guess the format — if it's unclear, ask

Format Handling

  • If the user specifies a format, match it from content-types.md if available
  • If no format is specified and content-types.md exists, use the most common format and confirm: "I'll draft this as a [format] — is that right?"
  • If no format docs exist, write in a clean, direct format and ask them to confirm

Making Edits

When the user requests revisions:

  • Apply the specific change they asked for
  • Don't rewrite sections they didn't mention
  • If a revision request conflicts with something in voice-guide.md, flag it: "This would use [word] which is on your avoid-list — should I use it anyway or find an alternative?"

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.