agentleFS
khadir-syedkhadir-syed/k_ai-agent-skills/skills/content/content-draft-assistant/SKILL.md

content-draft-assistant

Skill19 starsChanged 50 days agoMITView on GitHub

Draft one piece or section of content (a blog intro, a social caption, an email section) from notes or a confirmed brief, and write it to a file only with explicit approval. Use when the brief is already reasonably clear; do not use on a vague brief — run the Content Brief Gap Investigator first.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    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:

    If the source material is vague or contains conflicting signals, say so and recommend the Content Brief Gap Investigator instead of …

    line 14
  2. Distinctive:

    Never treat access to write a file as permission to write it.

    line 15
  3. Distinctive:

    If the source material leaves something un-fillable (e.g.

    line 23
  4. Distinctive:

    Use the shape implied by the brief — see references/content-section-format.md — such as a headline, intro, body sections, and a call to …

    line 27
  5. Distinctive:

    Keep claims concrete and checkable — prefer "cuts setup time from 20 minutes to under 2" over "makes setup faster," when the source …

    line 29
  6. Distinctive:

    Default: one-time approval.

    line 37
  7. Distinctive:

    Never infer standing approval from a single approval of one piece.

    line 39
  8. Distinctive:

    Write the approved content to the named file, in the right place if the file already has other sections.

    line 43
  9. Distinctive:

    Stop and ask rather than guessing when:

    line 47
  10. Distinctive:

    Before writing, confirm that:

    line 56
  11. Distinctive:

    every drafted statement traces back to the supplied source material.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Content Draft Assistant

Draft one piece of content (or a single section of one) from material the user supplies, show it before writing, and write only with the user's approval.

Operating boundary

  • Touch only the single content file named or clearly implied by the user (e.g. blog-post.md, a specific caption file, or a named section within one). Do not edit unrelated files.
  • Base every drafted sentence on the supplied notes, brief, or brand guide. Do not invent claims, statistics, quotes, or scope not present in the source material.
  • If the source material is vague or contains conflicting signals, say so and recommend the Content Brief Gap Investigator instead of drafting around the ambiguity.
  • Never treat access to write a file as permission to write it. Always get approval first (see below).

Workflow

1. Gather the source material

Identify what you're drafting from: a brief, a set of notes, a brand/style guide, or a prior gap-investigation report. State which one you used.

If the source material leaves something un-fillable (e.g. no call to action was ever stated), say so explicitly in the draft rather than inventing a plausible-sounding one.

2. Draft the piece or section

Use the shape implied by the brief — see references/content-section-format.md — such as a headline, intro, body sections, and a call to action. Only draft what the source material actually supports; leave anything else explicitly marked as needing input rather than filling it with plausible-sounding filler.

Keep claims concrete and checkable — prefer "cuts setup time from 20 minutes to under 2" over "makes setup faster," when the source material supports a specific number; otherwise state it as an open question rather than inventing one. Do not invent quotes, statistics, or customer names.

3. Show the draft and get approval

Show the complete drafted piece or section to the user before writing anything. Do not write first and confirm after.

Approval model:

  • Default: one-time approval. Ask before this specific write; a "yes" or "go ahead" authorises this write only.
  • Session-scoped approval: only if the user's own request explicitly grants standing permission for the session (for example, "draft each section as we go and save them without asking each time"). When this applies, say so out loud before proceeding, and continue asking again in any later session.
  • Never infer standing approval from a single approval of one piece.

4. Write and confirm

Write the approved content to the named file, in the right place if the file already has other sections. Confirm what was written and where.

Stopping conditions

Stop and ask rather than guessing when:

  • the source material is too vague or conflicting to draft from confidently — recommend the Content Brief Gap Investigator instead;
  • a section would require inventing a claim, statistic, quote, or scope not present in the source; state it as an open question instead;
  • the target file or section is ambiguous; or
  • the request also asks for a publishing or distribution decision (e.g. which channel, when to post) — that is out of scope for this skill.

Quality check

Before writing, confirm that:

  • every drafted statement traces back to the supplied source material;
  • sections that can't be responsibly filled are marked as open questions, not invented;
  • the draft was shown to the user before any write occurred; and
  • the approval obtained matches what is being written (one-time vs. session-scoped, and for this write specifically).

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.