agentleFS
gokulsvisiongokulsvision/Crewm8-Social-Media-Manager-Skill-Graph/skills/publishing/draft-review/SKILL.md

draft-review

Skill17 starsChanged 7 months agoMITView on GitHub

Create and maintain a draft review queue with founder sign-off checklist — categorize drafts by readiness, flag issues, track approvals, and minimize review friction.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Pre-review each draft: before sending to founder:

    line 55
  2. Distinctive:

    If 90%+ approved as-is, propose skipping review for certain content types

    line 79
  3. Distinctive:

    If founder consistently rejects certain formats/pillars, stop drafting them

    line 80
  4. Distinctive:

    All drafts are pre-reviewed (voice check + formatting + links)

    line 116
  5. Distinctive:

    No pre-review before founder sees it (erodes trust)

    line 125
  6. Distinctive:

    No clear deadline ("whenever" = never)

    line 126
  7. Distinctive:

    Check turnaround: draft submitted → founder approved.

    line 132

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Draft Review

Manage a review queue that gets content from "written" to "approved" to "scheduled" with clear sign-off gates. The founder's time is the scarcest resource — this skill minimizes review friction while maintaining quality control.

Purpose

Founders are the bottleneck. If they need to review 30 drafts at once, they'll skim 5 and ignore the rest. This skill batches, prioritizes, and pre-clears drafts so the founder only sees what needs their judgment — and the rest flows through automatically.

When to Use

  • Content batch is drafted and ready for review
  • Setting up recurring review cadence
  • Founder says "review everything before it goes out"
  • Review is becoming a bottleneck
  • Tracking approval patterns over time

Inputs Required

  • Drafts for the review window (posts, threads, captions, visual briefs)
  • Brand voice guide (for pre-review checks)
  • Any flagged uncertainties from the content creator

Quick Reference

Draft StatusMeaningAction
DraftWritten, unreviewedSend to review queue
Needs RevisionFounder flagged issuesRevise and re-submit
Conditionally ApprovedApproved with minor changesApply changes; no re-review
ApprovedReady to scheduleMove to schedule-queue
RejectedConcept doesn't workArchive with reason

Procedure

  1. Collect all drafts for the review window. Organize by platform and scheduled date.
  2. Pre-review each draft before sending to founder:
    • Brand voice check (from brand-voice-system)
    • Character counts and platform formatting verified
    • Factual claims sourced
    • URLs verified working
    • Uncertainties flagged
  3. Build the review package:
    • Group by urgency: "must review today / this week / when you have time"
    • Include context: why this post, what pillar, expected posting day/time
    • Limit each batch to 10-15 items
  4. Send for review with clear decision options:
    • Thumbs up = approved as-is
    • "Changes:" = conditionally approved (apply changes, no re-review)
    • "Let's rework:" = needs revision (clarify what)
    • "Skip:" = reject (add reason)
  5. Track review status:
    • Draft name → status → reviewer notes → date
    • Flag drafts "needs revision" for 48+ hours
    • Escalate if founder hasn't reviewed by scheduling deadline
  6. Optimize over time:
    • If 90%+ approved as-is, propose skipping review for certain content types
    • If founder consistently rejects certain formats/pillars, stop drafting them
    • Target: review-to-scheduled under 24 hours for standard content

Output Format

# Draft Review Queue: [Week of Date]

## Review Batch [N]
**Deadline:** [Date/time]

### Item 1: [Post Title]
**Platform:** [X / LinkedIn / IG / TikTok]
**Pillar:** [Pillar]
**Scheduled for:** [Day, time]
**Preview:** [Full text]

**Decision:**
- [ ] Approved
- [ ] Approved with changes: [notes]
- [ ] Needs revision: [what]
- [ ] Rejected: [reason]

### Item 2...
...

## Review Summary
- **Total in queue:** [N]
- **Urgent (by EOD):** [N]
- **Approval rate (trailing 4 weeks):** [N]%
- **Top rejection reasons:** [Pattern 1], [Pattern 2]

Done Criteria

The skill is complete when:

  1. All drafts are pre-reviewed (voice check + formatting + links)
  2. Review package is organized by urgency
  3. Decision options are clearly specified per draft
  4. Review status is tracked
  5. Approval patterns are documented (for process improvement)

Pitfalls

  • Sending founder 30 drafts at once (they skim 5, ignore the rest)
  • No pre-review before founder sees it (erodes trust)
  • No clear deadline ("whenever" = never)
  • Founder is bottleneck and posting stops (propose "trust me" tier)
  • Rejections without reasons (you keep making the same mistake)

Verification

Check turnaround: draft submitted → founder approved. Target: under 24 hours. Check approval rate: if consistently high (90%+), reduce review friction. Check rejection patterns: if a format/pillar is rejected >30%, stop drafting 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.