agentleFS
Sign inStart free
koinodkoinod/skills/content-qa-scorer/SKILL.md

content-qa-scorer

Skill0 starsChanged 6 months agoMITView on GitHub

Score any piece of content on 7 dimensions. Get a verdict: PASS, NEEDS WORK, or KILL. Content QA Scorer evaluates written content (social posts, emails, blog articles, ad copy, video scripts) against 7 battle-tested dimensions. Each dimension is scored 1-10 with specific feedback. The final verdict prevents you from publishing mediocre content that damages your brand. This is not subjective — each dimension has concrete criteria. A score of 6 on "Hook" means something specific and actionable. This skill activates…

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

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    When given content to score, respond with:

    line 102

≈ “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

Content QA Scorer

Score any piece of content on 7 dimensions. Get a verdict: PASS, NEEDS WORK, or KILL.

Description

Content QA Scorer evaluates written content (social posts, emails, blog articles, ad copy, video scripts) against 7 battle-tested dimensions. Each dimension is scored 1-10 with specific feedback. The final verdict prevents you from publishing mediocre content that damages your brand.

This is not subjective — each dimension has concrete criteria. A score of 6 on "Hook" means something specific and actionable.

Activation

This skill activates when:

  • The user asks to review, score, or QA a piece of content
  • The user shares draft content and asks "is this good?"
  • The user wants feedback on copy, posts, scripts, or emails
  • The user mentions content quality, scoring, or grading

Trigger phrases: "score this", "review this content", "is this good", "QA this", "rate this post", "content feedback", "grade this"

The 7 Dimensions

1. Hook (Weight: 2x)

Does the first line stop the scroll? Would someone reading this in a feed of 1000 posts pause on yours?

ScoreCriteria
9-10Pattern interrupt. Creates an open loop the reader MUST close.
7-8Strong curiosity or bold claim. Most people would pause.
5-6Decent but predictable. "5 Tips for..." territory.
3-4Boring. Reads like every other post in the niche.
1-2No hook at all. Starts with context nobody asked for.

2. Value Density

Is every sentence earning its place? Could you cut 30% without losing meaning?

ScoreCriteria
9-10Every sentence teaches, provokes, or moves the reader. Zero filler.
7-8Tight with 1-2 sentences that could be cut.
5-6Some filler, some repetition. Could be 30% shorter.
3-4More filler than substance. Reader skims.
1-2Fluff piece. Says nothing in many words.

3. Brand Alignment

Does this sound like the brand? Could a reader identify who wrote this without seeing the name?

ScoreCriteria
9-10Unmistakably on-brand. Voice, tone, values all aligned.
7-8Mostly on-brand with minor voice inconsistencies.
5-6Generic. Could be anyone's content.
3-4Off-brand in tone or message.
1-2Contradicts brand positioning or values.

4. Engagement Potential

Will people comment, share, save, or DM about this?

ScoreCriteria
9-10Polarizing, relatable, or so valuable people tag friends.
7-8Will generate meaningful comments from target audience.
5-6Might get likes but no comments or shares.
3-4Passive consumption. Scroll past and forget.
1-2Actively boring. Might cause unfollows.

5. CTA Clarity

Is there a clear next step? Does the reader know what to do after consuming this?

ScoreCriteria
9-10CTA feels natural, specific, and low-friction.
7-8Clear CTA but could be more compelling.
5-6CTA exists but is vague ("link in bio").
3-4No clear CTA. Reader finishes and does nothing.
1-2Multiple competing CTAs or completely missing.

6. Visual/Format

Is the content formatted for the platform? Easy to scan? Proper spacing?

ScoreCriteria
9-10Perfect for platform. White space, line breaks, formatting all optimized.
7-8Good formatting with minor improvements possible.
5-6Readable but not optimized for the platform.
3-4Wall of text or poor structure.
1-2Unreadable on target platform.

7. Platform Fit

Does this content match the platform's algorithm and user behavior?

ScoreCriteria
9-10Perfectly tailored — length, format, tone all match platform norms.
7-8Good fit with minor adjustments needed.
5-6Generic content posted to the platform without optimization.
3-4Wrong format or tone for the platform.
1-2Would actively hurt performance on this platform.

Instructions

When given content to score, respond with:

## Content QA Report

**Platform**: [detected or specified]
**Content Type**: [post / email / article / script / ad]
**Word Count**: [count]

### Scores

| Dimension | Score | Note |
|-----------|-------|------|
| Hook (2x) | X/10 | [one-line reason] |
| Value Density | X/10 | [one-line reason] |
| Brand Alignment | X/10 | [one-line reason] |
| Engagement Potential | X/10 | [one-line reason] |
| CTA Clarity | X/10 | [one-line reason] |
| Visual/Format | X/10 | [one-line reason] |
| Platform Fit | X/10 | [one-line reason] |

**Weighted Score**: XX/80 (Hook counts 2x)
**Verdict**: [PASS / NEEDS WORK / KILL]

### Top Fix (if not PASS)
[The single highest-leverage change that would improve the score the most]

### Rewrite Suggestion (if NEEDS WORK)
[Rewritten hook or weakest section, demonstrating the improvement]

Verdict Thresholds

  • PASS (64-80): Publish. This will perform.
  • NEEDS WORK (40-63): Fix the top issue and re-score. Do not publish as-is.
  • KILL (0-39): Start over. The core concept or execution is fundamentally weak.

Example

Input

Platform: LinkedIn "5 things I learned about sales this year. 1. Follow up matters. 2. Listen more than you talk. 3. Always add value. 4. Be authentic. 5. Never give up. What did you learn? Drop it in the comments!"

Output

DimensionScoreNote
Hook (2x)3/10"5 things I learned" is the most overused LinkedIn hook. Zero curiosity.
Value Density2/10All 5 points are cliches with no specificity or stories.
Brand Alignment4/10Too generic to be on-brand for anyone.
Engagement Potential3/10"Drop it in the comments" is lazy engagement bait.
CTA Clarity5/10CTA exists but has no value exchange.
Visual/Format6/10Numbered list is scannable. Line breaks are good.
Platform Fit5/10Right format but algorithm penalizes low-engagement bait posts.

Weighted Score: 31/80 Verdict: KILL

Top Fix: Replace every generic point with a specific story. "Follow up matters" becomes "I closed a $47K deal because I sent a 9th follow-up that said 'I'm going to stop reaching out — but before I do, here's what you're leaving on the table.'"

Built by KOINO Capital — Agentic growth systems that run while you sleep. Want this running autonomously 24/7? Deploy with KOINO

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.

Check your setup, free