review-content
Skill2 starsChanged 9 months agoMITView on GitHub
Review content for quality and accuracy
In this repository6 other files it gives its agents.
- auto-fixSkill
- content-pipelineSkill
- edit-contentSkill
- fact-checkSkill
- shipSkill
- write-contentSkill
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
- Distinctive: line 89
Every piece of feedback must be:
≈ “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.
Files
Review Content
Review the following content:
Target: $ARGUMENTS
Review the content against all 6 dimensions:
- Accuracy
- Clarity
- Style consistency
- Structure
- Completeness
- Audience appropriateness
Provide a scored report with specific, actionable feedback.
Full 6-Dimension Review Pipeline
1. Accuracy (Score 1-5)
Check:
- Statistics verified with current sources
- Claims supported by evidence
- Technical details correct (APIs, code examples, commands)
- Attributions and quotes properly cited
- No outdated information
2. Clarity (Score 1-5)
Check:
- Flesch-Kincaid reading level appropriate for audience
- Jargon explained on first use
- Sentence length varies (avoid 30+ word sentences)
- Complex ideas broken into digestible chunks
- Active voice predominates
3. Style (Score 1-5)
Check:
- Tone consistent with project voice
- Formatting follows project standards
- Terminology matches style guide
- Inclusive, accessible language
- No cliches or filler phrases
4. Structure (Score 1-5)
Check:
- Logical flow from intro to conclusion
- Heading hierarchy correct (H1 → H2 → H3)
- Paragraph length reasonable (3-4 sentences)
- Lists properly formatted
- Smooth transitions between sections
5. Completeness (Score 1-5)
Check:
- All promised points covered
- CTAs present and clear
- Next steps or conclusions provided
- Examples support every major point
- No dangling references
6. Audience (Score 1-5)
Check:
- Reading level appropriate for target readers
- Assumptions made explicit
- Background knowledge required is clear
- Examples relatable to audience
- Tone matches audience expectations
Scoring Rubric Per Dimension
- 5 — Excellent, publication-ready
- 4 — Good, minor tweaks needed
- 3 — Acceptable, moderate revision required
- 2 — Needs work, significant issues
- 1 — Poor, major revision or rewrite needed
Actionable Feedback Requirements
Every piece of feedback must be:
- Specific — "Paragraph 3 uses three acronyms without definition" not "Some sections are unclear"
- Actionable — "Replace 'utilize' with 'use'" not "Simplify language"
- Constructive — "Add a code example after the concept explanation" not "This is confusing"
Summary with Verdict
Overall Score: X/30
Calculate: sum of all 6 dimension scores
Verdict:
- APPROVE (≥24/30) — publication-ready, minor edits optional
- REVISE (18-23/30) — needs specific fixes listed in action items
- REJECT (<18/30) — major issues, consider rewrite
Specific Action Items
- [Highest priority fix]
- [Second priority fix]
- [Third priority fix] ...
Limit to 5-7 action items max — focus on highest impact changes.
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
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.

