priyanshu-aryapriyanshu-arya/LinkedIn_Automation/.claude/skills/critique-draft-substack-note/SKILL.mdcritique-draft-substack-note
Skill0 starsChanged 58 days agoMITView on GitHub
Use when the user asks to review/critique a Substack Note's quality, check it for accuracy or duplication, compute its viral potential score, or explicitly invokes /critique-draft-substack-note. Runs the Critic Agent on a status:draft, platform:substack-note Draft Note, auto-revises it once if it scores low, and hands it off to approval by moving it to status:in_review.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-draftSkill
- check-plagiarismSkill
- critique-draftSkill
- critique-draft-substack-articleSkill
- critique-draft-xSkill
- draft-commentSkill
- draft-replySkill
- extract-hookSkill
- generate-ideasSkill
- generate-visualSkill
- generate-visual-substack-articleSkill
- generate-weekSkill
- generate-week-substackSkill
- generate-week-xSkill
- humanize-draftSkill
- interviewerSkill
- monitor-engagementSkill
- optimize-profileSkill
- plan-advocacySkill
- plan-weekSkill
- plan-week-substack-articleSkill
- plan-week-substack-noteSkill
- plan-week-xSkill
- publish-substackSkill
- pull-analyticsSkill
- pull-analytics-xSkill
- repurpose-postSkill
- research-topicSkill
- review-draftsSkill
- schedule-approvedSkill
- schedule-approved-xSkill
- update-playbookSkill
- write-draftSkill
- write-draft-substack-articleSkill
- write-draft-substack-noteSkill
- write-draft-xSkill
The file
Files
Critique Draft Substack Note (Critic Agent — Substack Notes)
Reuses /critique-draft-x's short-form rubric shape (no thread-cohesion
factor needed — Notes have no thread concept), scoped to platform:
substack-note and Content-Learnings/playbook-substack.md's Notes
section.
Arguments
- draft-id (optional) — critique one specific note. If omitted, run
against every
platform: substack-noteDraft Note currentlystatus: draft.
Process (per draft)
1. Re-verify accuracy
Same as /critique-draft: re-read sources[], fix any drift now.
2. Originality / duplicate check
Scan Content-Learnings/content-index.md filtered to platform:
substack-note. Same severity split as /critique-draft: genuine
duplicate stops here (stay draft, flag, report); similar-but-distinct
pulls the Originality sub-score down and proceeds to review.
3. Score Viral Potential (0-10)
Average these, each 0-10:
| Factor | How to assess it |
| Hook strength | Does the opening line land immediately? |
| Scannability | Short and casual, no wall of text |
| Novelty / insight | Fresh beyond basic regurgitation |
| Discussion catalysis | Would this get real replies from subscribers? |
| Technical accuracy | Consistency with linked research |
| Originality | Inverse of step 2's findings |
| Historical playbook alignment | Check playbook-substack.md's Notes section for a matching evidenced rule; otherwise neutral (5) |
4. Auto-revise once if weak
Same rule as /critique-draft: below 6, one targeted pass re-reading
voice-guide-substack.md's Notes section, recompute, stop after one pass.
5. Update the Draft Note
Same field updates as /critique-draft — skip entirely if step 2 found a
genuine duplicate.
Report back
Same shape as /critique-draft's report.
Notifications
Same batching rule: one notification per run.
Hard rules
Identical to /critique-draft's hard rules, scoped to Substack Notes.
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.