agentleFS
priyanshu-aryapriyanshu-arya/LinkedIn_Automation/.claude/skills/plan-week-substack-note/SKILL.md

plan-week-substack-note

Skill0 starsChanged 58 days agoMITView on GitHub

Use when the user asks to plan the week's Substack Notes, decide what gets posted when as short-form Substack content, or explicitly invokes /plan-week-substack-note. Assigns candidate ideas tagged for the substack-note platform from Post-Ideas/ to specific days under a ~3/week cadence, without drafting any note text.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read Post-Ideas/ for ideas with substack-note in platforms, status: candidate (or already selected for another platform but not yet claimed …

    line 22
  2. Very specific:

    Read Content-Learnings/playbook-substack.md's Notes section for an evidenced day rule first.

    line 33
  3. Very specific:

    Never assign more than target_count (default 3) in one week.

    line 58
  4. Distinctive:

    Never force the count — fewer filled slots is the correct outcome when the pool doesn't support more.

    line 59
  5. Distinctive:

    Never draft note text here.

    line 61

≈ “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

Plan Week Substack Note (Content Strategist — Substack Notes)

Substack Notes' sibling to /plan-week-x, simplified — Notes are more conversational/evergreen and less tied to a specific optimal posting window than X or LinkedIn, so day selection matters less than variety and pacing across the week.

Arguments

  • week (optional) — same default rule as /plan-week.
  • target_count (optional) — default 3.

Process

1. Load the candidate pool, filtered to this platform

Read Post-Ideas/ for ideas with substack-note in platforms, status: candidate (or already selected for another platform but not yet claimed by this one).

2. Check recent history for fatigue

Scan Content-Learnings/content-index.md filtered to platform: substack-note for the prior ~2 weeks, same window as /plan-week.

3. Pick the days

Read Content-Learnings/playbook-substack.md's Notes section for an evidenced day rule first. Otherwise spread the target_count slots across the week with reasonable gaps (don't cluster all 3 on consecutive days by default) — there's no research-backed "best time" claim to make for this format yet, so say plainly this is just even spacing, not an optimized schedule.

4. Match ideas to slots

Same tie-breaking as /plan-week: best fit, rank_score as tiebreaker. Require at least 2 distinct categories across the week's Notes, same variety rule.

5. Commit the assignment

Append {platform: substack-note, week: <ISO week>, date: <date>} to the idea's platform_schedule. Advance status to selected if unclaimed.

6. Report

A table: date | idea (topic) | category | rank_score, with unfilled slots called out plainly.

Hard rules

  • Never assign more than target_count (default 3) in one week.
  • Never force the count — fewer filled slots is the correct outcome when the pool doesn't support more.
  • Never draft note text here.

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.