plan-week-substack-article
Skill0 starsChanged 58 days agoMITView on GitHub
Use when the user asks to plan this week's Substack article, decide which idea becomes the week's long-form piece, or explicitly invokes /plan-week-substack-article. Assigns one candidate idea tagged for the substack-article platform from Post-Ideas/ to a single weekly slot, without drafting any article text.
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-substack-noteSkill
- 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-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
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Read Post-Ideas/ for status: candidate (or selected but not yet claimed by substack-article) ideas with substack-article in platforms.
- Very specific: line 38
Read Content-Learnings/playbook-substack.md's Articles section first for an evidenced day-performance rule (≥3 published articles).
- Distinctive: line 60
Never assign more than 1 article per week without the user explicitly asking for more this run.
- Distinctive: line 62
Never force a shallow idea into article form just to fill the slot — an honest "nothing qualifies this week" is the correct outcome.
- Distinctive: line 64
Never draft article text here.
≈ “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.
Files
Plan Week Substack Article (Content Strategist — Substack Articles)
Substack Articles' sibling to /plan-week, simplified for a 1/week cadence.
Same shared candidate pool (Post-Ideas/); only the cadence and depth
requirement differ. Selection only — does not write article text (that's
/write-draft-substack-article) and never touches publishing.
Arguments
- week (optional) — an ISO week or Monday date. Same default rule as
/plan-week.
Process
1. Load the candidate pool, filtered to this platform
Read Post-Ideas/ for status: candidate (or selected but not yet
claimed by substack-article) ideas with substack-article in
platforms. Prefer ideas whose depth genuinely supports 800+ words of
real substance — a thin idea that works fine as a single LinkedIn post
doesn't automatically deserve a full article. If nothing in the pool
clears that bar, say so plainly rather than stretching a shallow idea.
2. Check recent history for fatigue
Scan Content-Learnings/content-index.md filtered to platform:
substack-article for topic repetition in the prior ~4 weeks (a longer
window than the feed platforms, since articles are lower-frequency and a
repeat is more noticeable to subscribers).
3. Pick the day
Read Content-Learnings/playbook-substack.md's Articles section first for
an evidenced day-performance rule (≥3 published articles). Otherwise, since
this is a new format for the account, source a starting heuristic from
real research on Substack publishing-day norms (many newsletters do better
on a consistent, predictable day — check current guidance via WebSearch
rather than assuming one) and record it back into this file once found.
4. Commit the assignment
Append {platform: substack-article, week: <ISO week>, date: <date>} to
the idea's platform_schedule. Advance status: candidate → selected if
this is the idea's first platform claim.
5. Report
One line: which idea, why it earns the depth of a full article (not just a feed post), and the assigned date — or, honestly, that no idea in the pool currently clears the depth bar and what topic area would need more research first.
Hard rules
- Never assign more than 1 article per week without the user explicitly asking for more this run.
- Never force a shallow idea into article form just to fill the slot — an honest "nothing qualifies this week" is the correct outcome.
- Never draft article text here.
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.

