agentleFS
JayantChopraJayantChopra/stanley-mcp-playground/.claude/skills/stanley-week-plan/SKILL.md

stanley-week-plan

Skill8 starsChanged 3 months agoApache-2.0View on GitHub

Runs a one-sitting weekly planning session that turns the user's raw material into a reviewed, bulk-scheduled batch of Stanley drafts; use when the user wants to plan a week of posts, batch-draft content, or fill their content calendar.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Never publish live, delete, DM, or email through Stanley without the user's explicit approval in this conversation.

    line 9
  2. Distinctive:

    If connections are unknown, first send Stanley the audit prompt: "List every platform and integration currently connected for this account, …

    line 11
  3. Distinctive:

    Run the audit above unless this conversation already established what's connected.

    line 14
  4. Distinctive:

    Ask Stanley for the 7-day calendar and the posting slots, and show the user what's already booked.

    line 15
  5. Distinctive:

    Only after the user approves the batch, ask Stanley to schedule the keepers into the configured posting slots across the coming week.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

You drive the message_stanley tool through the flow in recipes/02-content-calendar.md, interactively, with the user making every call.

Hard rules:

  • Never publish live, delete, DM, or email through Stanley without the user's explicit approval in this conversation.
  • Scheduling drafts into future slots is allowed without asking; it's reversible.
  • If connections are unknown, first send Stanley the audit prompt: "List every platform and integration currently connected for this account, flag anything expired or broken, and show the configured posting slots." No publishing platform or no slots means stop and send the user to getstanley.ai.

Steps:

  1. Run the audit above unless this conversation already established what's connected.
  2. Ask Stanley for the 7-day calendar and the posting slots, and show the user what's already booked.
  3. Gather raw material from the user: what they shipped, learned, or argued about this week. Offer to have Stanley pull from GitHub, Notion, or Granola where connected. Never invent material.
  4. Agree counts per platform with the user (say 4 X posts and 2 LinkedIn posts, sized to the open slots), then request the whole batch from Stanley in one message: numbered drafts, in the user's voice.
  5. Show the user the batch and collect a verdict per draft: keep, kill, or redraft with notes. Relay redraft notes to Stanley with wrapper tags like <tweet> intact, and loop until the user calls the batch done.
  6. Only after the user approves the batch, ask Stanley to schedule the keepers into the configured posting slots across the coming week. Never invent times outside the slots.
  7. Relay any moves or deletions the user wants, then close by showing the 7-day calendar.

A draft over a platform limit: point at recipes/09-what-stanley-can-do.md. Connection failures: recipes/01-first-connection.md.

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.