agentleFS
JayantChopraJayantChopra/stanley-mcp-playground/.claude/skills/build-in-public/SKILL.md

build-in-public

Skill8 starsChanged 3 months agoApache-2.0View on GitHub

Turns the user's recent GitHub activity into build-in-public posts through Stanley; use when the user wants to post about something they shipped, a specific PR or commit, or their recent coding work.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never publish live, delete posts, send DMs, or email a list through Stanley without the user's explicit approval in this conversation.

    line 12
  2. Distinctive:

    Ask the user which repo (or all connected repos) and what lookback window, 1 to 30 days.

    line 17
  3. Distinctive:

    Ask which platforms, then have Stanley draft: a single post for a small fix, a thread for a bigger ship.

    line 21
  4. Very specific:

    If the user wants this on a schedule, point them to recipes/08-rituals.md instead of creating a ritual unasked.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Build in public

Drive message_stanley to run this flow with the user. Stanley keeps conversation state across calls, so write to him in plain English and pass drafts back with their platform wrappers (<tweet>, <linkedin_post>, and so on) intact.

Hard rules:

  • Never publish live, delete posts, send DMs, or email a list through Stanley without the user's explicit approval in this conversation. Scheduling drafts is allowed, since it can be undone.
  • If you don't know what's connected, first send Stanley the audit prompt: list every connected platform and integration, flag anything expired or broken, and show the configured posting slots. GitHub must be on the list; if it isn't, stop and point the user at recipes/01-first-connection.md.

Steps:

  1. Ask the user which repo (or all connected repos) and what lookback window, 1 to 30 days. If they name a specific PR or commit instead, jump to step 4 with that target.
  2. Send Stanley the repo and window and ask for a shortlist of story-worthy changes: shipped features, gnarly bugs, decisions with tradeoffs. Tell him to skip dependency bumps and formatting churn.
  3. Show the user the shortlist as Stanley sent it and ask which item becomes a post. Draft nothing they haven't picked.
  4. Have Stanley read the actual diff for the picked item and pull one concrete, quotable detail. A draft that leans on the PR title alone goes back.
  5. Ask which platforms, then have Stanley draft: a single post for a small fix, a thread for a bigger ship. Show the user the draft, collect edits, and pass them back with the wrapper intact.
  6. Offer to schedule into the next open slot or leave it as a draft. Publish live only if the user says so in this conversation.

If the user wants this on a schedule, point them to recipes/08-rituals.md instead of creating a ritual unasked.

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.