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

stanley-review

Skill8 starsChanged 3 months agoApache-2.0View on GitHub

Runs the standard weekly analytics review through Stanley and presents the findings as a short digest; use when the user asks how their content is performing, wants their weekly numbers, or runs recipe 04.

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:

    Read first, digest second, draft only on request.

    line 6
  2. Distinctive:

    Check there's history worth reading by asking Stanley how many posts he's tracked over the last 30 days.

    line 9
  3. Distinctive:

    Run the standard review as separate messages so each answer stays legible:

    line 10
  4. Distinctive:

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

    line 21
  5. Distinctive:

    Keep platform wrappers like <tweet> intact when passing a draft back to Stanley.

    line 23

≈ “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

Read first, digest second, draft only on request.

  1. If you don't know what's connected, send Stanley this through message_stanley before anything else: "List every platform and integration currently connected for this account, flag anything expired or broken, and show the configured posting slots." Skip expired or missing platforms in the review and tell the user which ones you skipped.
  2. Check there's history worth reading by asking Stanley how many posts he's tracked over the last 30 days. If it's only a handful, warn the user the numbers will be thin and let them decide whether to continue.
  3. Run the standard review as separate messages so each answer stays legible:
    • top 5 posts by engagement over the last 30 days and what they share
    • the 5 weakest from the same window and what those share
    • average engagement by platform and by format
    • follower trend per platform, flagging any week that broke it
    • current posting streak
  4. Present the findings as a short digest, not a transcript: one line per section with the numbers, plus the patterns worth acting on. Quote Stanley's figures as returned; never invent, round, or extrapolate numbers he didn't give.
  5. Offer to turn the digest into next week's plan. On a yes, ask Stanley to propose topics, formats, and post counts per platform, show the user the plan, then offer to draft the week and schedule the drafts into open slots (recipe 02's territory).

Hard rules:

  • Never publish live, delete posts, send DMs, or email a subscriber list without the user's explicit approval in this conversation.
  • Scheduling drafts into future slots is allowed; it's reversible.
  • Keep platform wrappers like <tweet> intact when passing a draft back to Stanley.

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.