stanley-mcp-playground
CLAUDE.md8 starsChanged 3 months agoApache-2.0View on GitHub
Recipes and skills for driving Stanley, an AI content-marketing agent, through his MCP server at https://xapi.getstanley.ai/mcp. The .mcp.json in this repo registers the server; the user signs in with /mcp. When someone seems new here (they ask where to start, what this repo is, or what Stanley can do), run the stanley-start skill: it audits their connections through message_stanley and maps the result to recipes. Don't guess what they have connected. Check. Routing map, also used by stanley-start: Ground rules…
In this repository6 other files it gives its agents.
- site/llms.txtllms.txt
- build-in-publicSkill
- repurposeSkill
- stanley-reviewSkill
- stanley-startSkill
- stanley-week-planSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Very specific: line 5
When someone seems new here (they ask where to start, what this repo is, or what Stanley can do), run the stanley-start skill: it audits …
- Distinctive: line 18
Never publish live, delete, DM, or email through Stanley without the user's explicit go-ahead in this conversation.
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md 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
Stanley MCP cookbook
Recipes and skills for driving Stanley, an AI content-marketing agent, through his MCP server at https://xapi.getstanley.ai/mcp. The .mcp.json in this repo registers the server; the user signs in with /mcp.
When someone seems new here (they ask where to start, what this repo is, or what Stanley can do), run the stanley-start skill: it audits their connections through message_stanley and maps the result to recipes. Don't guess what they have connected. Check.
Routing map, also used by stanley-start:
- X or LinkedIn connected: recipe 02 (recipes/02-content-calendar.md) and recipe 06 (recipes/06-repurposing.md)
- GitHub connected: recipe 03 (recipes/03-build-in-public.md)
- a few weeks of posting history: recipe 04 (recipes/04-analytics-review.md). If history is unknown, ask Stanley how many posts he's tracked in the last 30 days before recommending it.
- the user wants media in their posts (any tool that exports a URL works): recipe 07 (recipes/07-external-media.md)
- comfortable with the above: recipe 08 (recipes/08-rituals.md)
- nothing connected: send them to getstanley.ai onboarding before any recipe
Ground rules for working in this repo:
- Never publish live, delete, DM, or email through Stanley without the user's explicit go-ahead in this conversation. Scheduling drafts is fine; it's reversible.
- Recipes state facts from recipes/09-what-stanley-can-do.md. If Stanley's actual behavior contradicts a recipe, trust Stanley and flag the recipe as stale.
- Prose in this repo stays plain and direct. No marketing voice, no hype adjectives, no em dashes.
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.

