grand-tour
Skill1 starsChanged 3 months agoMITView on GitHub
Use when the user is new to a codebase, coming back to one after months, or asks for a tour, an orientation, "how does this repo fit together", "walk me through this codebase", "where do I start", or "explain the architecture", optionally focused on one area. Read-only.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- closestfriend/grand-tourtheir own version, first seen Oct 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- closestfriend/grand-tour★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- anger-translatorSkill
- cache-moneySkill
- codebase-memoirSkill
- codex-reviewSkill
- goalpostSkill
- identity-theftSkill
- relocate-sessionSkill
- right-stuffSkill
- rubicon-wordpress-version-labSkill
- second-lookSkill
- secret-santa-generatorSkill
- showdownSkill
- star-chartSkill
- work-evidence-researchSkill
The file
We split this skill 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 17
If a code-graph index covers this repo, start there.
- Distinctive: line 22
If the user named an area, do all of this for that area and keep the rest to one sentence of context.
≈ “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.
Files
Grand tour
Onboard the user the way a senior teammate would on their first day: the mental model first, then just enough of the map to find their way, then where to start. Read-only.
1. Investigate
- If a code-graph index covers this repo, start there. Examples: a codebase-memory MCP server (
list_projects, thenget_architecture), or agraphify-out/directory. Use it for structure, entry points, and call paths, then confirm what matters in the source. - With no index, and in a large repo, fan out with the Explore agent, one area per search. In a small repo, read directly.
- Find the entry points, how the project is built and run, the main modules and how they talk to each other, and where shared code, types, and config live. Read enough real code to be accurate. Never describe a part from its name alone.
- Choose one representative flow, such as a request, a command, an install, or a build, and follow it through the actual code from where it starts to where it ends.
If the user named an area, do all of this for that area and keep the rest to one sentence of context.
2. Answer in this shape
Five sections, in this order, with these headings:
What this is: two or three sentences: what the project does, for whom, and its overall shape.
The main parts: one table, at most eight rows, one row per area of responsibility, with these columns: Part, Responsible for, Lives in. Group related directories into one row. A row is an area, not a file, and not one row per skill, plugin, or package of the same kind.
How it fits together: the flow you chose, as a numbered walk of four to eight steps. Each step names the file or module where it happens and what it hands to the next step.
Conventions and traps: up to five bullets. Each is a rule or pattern a newcomer would break or trip over, with where it is enforced or written down.
Where to start: two or three concrete pointers for a first read or a first change, each with the path to open first.
The tour describes the codebase as it is on disk. It does not report session state (branches, open PRs, CI runs, local tool versions). When you notice defects or drift while investigating, add an "Also noticed" list after the tour: at most three items, one line each. Do not offer to fix them inside the tour.
Example (abridged)
What this is: a recipe-sharing web app. A React front end talks to a REST API over a Postgres database, and a worker resizes uploaded photos.
How it fits together: uploading a photo:
web/src/pages/RecipeEdit.tsxposts the file to/api/recipes/:id/photo.api/routes/photos.tsstores the original in object storage and enqueuesresize-photo.worker/jobs/resizePhoto.tswrites three sizes and updatesrecipes.photo_urls.web/src/components/RecipeCard.tsxreadsphoto_urlsand picks a size per screen.
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.

