agentleFS
jwd83jwd83/skills/skills/project-layout/SKILL.md

project-layout

Skill1 starsChanged 5 months agoUnlicenseView on GitHub

Define and enforce the standard project paths for documentation, plans, notes, references, research, and publications. Use when creating or organizing a project or when another skill creates durable project artifacts.

2 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

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat all paths as relative to the project root, normally the Git worktree root.

    line 8
  2. Very specific:

    Keep tool-required files such as README.md, AGENTS.md, CLAUDE.md, LICENSE, and ecosystem configuration at the root.

    line 22
  3. Distinctive:

    When a skill creates a durable project artifact, place it under these paths.

    line 26
  4. Very specific:

    Keep non-status notes in plans/notes/.

    line 48
  5. Distinctive:

    Update links when moving a plan.

    line 49
  6. Very specific:

    Create every canonical directory in greenfield and early-stage projects.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Project Layout

Treat all paths as relative to the project root, normally the Git worktree root. Use this layout for new work; do not introduce alternative paths.

PathPurpose
docs/Maintained project documentation and knowledge.
docs/wiki/Interlinked or LLM-maintained knowledge base.
docs/public/Portable publication output.
plans/to-do/Draft or queued work.
plans/in-progress/Active work that must survive across sessions.
plans/completed/Finished plans retained as history.
plans/notes/Exploratory notes, notebooks, and long-term guidance.
ref/Immutable external sources and reference inputs.
ref/inbox/The one mutable lane under ref/: staging for sources awaiting placement. Files become immutable once moved into ref/.

Keep tool-required files such as README.md, AGENTS.md, CLAUDE.md, LICENSE, and ecosystem configuration at the root.

Source paths such as src/, tests/, package assets, repository utilities, and files inside an installed skill follow their own ecosystem conventions.

When a skill creates a durable project artifact, place it under these paths.

Legacy Equivalents

Use the canonical paths for new work. On an existing project, recognize these legacy names and keep using one established tree rather than creating a parallel canonical one. Migrate only when the user asks or the task includes reorganization; never split one artifact class across canonical and legacy paths.

Legacy pathCanonical destination
doc/docs/
wiki/docs/wiki/
corpus/docs/public/
plan/plans/
todos/, tasks/, plans/todos/plans/to-do/
notebook/, scratchpad/, thoughts/, notes/plans/notes/
raw/, reference/ref/
ingest/ref/inbox/

Plan Lifecycle

  • Draft work in plans/to-do/<slug>.md.
  • Move it to plans/in-progress/<slug>.md when work starts.
  • Move it to plans/completed/YYYY-MM-DD-<slug>.md when complete.
  • Keep non-status notes in plans/notes/.
  • Update links when moving a plan; do not leave duplicate copies.

Structure Markers

Create every canonical directory in greenfield and early-stage projects. Place and retain .gitkeep in each directory so the intended structure remains explicit and survives temporary emptiness.

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.