agentleFS
Rome-1Rome-1/obsidian-claude-starter/.claude/skills/project-brief/SKILL.md

project-brief

Skill5 starsChanged 33 days agoMITView on GitHub

Starts a new project note (a single file, or a folder with Brief, Current-State and Decisions) by interviewing the user for the why, scope and definition of done; or, for an existing project, loads its brief and current state and summarizes where things stand before any work begins. Use when the user says "start a project", "new project", "write a brief for X", "what's the status of X", "catch me up on X", "let's work on X", runs /project-brief, or when a task touches a project whose notes you have not read yet this session.

10 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, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    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. Very specific:

    Read Brief.md and Current-State.md (folder project), or the single project note.

    line 13
  2. Distinctive:

    Use the user's words for the why and the scope.

    line 40
  3. Very specific:

    Add typed links where they apply (works_with::, depends_on::, part_of::).

    line 42
  4. Very specific:

    Run python3 scripts/check_vault.py, show the user the note, and commit if they have agreed to agent commits.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 10 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

Project brief

First find out whether the project exists: Grep Projects/ for the name (files and folder names, and title-like headings).

Existing project: load it

  1. Read Brief.md and Current-State.md (folder project), or the single project note. Skim Decisions.md headings and the last few meetings that link the project.
  2. Summarize in the chat, in under ten lines: the goal, where things stand, next actions, open questions, anything blocked.
  3. Point out anything that looks stale: updated: more than a month old while status: active, checked boxes still listed as next actions, a Current-State that contradicts a newer meeting note. Ask before fixing.

Then do the task the user came for.

New project: create it

1. Interview (short)

  • What is it, and why now?
  • What is in scope, and what is explicitly out?
  • How will you know it worked? Push for something checkable ("ten people use it", "the bed survives a season"), not "it's good".
  • Who else is involved? (Link existing person notes.)
  • The first two or three next actions.

2. Choose the shape

  • Single file (Projects/Name.md) by default.
  • Folder (Projects/Name/Brief.md, Current-State.md, Decisions.md) when the project will run for months, involve several people, or collect many decisions. A single-file project can be split into a folder later; offer that when one grows past a couple of screens.

3. Write it

  • From System/Templates/Project.md (and Project-Current-State.md and Decision.md for the folder shape).
  • Use the user's words for the why and the scope.
  • Fill created: and updated: with today's date and set status: active (or idea if they are not starting yet).
  • Add typed links where they apply (works_with::, depends_on::, part_of::).
  • Run python3 scripts/check_vault.py, show the user the note, and commit if they have agreed to agent commits.

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.