agentleFS
lautioliverlautioliver/barrilete-kit/.claude/skills/project-status/SKILL.md

project-status

Skill6 starsChanged 7 days agoMITView on GitHub

Summarizes the current state of the project (version, branch flow, work in progress, epics, PRs, debt, recent decisions, pending migrations) and answers what can be started now, generated on the spot from git, GitHub and the docs. Use with "/project-status", "what state is the project in?", "catch me up", "what can I do now?", "what's next?", "what is blocked?" or when starting a new session.

15 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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    If something looks odd (an old open PR, an unassigned critical issue, a release open for weeks), mention it in one line.

    line 16
  2. Distinctive:

    If the user says which area or priority they want to work on, filter the list with that.

    line 30
  3. Very specific:

    If there are available ones with status:triage, mention it: they have no priority yet.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 11 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 status

.claude/skills/project-status/status.sh

It generates the summary on the spot from the sources (git, issues, PRs, ADRs, docs/agents-map.json). It is deliberately not saved to a file: a committed summary ages as soon as nobody regenerates it and ends up saying something false with an official look.

When answering:

  • Show the output and, if the user wants more, go deeper with the sources it cites (architecture.md, the epic, the ADR).
  • If something looks odd (an old open PR, an unassigned critical issue, a release open for weeks), mention it in one line.

What can be done now

For "what can I do now?", "what's next?", "what is blocked?":

.claude/skills/project-status/available.sh

It returns four lists: can be started now (no open blockers and unassigned, by priority), in progress (assigned or with an open PR that closes them, with who and which PR), blocked (with what blocks them) and epics in progress (with sub-issue progress). Epics do not show up as available: they are worked through their sub-issues. Taken ones do not either: /implement-issue assigns the issue when it takes it, and an open PR that closes it (through Closes #n in the body or the number in the branch) counts too. That way two sessions do not pick the same one.

When answering:

  • Show the output as is, without inventing issues that are not there.
  • If the user says which area or priority they want to work on, filter the list with that.
  • If there are available ones with status:triage, mention it: they have no priority yet.
  • GitHub takes a few seconds to update the dependency summary: if an issue was just closed, it may still show for a few more seconds.

It changes nothing, so no confirmation is needed.

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.