agentleFS
desertcachedesertcache/agent-os/skills/project-status/SKILL.md

project-status

Skill0 starsChanged 9 months agoMITView on GitHub

Check status of all active projects and identify next actions. Use when the user says "project status", "where are we", "what's blocked", or "/project-status".

12 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

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

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 6

    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. Distinctive:

    When invoked, check all registered projects and provide a unified status report.

    line 10
  2. Very specific:

    Read <vaultPath>/<projectVaultFolder>/STATUS.md (if it exists)

    line 16
  3. Distinctive:

    If user said "quick", "glance", or it's late evening: Use Quick mode

    line 50
  4. Distinctive:

    If user said "detailed", "deep dive": Use Detailed mode

    line 51
  5. Very specific:

    Read the projects list from agent-os.config.json

    line 66
  6. Distinctive:

    Read README.md / STATUS.md for each project's vault folder

    line 67
  7. Distinctive:

    Check recent session notes for context

    line 68
  8. Very specific:

    All paths come from agent-os.config.json — never hardcode user-specific paths

    line 73
  9. Distinctive:

    Use checkboxes for pending items

    line 76

“Common” is measured: kept by at least 6 in 10 of the 8 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

When invoked, check all registered projects and provide a unified status report.

Projects to Check

Scan all project vault folders registered in agent-os.config.json. For each project:

  • Read <vaultPath>/<projectVaultFolder>/README.md
  • Read <vaultPath>/<projectVaultFolder>/STATUS.md (if it exists)

Also check:

  • Recent sessions: <vaultPath>/Sessions/ for latest handoffs
  • Planning: <vaultPath>/Planning/ for priorities (if exists)

Report Format

# Project Status Report
**Generated:** [date]

## Summary
| Project | Status | Blocked On |
|---------|--------|------------|
| [name] | [status] | [blocker or "None"] |

## [Project Name]
**Status:** [summary]

**Blockers:**
- [ ] [blocker 1]

**Next Actions:**
1. [action 1]
2. [action 2]

## Upcoming Deadlines
[Any dates mentioned in status files]

Response Modes

Before generating report, check context:

  • If user said "quick", "glance", or it's late evening: Use Quick mode
  • If user said "detailed", "deep dive": Use Detailed mode
  • Otherwise: Ask "Quick overview or detailed breakdown?"

Quick Mode

  • Summary table only (Project | Status | Blocker)
  • 1 sentence per project max
  • Skip sections with no updates

Detailed Mode

  • Full report format as specified above
  • Include all blockers and next actions
  • Cross-reference with recent sessions

Execution Steps

  1. Read the projects list from agent-os.config.json
  2. Read README.md / STATUS.md for each project's vault folder
  3. Check recent session notes for context
  4. Synthesize into report format
  5. Highlight what needs attention most urgently

Rules

  • All paths come from agent-os.config.json — never hardcode user-specific paths
  • Concise bullet points, scannable format
  • Highlight blockers prominently
  • Use checkboxes for pending items

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.