agentleFS
Sign inStart free
xsovad06xsovad06/sova/.agents/skills/sova-status/SKILL.md

sova-status

Skill3 starsChanged 6 days agoApache-2.0View on GitHub

Project health check (git state, services, tests, and progress overview).

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 8 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check if project services are running (Docker, dev server, etc.)

    line 21
  2. Distinctive:

    Verify the application responds (health check endpoint if available)

    line 22
  3. Distinctive:

    Check for unapplied migrations (see CLAUDE.md for the migration check command)

    line 25
  4. Distinctive:

    Verify database is accessible

    line 26
  5. Distinctive:

    Check for outdated or conflicting packages

    line 29
  6. Distinctive:

    Verify lock file is in sync with dependency manifest

    line 30
  7. Distinctive:

    Run the project's tests (see CLAUDE.md for commands)

    line 33
  8. Very specific:

    Read agent memory files if they exist (.claude/agent-memory/MEMORY.md)

    line 37
  9. Very specific:

    Check open issues: gh issue list --assignee @me --state open --limit 10

    line 38
  10. Very specific:

    Check open PRs: gh pr list --author @me --state open

    line 39
  11. Very specific:

    Want to start working?: Run the sova-find-task skill or the sova-standup skill

    line 56
  12. Very specific:

    Need to run tests?: Run the sova-test skill

    line 57
  13. Distinctive:

    NEVER use emojis in any output

    line 61

≈ “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 Status Check

Perform a health check on the project and report current status.

Focus area: the arguments provided when this skill is invoked

Checks

1. Git Status

  • Current branch and clean/dirty state
  • Uncommitted changes summary
  • Recent commits (last 5)
  • Any stale feature branches: git branch --merged main

2. Services

  • Check if project services are running (Docker, dev server, etc.)
  • Verify the application responds (health check endpoint if available)

3. Database

  • Check for unapplied migrations (see CLAUDE.md for the migration check command)
  • Verify database is accessible

4. Dependencies

  • Check for outdated or conflicting packages
  • Verify lock file is in sync with dependency manifest

5. Test Suite

  • Run the project's tests (see CLAUDE.md for commands)
  • Report pass/fail count and coverage if available

6. Project Progress

  • Read agent memory files if they exist (.claude/agent-memory/MEMORY.md)
  • Check open issues: gh issue list --assignee @me --state open --limit 10
  • Check open PRs: gh pr list --author @me --state open
  • Reference project milestones: gh issue list --state open --json milestone

7. Report

Provide a concise status dashboard:

Branch:       main (clean)
Services:     app [running] | db [running]
Migrations:   up to date
Tests:        120 passed, 0 failed
Open PRs:     2
Open Issues:  5
Next up:      <suggested focus>

Cross-References

  • Want to start working? Run the sova-find-task skill or the sova-standup skill
  • Need to run tests? Run the sova-test skill

Rules

  • NEVER use emojis in any output

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.

Check your setup, free