agentleFS
Sign inStart free
Marwan-Ahmed-devMarwan-Ahmed-dev/vibecode-pro-max/.claude/skills/vc-watzup/SKILL.md

vc:watzup

Skill0 starsChanged 3 months agoMITView on GitHub

Use when you need a read-only handoff summary of current branch state, local/remote refs, worktrees, active plans, selected-plan hints, and suggested next checks.

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do use it for read-only branch, worktree, and active-plan summaries.

    line 17
  2. Distinctive:

    Do use it to surface likely selected-plan context when it can be proven or safely hinted.

    line 18
  3. Distinctive:

    Do not use it to choose a plan authoritatively.

    line 19
  4. Distinctive:

    Do not use it to approve execution, resume execution, or mutate repo/process state.

    line 20
  5. Very specific:

    If a user needs execution, the repo still requires explicit plan selection and ENTER EXECUTE MODE.

    line 30
  6. Distinctive:

    Run the local scanner:

    line 34
  7. Distinctive:

    If the scanner fails, say that explicitly and fall back to the minimal read-only commands:

    line 75
  8. Very specific:

    Read-only only. No branch switching, plan edits, or fetch unless --fetch is explicit.

    line 86
  9. Very specific:

    Treat selected-plan inference as tentative unless it came from an explicit --selected-plan argument.

    line 87
  10. Distinctive:

    Use this for session handoff and quick repo orientation, not for workflow control.

    line 89
  11. Distinctive:

    If the scan cannot prove something, emit a warning instead of guessing.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Watzup

Summarize the current repo state for handoff and resume work.

This is a helper skill only.

  • Do use it for read-only branch, worktree, and active-plan summaries.
  • Do use it to surface likely selected-plan context when it can be proven or safely hinted.
  • Do not use it to choose a plan authoritatively.
  • Do not use it to approve execution, resume execution, or mutate repo/process state.

Core Contract

watzup is advisory.

  • Evidence comes from git, worktree metadata, and process/* plan inventory.
  • Selected-plan awareness is a hint, not a command.
  • Next-step recommendations are suggestions, not workflow gates.

If a user needs execution, the repo still requires explicit plan selection and ENTER EXECUTE MODE.

Invocation

Run the local scanner:

node .claude/skills/watzup/scripts/watzup-scan.cjs --json

Useful flags:

node .claude/skills/watzup/scripts/watzup-scan.cjs
node .claude/skills/watzup/scripts/watzup-scan.cjs --json --max-branches 8 --plan-limit 6
node .claude/skills/watzup/scripts/watzup-scan.cjs --selected-plan process/general-plans/active/example_PLAN_27-05-26.md
node .claude/skills/watzup/scripts/watzup-scan.cjs --since "14 days ago"
node .claude/skills/watzup/scripts/watzup-scan.cjs --fetch

Input Sources

The scanner reads from:

  • git status --short --branch
  • git worktree list --porcelain
  • local and remote branch refs plus sampled recent commits
  • process/general-plans/active/
  • process/features/*/active/
  • optional session-state hints if a local session id is present

It does not scan upstream plans/**, and it never treats a selected-plan hint as execute authority.

Output Shape

The default output is a human-readable report with these sections:

  • Current State
  • Recent Work
  • In-Flight Plans
  • Next Steps
  • Warnings

--json returns the same information as structured data.

If the scanner fails, say that explicitly and fall back to the minimal read-only commands:

git status --short --branch
git worktree list --porcelain
git for-each-ref --format='%(refname:short) %(committerdate:iso8601) %(objectname:short) %(subject)' refs/heads refs/remotes
find process/general-plans/active process/features -path '*/active/*' -type f | sort

Safety Rules

  1. Read-only only. No branch switching, plan edits, or fetch unless --fetch is explicit.
  2. Treat selected-plan inference as tentative unless it came from an explicit --selected-plan argument.
  3. Remote branch data is stale-by-default unless --fetch is explicit.
  4. Use this for session handoff and quick repo orientation, not for workflow control.
  5. If the scan cannot prove something, emit a warning instead of guessing.

Good trigger phrases:

  • what's in flight
  • give me a handoff summary
  • what active plans do we have
  • show branch and worktree status
  • what should I look at next

Load references/watzup-workflow.md when you need the decision tree or hint-priority rules.

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