agentsclimarketplace

Commit worklog guardrails

Skill jukrap/ai-agent-playbook/skills/git/commit-worklog-guardrails

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install
npx -y skills add jukrap/ai-agent-playbook --skill commit-worklog-guardrails

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when staging files, writing commits, pushing branches, opening PRs, preparing release notes, or recording worklogs with local-only doc constraints.

SKILL.md

1.1 KB, 178 tokens by cl100k_base, as published. Nobody here has run it

Commit Worklog Guardrails

Primary route: delivery/git-worklog-guardrails.

Protect unrelated changes, local-only files, and verification integrity.

Workflow

  1. Check branch, remote, upstream, dirty files, and staged files.
  2. Stage only explicit files related to the task.
  3. Run project-defined verification and report only commands actually executed.
  4. Write structured Conventional Commit messages unless the repo proves another convention.
  5. Suggest a checkpoint commit when a verified logical slice, large diff, many touched files, or mixed concern set would be clearer as a separate commit.
  6. Push only to the intended remote/branch.
  7. Write detailed worklogs for milestones, blockers, large direction changes, or long debugging.

Reference

Read references/git-worklog-checklist.md before committing, pushing, writing PR bodies, or creating worklogs.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.