From vibestack
Summarizes your recent git activity into a chill standup script you can recite to your boss
How this skill is triggered — by the user, by Claude, or both
Slash command
/vibestack:bosskeyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn your recent git history into a standup script that sounds good without inviting follow up questions.
Turn your recent git history into a standup script that sounds good without inviting follow up questions.
Run git config user.name to get the current user's git identity. Use the result as the author filter for all log queries.
Run a git log filtered to that author. Collect the last 3 days of commits OR the last 10 commits, whichever set is larger.
Use something like:
git log --author="<name>" --since="3 days ago" --pretty=format:"%H %s" --no-merges
Then also:
git log --author="<name>" --pretty=format:"%H %s" --no-merges -10
Merge and deduplicate the two lists.
For each commit, read the diff to understand what actually changed:
git show <hash> --stat
git show <hash>
Don't just rely on commit messages. Look at the code to understand the substance of the work.
Analyze all the commits together and write a status update the user can read verbatim in a standup, meeting, email, or slack message.
Tone rules:
Translation guide, think along these lines:
Present the result like this:
Your Boss Key, ready to go:
Here's where I'm at:
- [bullet 1]
- [bullet 2]
- [bullet 3]
- ...
Next up I'm [one liner about what's coming].
Also include a shorter hallway version for when someone catches you off guard:
"Been heads down on [vague but real sounding summary], making good progress. Should have more to share soon."
Keep it chill. The goal is to sound like someone who's been getting stuff done and has things under control. Not a robot, not a try hard, just a person doing their job well.
npx claudepluginhub vibestackmd/vibestack --plugin vibestackProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.