git-standup
Skill14 starsChanged 6 months agoMITView on GitHub
Generate a clean daily standup summary from your git commits. No more staring at the blank "what did you do yesterday?" field. Bullet (default): Clean 3-section list Slack: Prefixed with :white_check_mark: / :hammer: / :red_circle: Jira: Extracts ticket numbers from commit messages (e.g. PROJ-123) Plain: Flat chronological list, good for email Raw git log is noisy. This skill: - Deduplicates related commits into one line - Infers intent from commit message prefixes - Separates "done" from "in progress" (unmerged branches…
In this repository14 other files it gives its agents.
- llms.txtllms.txt
- claude-cost-trackerSkill
- commit-roastSkill
- context-budgetSkill
- debug-trailSkill
- env-doctorSkill
- ev-calculatorSkill
- growth-trackerSkill
- investment-briefing-agentSkill
- multi-agent-orchestratorSkill
- news-sentiment-engineSkill
- options-flow-analyzerSkill
- price-monitor-alertSkill
- pr-review-prepSkill
The file
Files
Git Standup Generator
Generate a clean daily standup summary from your git commits. No more staring at the blank "what did you do yesterday?" field.
What it does
- Reads your git log for the last 24 hours (or configurable window)
- Groups commits by repo and type (feat/fix/refactor/docs/chore)
- Generates a standup in your preferred format (bullet list, Slack-ready, Jira-style)
- Flags blocked work and carry-overs automatically
- Strips noise: merge commits, version bumps, auto-generated entries
Usage
Run git standup for today.
Look at commits in the last 24 hours across all repos in ~/Projects.
Group by: what I did, what I'm doing today, any blockers.
Format: 3-bullet standup (Yesterday / Today / Blockers).
Keep it under 150 words total.Example Output
Git Standup — 2026-05-13 (Tue)
YESTERDAY
- Shipped options flow scanner real/lottery split (6 commits, news-engine)
- Fixed ComposioHQ PR CI failure — moved entry alphabetically before CSV Data Summarizer
- Added MIT license to ai-investment-skills for awesome-list compliance
TODAY
- Post-mortem write-up: XLI anomaly methodology
- Review VoltAgent PR #253 feedback
- Start backtest feature scoping
BLOCKERS
- dev.to daily publish limit — 3 articles queued for tomorrowConfiguration
Run git standup:
Repos: ~/Projects/news-engine, ~/Projects/ai-investment-skills
Window: last 24 hours
Author: me (use git config user.email)
Format: slack # options: bullet | slack | jira | plain
Include: feat, fix, refactor
Exclude: chore, merge commits, version bumps
Max length: 150 wordsFormats
Bullet (default): Clean 3-section list
Slack: Prefixed with :white_check_mark: / :hammer: / :red_circle:
Jira: Extracts ticket numbers from commit messages (e.g. PROJ-123)
Plain: Flat chronological list, good for email
Why this beats git log --oneline
Raw git log is noisy. This skill:
- Deduplicates related commits into one line
- Infers intent from commit message prefixes
- Separates "done" from "in progress" (unmerged branches = in progress)
- Generates human-readable phrasing, not commit hash soup
Requirements
- Bash tool access (runs
git loginternally) - Works with any git repo — no special setup
Free
This skill is fully free and open source.
Part of the AI Investment Skills Bundle — $29 one-time for the full investment analysis suite. → https://jaehyunpark.gumroad.com/l/tcyahy
Author
Built because standup prep was taking 5 minutes every morning for something that should take 5 seconds.
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
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.

