work-summary
Work Summary Generator
Generate a summary of work done based on git commit history.
Arguments
<author> <start_datetime> <end_datetime> <repo1> [repo2] [repo3]...
Examples
/work-summary Alice "2026-01-08 09:00" "2026-01-09 18:00" frontend backend/work-summary "Alice Smith" "2026-01-07 09:00" "2026-01-07 18:00" .
When to use this skill
Use this skill when you need to:
- Generate work summaries for standup or status reports
- Create summaries for timesheets or billing
- Review what was accomplished in a time period
- Prepare for retrospectives or reviews
- Track work across multiple repositories
Instructions
1. Parse Arguments
If no arguments provided, ask the user for:
- Author name - Git author to filter by
- Start date/time - Format:
YYYY-MM-DD HH:MM(in local timezone) - End date/time - Format:
YYYY-MM-DD HH:MM(in local timezone) - Repository paths - Space-separated, relative to current directory or absolute paths
Example prompts:
Please provide:
- Author name: (e.g., "Alice" or "Alice Smith")
- Start time: (e.g., "2026-01-08 09:00")
- End time: (e.g., "2026-01-08 18:00")
- Repositories: (e.g., "frontend backend" or "." for current)
2. Collect Git Data
For each repository:
Get commits:
cd <repo> && git log --author="<author>" --since="<start>" --until="<end>" --pretty=format:"%h|%s"
Get stats:
cd <repo> && git log --author="<author>" --since="<start>" --until="<end>" --shortstat --pretty=format:"%h"
Notes:
- Assume the user's local timezone unless otherwise specified
- Handle relative paths (convert to absolute if needed)
- If repo doesn't exist, warn and skip it
3. Group and Categorize Commits
Group related commits into logical tasks:
- Same feature across multiple commits
- Related bug fixes
- Single refactoring effort
- Use commit message prefixes to help (feat, fix, refactor, chore, docs, test)
Categorize by size:
Large Tasks:
- New packages or major modules
- Significant new functionality with multiple components
- Major architectural changes
- Complex features spanning many files
- Examples: "Add authentication system", "Implement payment processing"
Medium Tasks:
- Feature additions to existing modules
- Substantial refactoring efforts
- Multi-file changes with moderate complexity
- API endpoint additions
- Examples: "Add user profile editing", "Refactor API error handling"
Small Tasks:
- Bug fixes
- UI tweaks and styling
- Single-file changes
- Cleanup and formatting
- Documentation updates
- Minor refactors
- Examples: "Fix typo", "Update button color", "Add JSDoc"
4. Calculate Totals
- Total commit count across all repos
- Total lines added (sum from git stats)
- Total lines deleted (sum from git stats)
- Total distinct tasks
5. Generate Output
Use this format:
## Work Summary: <start> - <end>
### Large (<count>)
1. **Task Name** (repo-name) - Brief description of what was accomplished
2. **Another Task** (repo-name) - Description
### Medium (<count>)
1. **Task Name** (repo-name) - Brief description
2. **Another Task** (repo-name) - Description
### Small (<count>)
- Fix login validation error (repo-name)
- Update dashboard styling (repo-name)
- Add API documentation (repo-name)
- Refactor utility functions (repo-name)
---
**Summary:** X commits, ~Yk lines added, ~Zk lines deleted across N distinct tasks
Formatting notes:
- Use bold for task names
- Include repo name in parentheses if multiple repos
- Round line counts to nearest thousand (e.g., ~2k, ~500)
- List small tasks as bullet points (not numbered)
- Keep descriptions concise (one line)
Examples
Example 1: With Arguments
User: "/work-summary Alice '2026-02-13 09:00' '2026-02-13 18:00' frontend"
You:
1. cd frontend
2. Run git log commands
3. Analyze commits
4. Output:
## Work Summary: 2026-02-13 09:00 - 2026-02-13 18:00
### Large (1)
1. **Add user authentication system** (frontend) - Implemented JWT-based auth with login, signup, and password reset flows
### Medium (2)
1. **Refactor API error handling** (frontend) - Standardized error responses across all endpoints
2. **Add test coverage reporting** (frontend) - Integrated coverage tools and added dashboard
### Small (5)
- Fix session timeout bug
- Update login page styling
- Add API documentation for auth endpoints
- Remove unused dependencies
- Fix TypeScript type errors
---
**Summary:** 15 commits, ~2k lines added, ~500 lines deleted across 8 distinct tasks
Example 2: Multiple Repos
User: "/work-summary 'Alice Smith' '2026-02-01 00:00' '2026-02-07 23:59' frontend backend docs"
You analyze commits across all three repos and group by task:
## Work Summary: 2026-02-01 - 2026-02-07
### Large (2)
1. **Implement CI/CD pipeline** (frontend, backend) - Set up GitHub Actions for automated testing and deployment
2. **Add real-time collaboration** (backend) - WebSocket-based live editing with conflict resolution
### Medium (3)
1. **Optimize database queries** (backend) - Added indexes and rewrote slow queries
2. **Update documentation site** (docs) - Redesigned docs with new examples
3. **Add error tracking** (frontend) - Integrated Sentry for error monitoring
### Small (8)
- Fix dashboard loading spinner (frontend)
- Update README with new features (backend)
- Add changelog for v2.1 (docs)
- Fix mobile responsive issues (frontend)
- Remove debug logging (backend)
- Update dependencies (frontend, backend)
- Fix broken links in docs (docs)
- Add code of conduct (docs)
---
**Summary:** 42 commits, ~5k lines added, ~2k lines deleted across 13 distinct tasks
Example 3: No Arguments - Interactive
User: "/work-summary"
You: "Please provide the following information:
- Author name: (e.g., 'Alice' or 'Alice Smith')
- Start date/time: (format: YYYY-MM-DD HH:MM, e.g., '2026-02-13 09:00')
- End date/time: (format: YYYY-MM-DD HH:MM, e.g., '2026-02-13 18:00')
- Repository paths: (space-separated, e.g., 'frontend backend' or '.' for current directory)"
User: "Alice, 2026-02-13 09:00, 2026-02-13 18:00, ."
You: [Process current directory as repository and generate summary]
Tips
- Smart grouping: Combine commits like "Add feature X", "Fix feature X bug", "Update feature X tests" into one task
- Use commit messages: Look for conventional commit prefixes (feat:, fix:, refactor:, etc.)
- Context matters: A 10-line change to a critical file might be "Medium", while a 100-line new test file might be "Small"
- Repo names: Only show repo names if analyzing multiple repos
- Time zones: Default to local timezone but respect user's timezone if specified
- Clarity: Make task descriptions clear and business-value focused
- Accuracy: Count lines accurately from git stats
Notes
- This skill works best with clean, descriptive commit messages
- For very large time ranges, consider summarizing by day or week
- If no commits found, clearly state that and verify the author name and date range
- Handle errors gracefully (missing repos, invalid dates, git errors)
More from supatest-ai/supa-skills
bug
Investigate, reproduce, and fix a bug using a structured workflow. Captures a complete bug report, reproduces the issue reliably, finds the true root cause, writes a failing test before fixing, verifies the fix, and optionally files a well-formed GitHub issue.
1debug-prod
Investigate a production incident or live bug. Follows mitigation-first protocol — stops the bleeding before investigating, then uses the observability funnel (metrics → traces → logs) to find root cause. Produces a structured findings report and optional postmortem.
1agent-readiness
Evaluate how ready a codebase is for autonomous AI agent work. Produces a scored report across 11 dimensions with a maturity level and prioritized action plan.
1test-feature
Interactively test a completed feature using browser automation. Navigates the live app, exercises all key flows, captures a GIF video of the happy path, and produces a visual verification report. Use after implementing a new feature or making code changes that need testing verification.
1review-pr
Review a pull request or set of code changes. Filters to issues introduced by this PR (not pre-existing), scores confidence, and produces a prioritized report with severity tiers. Requires user approval before posting anything to GitHub.
1signoz-health-check
Check broad metrics and health status of SigNoz observability platform. Shows service health, error rates, latency, recent errors, and alerts. Use when you need to monitor system health or investigate issues.
1