From dev-flow
Generate daily and weekly codebase activity summaries from Azure DevOps (PRs, work items), local git commits, and Confluence. Use when asked about "what happened", "codebase activity", "team summary", "pr summary", or to understand what's going on in a large codebase.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-flow:insightsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate activity summaries revealing what's happening in a codebase day-to-day and week-to-week.
Generate activity summaries revealing what's happening in a codebase day-to-day and week-to-week.
| Source | Tool | Data |
|---|---|---|
| Azure PRs | az repos pr list | PRs opened, merged, reviewed |
| Azure Work Items | az boards query | Tickets started, completed, in progress |
| Local Git | git log | Commits in current repo |
| Confluence | Atlassian MCP | Recently modified pages |
Run collectors from the current repository directory:
# Azure PRs (last N days)
node ${CLAUDE_SKILL_DIR}/collectors/azure-prs.js --days 7
# Azure work items (last N days)
node ${CLAUDE_SKILL_DIR}/collectors/azure-workitems.js --days 7
# Local git commits (last N days)
node ${CLAUDE_SKILL_DIR}/collectors/git-commits.js --days 7
Confluence: Search for recent pages using Atlassian MCP:
mcp__atlassian__rovo_search(query: "modified:>YYYY-MM-DD space_key")
Extract and save to .insights/raw/confluence.json:
[
{
"id": "12345",
"title": "Page Title",
"space": "SPACE",
"lastModified": "2025-01-08",
"lastModifiedBy": "Author Name",
"url": "https://..."
}
]
Data saved to .insights/raw/.
# For daily summary
node ${CLAUDE_SKILL_DIR}/collectors/filter-by-date.js .insights/raw/commits.json --day 2025-01-08
# For weekly summary
node ${CLAUDE_SKILL_DIR}/collectors/filter-by-date.js .insights/raw/commits.json --week 2025-01-08
Use templates from ${CLAUDE_SKILL_DIR}/templates/:
daily-summary.md - Daily activity reportweekly-summary.md - Weekly activity reportReports saved to .insights/:
.insights/YYYY-MM-DD-insights.md.insights/YYYY-WXX-insights.md| Command | Description |
|---|---|
/df:insights:daily [date] | Generate daily codebase summary |
/df:insights:weekly [date] | Generate weekly codebase summary |
/df:insights:catchup | Download raw data since last collection |
For monthly reviews, use the significance-based formatter:
node ${CLAUDE_SKILL_DIR}/collectors/format-review.mjs --month YYYY-MM
Or follow the templates/monthly-review.md template for AI-generated analysis focusing on:
# Azure DevOps CLI configured
az devops configure --defaults organization=https://dev.azure.com/YOUR_ORG project=YOUR_PROJECT
# Authenticated
az login
Requires Atlassian MCP server configured. During data collection, use rovo_search to find recently modified pages.
Search query format: modified:>YYYY-MM-DD [space_key] [keywords]
Collects metadata only: page title, space, last modified date, author. No full content.
Ensure Atlassian MCP is configured.
.insights/
├── raw/
│ ├── prs.json # Azure PRs
│ ├── workitems.json # Azure work items
│ ├── commits.json # Local git commits
│ └── confluence.json # Confluence pages
├── 2025-01-08-insights.md # Daily reports
└── 2025-W02-insights.md # Weekly reports
npx claudepluginhub lttr/claude-marketplace --plugin dfSummarizes recent codebase activity over a time period (default 2 weeks): features landed, fixes, refactors, focus/neglected areas, and contributor patterns. Uses git log or timewarp tools for quick catch-up.
Analyzes git commit history for engineering retrospectives, tracking work patterns, code quality metrics, trends, per-person breakdowns, shipping streaks, and actionable improvements. Use for 'retro', weekly reviews, or 'what did we ship'.
Runs weekly engineering retrospectives analyzing git commit patterns, velocity, code quality, and work sessions with persistent trend tracking.