Skip to main content
command CX Codex

retrospective-analyzer · qdhenry — Claude Code command: what it does

retrospective-analyzer pulls sprint numbers from Linear and Git, finds problems that repeat across retros, and drafts action items with owners and dates.

no license ★ 1,357 updated 2026-03-01

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/retrospective-analyzer.md
Open on GitHub

What retrospective-analyzer does

It reads a sprint the way a team lead would: planned points against delivered, velocity, cycle time, escaped defects, how much work arrived unplanned. Git and GitHub supply the rest — commit spread, how long pull requests sit before merge, review turnaround, build success.

The flow is a set of steps. Pick the sprint, defaulting to the latest; confirm the Linear MCP connection; pull numbers and the softer signals such as review comments, commit messages and last retro's action items. Then it hunts for patterns and writes the output: a retro summary and a trend report across sprints, plus SMART actions with an owner and a date. With no Linear MCP you get Git data only, and it offers to go ahead on that, take metrics by hand, or reconnect and start over.

Sentiment comes from word lists applied to comments and commit messages, so treat it as a rough signal. A sprint still in flight gets a partial read, and the command asks before continuing.

What it helps with

  • pull sprint metrics from Linear and Git into one report
  • spot issues that keep coming back across retros
  • prepare discussion questions before a retro
  • turn retro notes into SMART actions with owners and dates
  • compare velocity and cycle time against the previous sprint

Example prompts for the agent

  • Run /retrospective-analyzer on the last sprint and show planned versus delivered points
  • Find the problems that repeated across the last five retros
  • Turn these retro notes into SMART action items with owners and dates

How to install retrospective-analyzer

Manually: put the files in place

.claude/commands/retrospective-analyzer.md

Call it with /retrospective-analyzer. For all projects use ~/.claude/commands/

Questions about retrospective-analyzer

How do I install retrospective-analyzer in Claude Code?

Place the command file at .claude/commands/retrospective-analyzer.md in your project. It then shows up among your slash commands.

What does retrospective-analyzer do?

It gathers sprint metrics from Linear and Git, looks for recurring patterns across retros, and produces a summary with suggested discussion topics and action items.

Does it need Linear?

Linear MCP supplies story points, task-level metrics and team capacity. Without that connection it falls back to Git data or to metrics you type in yourself.

Similar slash commands

All slash commands for DevOps and infrastructure →

retrospective-analyzer by other authors comes first.

retrospective-analyzer davila7 retrospective-analyzer runs retrospective analysis on sprint git commits and Linear completion data. Helps engineering teams track metrics and plan concrete action items. CX Codex +1 196installs retrospective Donchitos A skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that runs a sprint or milestone retrospective from commit history, sprint plans, and task statuses. Produces a concrete action list for the next iteration. CX Codex +1 659installs groove-utilities-memory-retrospective andreadellacorte groove-utilities-memory-retrospective summarizes workflow trends from .groove/memory/ by analyzing session ratings, mistake patterns, and recorded learnings. Helpful for weekly or monthly development check-ins. CX Codex +1 517installs iterate-retrospective product-on-purpose iterate-retrospective is a Claude Code skill that facilitates and documents team retrospectives after sprints or milestones, capturing successes, failures, and follow-up owners. CX Codex +1 832installs sprint-retrospective akillness sprint-retrospective runs a sprint or milestone retrospective and turns it into a few owned actions instead of another template ritual. CX Codex +1 365installs game-retrospective AlterLab-IEU game-retrospective — a skill for Claude Code, Codex, and Cursor that runs sprint and milestone retrospectives in GDC post-mortem fashion. Audits design decisions, cuts scope, and measures agent contributions. CX Codex +1 ★ 57repo stars gstack-openclaw-retro garrytan gstack-openclaw-retro generates weekly engineering retrospectives from git history, analyzing developer sessions, test ratios, churn hotspots, and individual contributions. CX Codex +1 314installs

From the same set112

The whole set →
typescript-pro The typescript-pro subagent designs and refactors TypeScript applications for Node.js and browsers. Use it for advanced types, architecture, testing, and large code changes. CX Codex ★ 1,357repo stars cleanup-vibes cleanup-vibes turns a vibecoded repo into something deployable: pulls hardcoded keys into .env, sorts files into folders, writes the README. CX Codex +1 ★ 1,357repo stars sync-pr-to-task sync-pr-to-task connects GitHub pull requests to Linear issues, mapping review statuses and comments bidirectionally. CX Codex +1 ★ 1,357repo stars nextjs-pro nextjs-pro — a Next.js subagent for architecture, rendering choices, SEO, testing, and performance work across an existing or new application. CX Codex ★ 1,357repo stars boundary-guardian boundary-guardian monitors reasoning boundaries and detects semantic drift to stop AI hallucinations before invalid statements occur. CX Codex ★ 1,357repo stars react-pro react-pro — a React-focused subagent for building components, refactoring code, and tackling UI problems. It examines existing project patterns and includes testing in its workflow. CX Codex ★ 1,357repo stars Linear Todo Sync Linear Todo Sync pulls your open Linear tasks through the API and writes them as a markdown todo file in the project root. Useful when you want a quick view of assigned work. CX Codex +1 ★ 1,357repo stars reasoning-validator The reasoning-validator subagent for Claude Code checks reasoning chains with WFGY formulas and quantitative metrics, helping identify logical errors in assistant reasoning. CX Codex ★ 1,357repo stars

Project sponsors

Companies that keep this analytics open