Agent skill · Code Review & Quality

retro

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill gstack-retro-caraseli02-moldovadirect --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 33 KB
Bundled scripts: none
Path: skills/analysis/gstack-retro-caraseli02-moldovadirect/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Generates a comprehensive weekly engineering retrospective analyzing commit history, work patterns, and code quality metrics. Identifies the user running the command and analyzes every contributor with per-person praise and growth opportunities.

How it works

Follows an invocation model: when the user types /retro (or with an optional time window like 24h, 14d, 30d, or compare variants), it determines the time window, aligned to local midnight for day and week units, and builds a set of git data queries against origin/<default>. It runs multiple git commands in parallel to gather:

  • All commits in the window with timestamps, subject, hash, author, files changed, insertions, deletions.
  • Per-commit test vs total LOC breakdown by author, separating test files from production files.
  • Commit timestamps for session detection and hourly distribution, with author info.
  • Files most frequently changed (hotspots).
  • PR numbers from commit messages.
  • Per-author file hotspots (who touches what).
  • Per-author commit counts.
  • Greptile triage history (if available).

The results are used to compose a narrative that contrasts the current user's commits against teammates, highlighting praise and growth opportunities.

When to use it

Use when asked for a weekly or period-specific retrospective, e.g., /retro, /retro 24h, /retro 14d, /retro 30d, /retro compare, or /retro compare 14d.

What it can touch

The skill interfaces with the local git repository and runs commands such as:

  • git fetch origin <default> --quiet
  • git config user.name
  • git config user.email
  • git log origin/<default> --since="<window>" --format="%H|%aN|%ae|%ai|%s" --shortstat
  • other git log origin/<default> --since="<window>" ... variants as listed
  • git shortlog origin/<default> --since="<window>" -sn --no-merges

Caveats

The description specifies local timezone handling and midnight alignment for windows; results depend on the repository having an origin and default branch detectable via gh queries, and on the presence of commit data within the specified window. The skill expects to run commands in parallel and build a narrative from their outputs. No outcomes are promised beyond generating the retrospective from the gathered data.

From the SKILL.md

<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs --> ## Preamble (run first) ```bash _UPD=$(~/.codex/skills/gstack/bin/gstack-update-check 2>/dev/null || .agents/skills/gstack/bin/gstack-update-check 2>/dev/null || true) [ -n "$_UPD" ] && echo "$_UPD" || true mkdir -p ~/.gstack/sessions touch ~/.gstack/sessions/"$PPID" _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ') find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true _CONTRIB=$(~/.codex/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true) _PROACTIVE=$(~/.codex/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true") _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown") echo "BRANCH: $_BRANCH" echo "PROACTIVE: $_PROACTIVE" _LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no") echo "LAKE_INTRO: $_LAKE_SEEN" _TEL=$(~/.codex/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || true) _TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no") _TEL_START=$(date +%s) _SESSION_ID="$$-$(date +%s)" echo "TELEMETRY: ${_

What's inside
Steps it walks through
  1. Preamble (run first)
  2. AskUserQuestion Format
  3. Completeness Principle — Boil the Lake
  4. Contributor Mode
  5. Completion Status Protocol
  6. Escalation
  7. Telemetry (run last)
  8. Detect default branch
  9. User-invocable
  10. Arguments
  11. Instructions
  12. Step 1: Gather Raw Data
  13. Step 2: Compute Metrics
  14. Step 3: Commit Time Distribution
Ships with 1 file
  • metadata.json
Commands it runs
mkdir -p ~/.gstack/sessions
touch ~/.gstack/sessions/"$PPID"
find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
echo "BRANCH: $_BRANCH"
echo "PROACTIVE: $_PROACTIVE"
echo "LAKE_INTRO: $_LAKE_SEEN"
echo "TELEMETRY: ${_TEL:-off}"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
mkdir -p ~/.gstack/analytics
open https://garryslist.org/posts/boil-the-ocean
More from claude-skill-registry
All skills →
About this skill
What does the retro skill do?

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill gstack-retro-caraseli02-moldovadirect --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going