gstack-openclaw-retro

An agent skill by garrytan, from garrytan/gstack. Tags: analytics, code-quality, review, tracking, trend-analysis.

What it does

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware with per-person contributions, praise, and growth areas. Use when asked for weekly retro, what shipped this week, or engineering retrospective.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add garrytan/gstack --skill gstack-openclaw-retro

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/garrytan/gstack
cp -r gstack/openclaw/skills/gstack-openclaw-retro ~/.claude/skills/gstack-openclaw-retro

Safety box score

Grade B, low risk: 14 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a local git-history analyzer that fetches `origin/main`, reads commit metadata, and saves a retrospective snapshot under `memory/`. The main risks are bounded network access to the configured remote, broad exposure of repository history and author identity, and automatic persistence of the generated retro on disk.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It drives a series of shell/git commands such as `git fetch`, `git log`, `git shortlog`, and `git ls-files`, but it does not run arbitrary code or shipped binaries.
Network access	1 (low)	It contacts the configured remote with `git fetch origin main --quiet`, which downloads repository data but only from the existing git remote.
Filesystem reach	1 (low)	It reads the repo history and writes a persistent snapshot to `memory/retro-YYYY-MM-DD.json`, but does not call for edits outside the workspace.
Secrets & credentials	0 (none)	It reads `git config user.name` and `git config user.email` plus commit author emails, but it does not target tokens, passwords, `.env` files, or key stores.
Privilege & persistence	0 (none)	There is no `sudo`, service installation, shell startup modification, or other privileged system change.
Instruction hijack surface	0 (none)	The skill text does not ask the agent to ignore instructions, follow remote prompt text, or hide actions.
Irreversible actions	1 (low)	It automatically generates and saves a retro snapshot (`memory/retro-YYYY-MM-DD.json`) without a human approval step, but it does not post, deploy, pay, or delete anything.
Transparency	0 (none)	The file is plain markdown with explicit commands; there are no binaries, base64 blobs, or opaque installers.

Before installing

Confirm `origin` points to the repo you expect before allowing `git fetch origin main`.
Decide whether it is acceptable for the skill to read and display `git config user.email` and commit author emails.
Check that `memory/retro-*.json` is a place you want persistent retro history written locally.
Run it once in a scratch clone to see the command volume and whether the output matches your privacy expectations.

Rated 2026-10-16 by an automated review of 1 file from the skill's repository.

Source

Repository: garrytan/gstack (all skills from this repository)
Path: openclaw/skills/gstack-openclaw-retro/SKILL.md
Branch: main
Updated: 2026-10-05

retro — Weekly engineering retrospective. (gstack)
analytics — When the user wants to set up, improve, or audit analytics tracking and measurement.
attribution — When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model.
caveman-stats — Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.
code-improver — Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names.
deslop — Remove AI-generated code slop and clean up code style