what-did-i-get-done

An agent skill by cursor, from cursor/plugins. Tags: analysis, development, documentation, review.

What it does

Summarize authored commits over a user-specified time period into a concise update

Install

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

npx skills add cursor/plugins --skill what-did-i-get-done

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/cursor/plugins
cp -r plugins/cursor-team-kit/skills/what-did-i-get-done ~/.claude/skills/what-did-i-get-done

Safety box score

Grade A, minimal risk: 4 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 only summarizes your own git commits over a chosen time window. It does not ship code or contact external services, but it does require the agent to read local git history and your configured git identity to produce the update.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code execution are included; the skill is just a markdown workflow description.
Network access	0 (none)	The skill does not download data or send anything to remote hosts.
Filesystem reach	1 (low)	It reads local git history in the current repository: 'Read commits authored by the current git user email within that range.'
Secrets & credentials	0 (none)	It does not ask for tokens, passwords, .env files, or other secret stores.
Privilege & persistence	0 (none)	No sudo, global installs, services, or OS settings are involved.
Instruction hijack surface	0 (none)	There is no instruction to ignore rules, hide behavior, or follow remote content.
Irreversible actions	0 (none)	The skill only summarizes changes; it does not push, post, deploy, pay, or delete anything.
Transparency	0 (none)	All content is plain text markdown; there are no binaries, blobs, or hidden runtime code.

Before installing

Confirm you’re comfortable letting the agent read local git history in the repo you point it at.
Check what identity it will use by default (your git user email) if you rely on multiple accounts.
If the repo contains sensitive commit messages, run it only in a scratch clone or a non-sensitive repository.

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

Source

Repository: cursor/plugins (all skills from this repository)
Path: cursor-team-kit/skills/what-did-i-get-done/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

get-pr-comments — Fetch and summarize review comments from the active pull request
how — Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live".
principle-minimize-reader-load — Apply when reviewing or shaping code that's hard to trace.
show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
weekly-review — Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
review-walkthrough — Generates an interactive HTML walkthrough for reviewing code changes. Use only when explicitly called.