weekly-review
An agent skill by cursor, from cursor/plugins. Tags: analysis, development, git, planning, review.
What it does
Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill weekly-review
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/weekly-review ~/.claude/skills/weekly-review
Safety box score
Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-19. 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 reads local git metadata and commit history to generate a short weekly recap. It does not write files, contact remote services, or handle secrets; the main exposure is limited to the repository’s history and the developer identity in git config.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | It relies on git-based inspection of the repo history and config to summarize commits, but it ships no scripts and performs no arbitrary code execution. |
| Network access | 0 (none) | No remote downloads or outbound data transfers are described. |
| Filesystem reach | 1 (low) | It reads the local repository’s commit history and configuration only; there is no instruction to modify or delete files. |
| Secrets & credentials | 0 (none) | It references the git user email from repo config, but does not ask for passwords, tokens, or other credential stores. |
| Privilege & persistence | 0 (none) | No sudo, global installs, services, or OS-level configuration changes are involved. |
| Instruction hijack surface | 0 (none) | There are no instructions to ignore safeguards, follow remote content, or hide behavior. |
| Irreversible actions | 0 (none) | The skill only summarizes history; it does not push, publish, delete, or otherwise act externally. |
| Transparency | 0 (none) | The skill is plain markdown with no hidden or generated code and no unreadable assets. |
Before installing
- Read `SKILL.md` to confirm it only summarizes local commit history and does not modify the repo.
- If you need the review to work, make sure `git config user.email` is set in the target repo.
- Run it first on a non-sensitive repository if you want to verify the exact commit-selection behavior.
Rated 2026-10-19 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/weekly-review/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- run-learning-retrospective — Evaluate learning progress, identify blockers, and adjust the learning plan
- what-did-i-get-done — Summarize authored commits over a user-specified time period into a concise update
- improve-animations — Survey a codebase's animation and motion code as a senior motion advisor.
- architect — Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
- deslop — Remove AI-generated code slop and clean up code style
- figure-it-out — Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.