show-me-your-work

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

What it does

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

Install

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

npx skills add cursor/plugins --skill show-me-your-work

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/pstack/skills/show-me-your-work ~/.claude/skills/show-me-your-work

Safety box score

Grade B, low risk: 11 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 mainly adds a local append-only TSV trail and a Bash helper to write it, with optional commit/review workflow around that log. The main exposure is limited workspace writes plus the fact that the trail and run transcript are shared with a second model for cross-review.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It ships `scripts/log.sh`, a Bash helper that runs `mkdir -p`, `date`, `tr`, and `printf` to append rows, but it does not eval or fetch code.
Network access	1 (low)	The cross-model review step sends the audit trail and transcript to "a subagent on a different model family," so work contents leave the primary model context.
Filesystem reach	1 (low)	It writes only local artifacts like `decisions.tsv` or `.audit/<task-slug>.tsv` and reads the workspace transcript under `agent-transcripts/`.
Secrets & credentials	0 (none)	No instruction targets `.env`, keychains, browser sessions, tokens, or passwords; the helper only handles generic TSV cells.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, or shell-startup editing in the skill or helper script.
Instruction hijack surface	0 (none)	There are no instructions to ignore safeguards or follow remote content; the helper instead strips tabs/newlines and formula-leading cells.
Irreversible actions	0 (none)	It does not push, deploy, publish, pay, or delete anything; it only records decisions for later review.
Transparency	0 (none)	All shipped files are plain text (`SKILL.md`, a TSV template, and a Bash script); there are no binaries or unpinned downloads.

Before installing

Read `scripts/log.sh` to confirm the only write target is the local decision log.
Decide whether sending `agent-transcripts/` to a second model for review is acceptable in your workspace.
If you plan to commit the trail, confirm your repo policy allows committing reviewer logs.

Rated 2026-10-19 by an automated review of 3 files from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: pstack/skills/show-me-your-work/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
get-pr-comments — Fetch and summarize review comments from the active pull request
maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
principle-minimize-reader-load — Apply when reviewing or shaping code that's hard to trace.
recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).
what-did-i-get-done — Summarize authored commits over a user-specified time period into a concise update