Show Me Your Work

A TSV-based decision log for long-running or autonomous work that someone will review after the fact. Each row captures what was decided, why, what evidence backs it, and what happened. It lives local by default and only gets committed when the work is ambitious enough that a reviewer needs the trail to trust the result. The format is deliberately plain: GitHub renders it as a table, spreadsheets open it, and you can append rows with a one-liner. At the end of a run, you audit the log against the transcript to make sure it told the truth, then spawn a subagent on a different model to flag gaps or risky calls. It's infrastructure for unattended work where the human wasn't watching every step.

skills.sh installs: 5K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill show-me-your-work --agent claude-code

Installs into .claude/skills of the current project.

Files

Show me your work

Keep one canonical log.

The format

A single TSV file, one row per decision. Cells stay single-line. Evidence is a pointer, not prose.

Copy references/decision-log-template.tsv (the header row) to start a clean log. Columns:

ts. ISO8601 timestamp.
phase. The phase or workstream.
decision. What was chosen or done, one line.
why. The reason in plain words. If a principle drove it, say it plainly, not as a jargon tag.
evidence. A link or path that proves it: commit SHA, PR number, file:line, or an artifact, trace, or screenshot path. Never a paragraph.
result. The outcome or predicate state: tests green, reverted, pixel-diff 0, INCONCLUSIVE, open.