Diff Intake

The diff-intake skill is the first stop in an analytics instrumentation workflow, and it earns its place by doing the tedious part for you. Point it at a PR link, a branch comparison, or a raw diff and it returns a YAML change brief: classified change type, an analytics scope rating from none to high, a plain list of user-facing behavior changes, and the UI surfaces most likely to need tracking. Downstream skills consume that brief directly, so the output format matters more than the prose. The main thing to watch is the file categorization step, which relies on path heuristics; a repo with unusual layouts may need a manual check on which files count as core logic. It assumes `gh` and git are configured, so expect a bit of setup friction on a fresh machine.

skills.sh installs: 55.5K
GitHub stars: 47
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add amplitude/mcp-marketplace --skill diff-intake --agent claude-code

Installs into .claude/skills of the current project.

Files

diff-intake

Follow this skill step by step. You are step 1 of the analytics instrumentation workflow. Produce a compact YAML change brief that downstream skills (discover-event-surfaces, instrument-events) will consume. Keep the output machine-readable and precise — no prose around the YAML block.

Step 1: Gather changed files and categorize

Fetch the list of changed files from the source, then categorize each one.

Fetching changes

PR URL gh pr view <number-or-url> gh pr view <pr-number> --json files --jq '.files[] | "\(.path)\t+\(.additions) -\(.deletions)\t"'
Branch comparison git log <main|master>..<branch> git diff --stat <main|master>..<branch>
Ambiguous mention (PR number, branch name): infer the right form and fetch without asking unless auth fails.

SKILL.md on GitHub