simonepri/ifttt-lint / .agents/skills/diff
diff
VerifiedFetch and display diffs for various scopes (PR, commit, branch, staged, working tree). Used by other skills that need to analyze changes.
Diff
Fetch a diff based on the input scope.
Scope detection
$ARGUMENTS determines the scope. Auto-detect the type:
| Input | Diff command |
|---|---|
A PR number (e.g., 123) | gh pr diff 123 |
| A commit SHA (7-40 hex chars) | git diff {sha}~1 {sha} |
A commit range (a..b) | git diff a b |
| A branch name | git diff {base}...{branch} (detect base: gh pr view --json baseRefName -q .baseRefName 2>/dev/null, fall back to main) |
staged or pending | git diff --staged |
current or empty | git diff HEAD |
If empty and the working tree is clean, fall back to the current branch vs main.
Output
Write the diff to a temp file and read it with the Read tool — diffs frequently exceed inline output limits.
If reviewing a PR, also read the PR description. If reviewing a commit, also read the commit messages.
Provide a report of the diffs:
Title: Description: Size: <size (XS|S|M|L|XL|XXL)> Diffs:
Size guidelines:
| Size | Lines | Files | Review complexity |
|---|---|---|---|
| XS | < 50 | 1-2 | Trivial: minor typos, documentation, or config tweaks |
| S | 50-200 | 3-5 | Ideal: single bug fix or small, focused feature |
| M | 200-400 | 6-10 | Standard: complete feature or logical refactor |
| L | 400-1k | 11-20 | Warning: high cognitive load, reviewers may start skimming |
| XL | 1k-2k | 20+ | Critical: likely needs to be split into smaller, independent PRs |
| XXL | 2k+ | 50+ | Dangerous: defect detection drops significantly |
Use whichever dimension gives the larger size (e.g., 3 files but 500 lines = L).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |