agentleFS
Vix0007Vix0007/vixero-skills/skills/surgical-diff/SKILL.md

surgical-diff

Skill1 starsChanged 7 months agoMITView on GitHub

Review a code diff for scope creep, drive-by changes, and style drift. Use when the user pastes a diff, asks "review this diff", "did I change too much", "is this change surgical", or wants to audit an AI-generated patch before merging. Returns flagged lines, scope analysis, a minimal-diff proposal, and a verdict.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After the edit, are imports / variables / functions orphaned?

    line 61
  2. Distinctive:

    Never recommend deleting pre-existing dead code unless user asked.

    line 108
  3. Distinctive:

    If stated intent is missing, do not analyze.

    line 110
  4. Distinctive:

    If the diff is under 5 lines, skip and say "too small to drift".

    line 111
  5. Distinctive:

    Never "fix" the diff yourself.

    line 115

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

surgical-diff

Audit a diff against its stated intent. Every changed line must trace to the request.

Trigger on

  • "review this diff"
  • "is this surgical"
  • "did I change too much"
  • "audit this patch"
  • "scope-check this PR"
  • User pastes a diff plus a statement of what the change was supposed to do

Input shapes

shapehandling
unified diff + stated intentfull analysis
diff only, no intentask for intent first, do not guess
file-before + file-aftertreat as implicit diff
PR description + diffextract intent from description
commit message + diffextract intent from subject line

Analysis passes

Pass 1 — scope trace

For each changed line: does this line solve the stated request? Mark yes / no / indirect.

Pass 2 — drift detection

Universal drift flags:

drift typeexamples
stylequote style changes, whitespace, trailing commas
type theatretype hints added to unrelated functions
doc theatredocstrings added to unrelated functions
renamevariable / function renames not required by fix
scope creepnew features adjacent to the fix
unauthorized deletepre-existing dead code removed
dependency creepnew import not needed by the fix
test theatreunrelated tests added alongside the fix

Language-specific drift:

languageflag when you see
Pythonf-string conversion of unrelated % or .format() lines; list → List type annotation backport on unrelated functions
TypeScriptany → specific type on unrelated signatures; interface → type or reverse
JavaScriptvar → const/let on unrelated lines; function → arrow on unrelated
Goerror wrap reformat on unrelated errors; interface{} → any swap on unrelated
Rustunwrap() → ? conversion on unrelated call sites
Javavar local-type inference backport on unrelated locals

Pass 3 — orphan check

After the edit, are imports / variables / functions orphaned?

orphan typeaction
Import your edit orphanedremove
Variable your edit orphanedremove
Function your edit orphanedremove
Orphan that pre-existedleave. flag only if user asks about it

Output

stated intent: {one line}
lines changed: {n}
lines tracing to intent: {n} ({pct}%)

drift flags:
  style: {line numbers}
  type-theatre: {line numbers}
  doc-theatre: {line numbers}
  rename: {line numbers}
  scope-creep: {line numbers + description}
  unauthorized-delete: {line numbers}
  dependency-creep: {line numbers}
  language-specific: {type + line numbers}
  orphans-created: {list — remove}
  orphans-untouched: {list — leave, informational}

minimal diff (only lines tracing to intent):
```diff
{the subset}

verdict: {surgical | minor drift | scope creep | rewrite needed} reasoning: {one line}


## Verdict thresholds

| tracing % | verdict |
|-----------|---------|
| ≥ 95 | surgical |
| 80–94 | minor drift (acceptable with flags) |
| 50–79 | scope creep (split into multiple PRs) |
| < 50 | rewrite needed (start from stated intent again) |

## Hard rules
- Never recommend deleting pre-existing dead code unless user asked.
- Style drift is a flag, not an error. Flag it, let the user decide.
- If stated intent is missing, do not analyze. Ask for it first.
- If the diff is under 5 lines, skip and say "too small to drift".
- Type hints on NEW code do not flag. Type hints added to UNRELATED code do.
- Tests added that cover the stated fix do NOT flag. Tests unrelated to the fix do.
- Whitespace-only diffs (reformat commits) are flagged as their own category — suggest splitting into a separate PR.
- Never "fix" the diff yourself. Report and propose. The user decides.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.