How do I install the Prune skill?

Run npx skillmds@latest add domengabrovsek/prune in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prune safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prune?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prune free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

domengabrovsek (@domengabrovsek) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prune by domengabrovsek — Agent Skill

Name: Prune
Author: domengabrovsek

Prune

Reviews code exclusively for over-engineering and lists what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. Use when the user says 'review for over-engineering', 'is this over-engineered', or invokes /prune. Complements correctness-focused review; this one only hunts complexity.

File contents

If no diff is in context, fetch one first: run git diff HEAD for uncommitted changes, gh pr diff $ARGUMENTS for a PR number, or git diff main...HEAD for the current branch.

Review diffs for unnecessary complexity. One line per finding: location, what to cut, what replaces it. The diff's best outcome is getting shorter.

Format

L<line>: <tag> <what>. <replacement>., or <file>:L<line>: ... for multi-file diffs.

Tags:

delete: dead code, unused flexibility, speculative feature. Replacement: nothing.
stdlib: hand-rolled thing the standard library ships. Name the function.
native: dependency or code doing what the platform already does. Name the feature.
yagni: abstraction with one implementation, config nobody sets, layer with one caller.
shrink: same logic, fewer lines. Show the shorter form.

Examples

❌ "This EmailValidator class might be more complex than necessary, have you considered whether all these validation rules are needed at this stage?"

✅ L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.

✅ L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.

✅ repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.

✅ L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.

✅ L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.

Scoring

End with the only metric that matters: net: -<N> lines possible.

If there is nothing to cut, say Lean already. Ship. and stop.

Boundaries

why-no-hook: scope and YAGNI exceptions are subjective complexity judgments; no hook can detect that a finding belongs in a "correctness" pass versus a "complexity" pass.

Complexity only - correctness bugs, security holes, and performance go to a normal review pass, not this one (review-time: see section note)
A single smoke test or assert-based self-check is the minimum, not bloat - never flag it for deletion (review-time: see section note)
Does not apply the fixes, only lists them (review-time: see section note)

Attribution

Adapted from DietrichGebert/ponytail (MIT).

---name: prunedescription: Reviews code exclusively for over-engineering and lists what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. Use when the user says 'review for over-engineering', 'is this over-engineered', or invokes /prune. Complements correctness-focused review; this one only hunts complexity.---If no diff is in context, fetch one first: run `git diff HEAD` for uncommittedchanges, `gh pr diff $ARGUMENTS` for a PR number, or `git diff main...HEAD`for the current branch.Review diffs for unnecessary complexity. One line per finding: location, whatto cut, what replaces it. The diff's best outcome is getting shorter.## Format`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` formulti-file diffs.Tags:- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.- `stdlib:` hand-rolled thing the standard library ships. Name the function.- `native:` dependency or code doing what the platform already does. Name the feature.- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.- `shrink:` same logic, fewer lines. Show the shorter form.## Examples❌ "This EmailValidator class might be more complex than necessary, have youconsidered whether all these validation rules are needed at this stage?"✅ `L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.`✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`## ScoringEnd with the only metric that matters: `net: -<N> lines possible.`If there is nothing to cut, say `Lean already. Ship.` and stop.## Boundaries**why-no-hook:** scope and YAGNI exceptions are subjective complexity judgments; no hook can detect that a finding belongs in a "correctness" pass versus a "complexity" pass.- Complexity only - correctness bugs, security holes, and performance go to a normal review pass, not this one `(review-time: see section note)`- A single smoke test or `assert`-based self-check is the minimum, not bloat - never flag it for deletion `(review-time: see section note)`- Does not apply the fixes, only lists them `(review-time: see section note)`## AttributionAdapted from [DietrichGebert/ponytail](https://github.com/DietrichGebert/ponytail) (MIT).

Frequently asked questions