agentleFS
Sign inStart free
WanbinyuWanbinyu/ship-guard-skills/skills/dead-code-safe-delete/SKILL.md

dead-code-safe-delete

Skill1 starsChanged 3 months agoMITView on GitHub

Safely remove dead code left by agents or refactors. Use when deleting exports, unused files, or Chinese "删死代码", "unused", "安全删除". Evidence before delete.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Delete only safe set; run tests/typecheck.

    line 19
  2. Distinctive:

    If maybe: quarantine with comment or feature-owner ask — don’t guess.

    line 20
  3. Distinctive:

    Delete because “agent says unused” without search

    line 31

≈ “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

Dead Code Safe Delete

Overview

AI leaves unused helpers. Delete only with evidence of non-use; prefer small PRs.

Steps

  1. Candidate list (files/symbols).
  2. Evidence: search references, exports, dynamic imports, routes, reflection.
  3. Mark: safe-delete | maybe (dynamic) | keep.
  4. Delete only safe set; run tests/typecheck.
  5. If maybe: quarantine with comment or feature-owner ask — don’t guess.

Exit criteria

  • Evidence per candidate
  • Only safe items removed (or none)
  • Tests/typecheck plan
  • Maybes not deleted silently

Anti-patterns

  • Delete because “agent says unused” without search
  • Huge delete mix with features

Output template

## Dead code
| symbol | evidence | action |
|--------|----------|--------|
### Deleted
- ...
### Needs human
- ...

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.

Check your setup, free