/dead-code-cleanup
Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size, or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when discussing technical debt, code hygiene, or repository maintenance.
$ npx -y skills add repowise-dev/repowise --skill dead-code-cleanup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/dead-code-cleanup
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size, or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when discussing technical debt, code hygiene, or repository maintenance.
SKILL.md
dead-code-cleanup.SKILL.mdname: dead-code-cleanup
description: >
Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size,
or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also
activates when discussing technical debt, code hygiene, or repository maintenance.
user-invocable: false
Dead Code Cleanup with Repowise
Repowise detects dead code through graph analysis — no LLM needed, works even with a template-rendered wiki.
When the user asks about dead/unused code
Call `get_dead_code()` to get findings sorted by confidence tier. Useful parameters:
- `safe_only=true` — only findings confirmed safe to delete (confidence >= 0.7)
- `kind="unreachable_file"` — files with no importers
- `kind="unused_export"` — public symbols nobody uses
- `kind="zombie_package"` — monorepo packages with no consumers
- `directory="src/old/"` — limit to a specific directory
- `tier="high"` — only high-confidence findings (>= 0.8)
- `min_confidence=0.7` — raise the floor (default is 0.5) for a release-ready cleanup
- `group_by="directory"` or `group_by="owner"` — roll up to see where the dead code concentrates and who owns the most of it
How to present findings
- Only suggest deletion for findings with `safe_to_delete: true`
- For lower-confidence findings, present them as "candidates to investigate" not "things to delete"
- Dynamically-loaded code (plugins, handlers, adapters) may appear as dead code but isn't — Repowise filters common patterns but edge cases exist
Before deleting anything
1. Confirm with the user. Present the file/symbol name, confidence score, and why Repowise thinks it's dead. 2. Call `get_risk(targets=["path/to/file"])` to double-check dependents. 3. Recently-modified "dead" code is more likely a false positive — flag this if the finding has recent git activity.
Safe deletion order
1. Unreachable files first (whole file removal, cleanest) 2. Unused internal symbols next 3. Unused exports last (highest false-positive risk due to potential dynamic imports)
Read more
name: dead-code-cleanup description: > Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size, or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when discussing technical debt, code hygiene, or repository maintenance. user-invocable: false
Dead Code Cleanup with Repowise
Repowise detects dead code through graph analysis — no LLM needed, works even with a template-rendered wiki.
When the user asks about dead/unused code
Call `get_dead_code()` to get findings sorted by confidence tier. Useful parameters:
- `safe_only=true` — only findings confirmed safe to delete (confidence >= 0.7)
- `kind="unreachable_file"` — files with no importers
- `kind="unused_export"` — public symbols nobody uses
- `kind="zombie_package"` — monorepo packages with no consumers
- `directory="src/old/"` — limit to a specific directory
- `tier="high"` — only high-confidence findings (>= 0.8)
- `min_confidence=0.7` — raise the floor (default is 0.5) for a release-ready cleanup
- `group_by="directory"` or `group_by="owner"` — roll up to see where the dead code concentrates and who owns the most of it
How to present findings
- Only suggest deletion for findings with `safe_to_delete: true`
- For lower-confidence findings, present them as "candidates to investigate" not "things to delete"
- Dynamically-loaded code (plugins, handlers, adapters) may appear as dead code but isn't — Repowise filters common patterns but edge cases exist
Before deleting anything
1. Confirm with the user. Present the file/symbol name, confidence score, and why Repowise thinks it's dead. 2. Call `get_risk(targets=["path/to/file"])` to double-check dependents. 3. Recently-modified "dead" code is more likely a false positive — flag this if the finding has recent git activity.
Safe deletion order
1. Unreachable files first (whole file removal, cleanest) 2. Unused internal symbols next 3. Unused exports last (highest false-positive risk due to potential dynamic imports)
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Repo: repowise-dev/repowise
Other skills on repowise.
- /architectural-decisions
Use when encountering questions about WHY code is built a certain way, when about to make architectural changes (new patterns, restructuring, choosing between approaches), or when the user asks about design rationale in a Repowise-indexed codebase (.repowise/ directory exists).
Open skill - /change-review
Use when reviewing a set of changes before they merge — a PR, a branch diff, or the working-tree changes you just made — in a Repowise-indexed codebase (.repowise/ directory exists). Activates for "review this PR", "is this safe to merge", "what's the blast radius of these
Open skill - /code-health
Use when the user asks about code health, code quality, complexity, technical debt, which files are risky or hard to maintain, what to refactor next, untested hotspots, or coverage gaps in a Repowise-indexed codebase (.repowise/ directory exists). Also use to get a before/after
Open skill - /codebase-exploration
Use when exploring, understanding, or answering questions about a codebase that has Repowise indexed (a .repowise/ directory in the project root). Activates for "how does X work", "explain the architecture", "where is Y implemented", "what does this module do", or any task that
Open skill - /pre-modification
Use before modifying, refactoring, or deleting files in a codebase that has Repowise indexed (indicated by a .repowise/ directory). Activates when Claude is about to edit code, especially shared utilities, core modules, or files the user didn't explicitly mention. Helps assess
Open skill - /architectural-decisions
Use when a task asks why code is built a certain way, proposes architectural changes, compares implementation approaches, or mentions decision markers such as WHY, DECISION, TRADEOFF, or ADR in a Repowise-indexed repository.
Open skill

