prune-comments
Aggressively remove redundant comments from code files — deletes narration that restates the code, "pseudo-why" comments whose reason is already visible in…
Skill by will-wright-eng
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/will-wright-eng-prune-comments
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prune-comments
What's inside
- Skill name
prune-comments- Description
- Aggressively remove redundant comments from code files — deletes narration that restates the code, "pseudo-why" comments whose reason is already visible in the code, and step-heading comments over blocks; condenses verbose why-comments and doc comments to minimal technical language; never touches semantic comments (directives, pragmas, shebangs, license headers) or genuine why-comments. Doubt resolves toward deletion. Scopes to the diff against main (or a named base branch) by default, or sweeps a named path; optionally drives the comment ratio under a target percentage; modifies comments only, never code, and never markdown/docs. Use when comments are noisy or redundant — "remove redundant comments", "clean up the comments", "prune comments", "strip unnecessary comments", "too many AI comments", "comment ratio too high", "get comments under N%".
- License
- unknown
- Instructions
- 109 lines in SKILL.md · view on GitHub
Files (2)
- DIRECTIVES.md
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from will-wright-eng/skills
- 0.559score
blog-antipatterns
will-wright-eng
Review a markdown software blog post against Michael Lynch's "Anti-Patterns in Software Blogging" — the meandering intro and preamble, assuming the reader…
SkillAFreshness: AClaude Code +9 - 0.469score
autoresearch-method
will-wright-eng
Explain the autoresearch methodology — a verifiable autonomous experiment loop — and evaluate whether the current repo is a good fit before running the…
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-program
will-wright-eng
Generate `program.md` at the repo root from the autoresearch program template, with mutable/immutable scope and verifier commands baked in via light templating.
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-verify
will-wright-eng
Build a repo-specific verifier script for an autoresearch loop.
SkillCFreshness: CClaude Code +9 - 0.469score
distill-adrs
will-wright-eng
Distill existing implementation markdown documents (plans, design docs, RFCs) into Architecture Decision Records (ADRs).
SkillCFreshness: CClaude Code +9 - 0.469score
anneal
will-wright-eng
Decompose a god module into stable and volatile pieces whose boundaries match how the code actually changes.
SkillCFreshness: CClaude Code +9 - 0.469score
create-context
will-wright-eng
Build or refine a CONTEXT.md glossary through a question/answer session.
SkillCFreshness: CClaude Code +9 - 0.469score
design-readiness
will-wright-eng
Audit a design/implementation/proposal markdown document for consistency with the codebase and its documented context (ADRs in docs/adr/, CONTEXT.md) and…
SkillCFreshness: CClaude Code +9 - 0.445score
caveman
will-wright-eng
Ultra-compressed communication mode.
SkillCFreshness: CClaude Code +9 - 0.445score
improve-codebase-architecture
will-wright-eng
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/will-wright-eng/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from will-wright-eng
- 0.559score
blog-antipatterns
will-wright-eng
Review a markdown software blog post against Michael Lynch's "Anti-Patterns in Software Blogging" — the meandering intro and preamble, assuming the reader…
SkillAFreshness: AClaude Code +9 - 0.469score
anneal
will-wright-eng
Decompose a god module into stable and volatile pieces whose boundaries match how the code actually changes.
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-method
will-wright-eng
Explain the autoresearch methodology — a verifiable autonomous experiment loop — and evaluate whether the current repo is a good fit before running the…
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-program
will-wright-eng
Generate `program.md` at the repo root from the autoresearch program template, with mutable/immutable scope and verifier commands baked in via light templating.
SkillCFreshness: CClaude Code +9 - 0.469score
create-context
will-wright-eng
Build or refine a CONTEXT.md glossary through a question/answer session.
SkillCFreshness: CClaude Code +9 - 0.469score
design-readiness
will-wright-eng
Audit a design/implementation/proposal markdown document for consistency with the codebase and its documented context (ADRs in docs/adr/, CONTEXT.md) and…
SkillCFreshness: CClaude Code +9
Cite this page
prune-comments skill. Agent Mart. https://agentmart.dev/skills/will-wright-eng-prune-comments (last updated 2026-10-24)