Agent skill

Asw Cleanup

by wjgoarxiv in wjgoarxiv/antigravity-swarm

Remove AI-looking clutter and temporary artifacts without changing behavior.

MITAuto-check passed

Install Asw Cleanup

skills CLI
$ npx skills add wjgoarxiv/antigravity-swarm --skill asw-cleanup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wjgoarxiv/antigravity-swarm asw-cleanup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wjgoarxiv/antigravity-swarm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/antigravity-swarm/skills/asw-cleanup .claude/skills/asw-cleanup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
asw-cleanup
GitHub stars
166
Token cost
~1.2k tokens
SKILL.md length
596 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Remove AI-looking clutter and temporary artifacts without changing behavior.

  • Works in 5 steps: Remove internal notes, stale TODOs, and… → Delete dead imports, unused helpers, and… → Collapse needless wrappers only when… → …
  • SKILL.md covers Cleanup Order, Preserve, Detection Criteria and Deep Consideration, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Asw Cleanup is an agent skill from wjgoarxiv/antigravity-swarm. Remove AI-looking clutter and temporary artifacts without changing behavior.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: ::A team of AI agents to code for you.::. The licence is MIT.

Example prompts

  • “/asw-cleanup”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Remove internal notes, stale TODOs, and generated-looking prose.
  2. Delete dead imports, unused helpers, and unreachable branches.
  3. Collapse needless wrappers only when call sites remain clear.
  4. Simplify defensive checks that cannot be reached from a real boundary.
  5. Re-run the smallest relevant test after each risky file.

What it can do on your machine

Read from SKILL.md and the folder at commit a949cb8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Asw Cleanup loads about 1.2k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 596 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wjgoarxiv/antigravity-swarm at commit a949cb8, republished under its MIT licence (© wjgoarxiv). 596 words, ~1,220 tokens.

Download SKILL.mdSave it as .claude/skills/asw-cleanup/SKILL.md (or your agent's skills folder).
name
asw-cleanup
description
Remove AI-looking clutter and temporary artifacts without changing behavior.

Antigravity Swarm Cleanup

Use this skill when a file looks generated, noisy, or over-defensive.

  • Work on one file at a time unless the user asks for a broader sweep.
  • Preserve behavior unless the cleanup request explicitly includes behavior change.
  • Remove redundant comments, dead branches, stale compatibility exports, unused helpers, and debug output.
  • Keep validation at real boundaries: user input, network, filesystem, subprocesses, and external APIs.
  • Stop when cleanup would require guessing about product intent.

Cleanup Order

  1. Remove internal notes, stale TODOs, and generated-looking prose.
  2. Delete dead imports, unused helpers, and unreachable branches.
  3. Collapse needless wrappers only when call sites remain clear.
  4. Simplify defensive checks that cannot be reached from a real boundary.
  5. Re-run the smallest relevant test after each risky file.

Preserve

  • Compatibility that is still documented and tested.
  • Comments that explain non-obvious behavior.
  • Explicit validation at external boundaries.
  • User-facing copy that carries product tone.
  • Changelog, license, and attribution text that is intentionally public.

Detection Criteria

Look for specific clutter, not vibes:

Obvious Comments

Remove comments that restate the code, section dividers that add no navigation, stale notes, commented-out code, and generic TODOs with no owner or reason.

Keep:

  • comments explaining why,
  • edge-case notes,
  • ticket or issue references,
  • regex or algorithm explanation,
  • Given / When / Then test markers.
Over-Defensive Code

Consider simplifying:

  • null checks after required parsing,
  • broad catches around code that should fail loudly,
  • duplicate validation inside trusted paths,
  • compatibility branches for versions no longer supported,
  • default values for required fields,
  • wrappers that only hide errors.

Keep:

  • user input validation,
  • network and filesystem error handling,
  • subprocess error handling,
  • package/config boundary validation,
  • top-level CLI error reporting.
Spaghetti Nesting

Flag:

  • deeply nested conditionals,
  • nested ternaries,
  • boolean expressions with many unrelated predicates,
  • long functions that mix parse, IO, compute, render, and write,
  • variant chains that should be exhaustive handling.

Prefer:

  • guard clauses,
  • small pure helpers,
  • structured variants,
  • named predicates only when they clarify domain meaning.
Dead Or Temporary Code

Remove:

  • debug prints,
  • unused imports,
  • unreachable branches,
  • stale feature flags,
  • local probe scripts,
  • copied output transcripts in source,
  • temporary files from QA.
Show full SKILL.md (253 more words)Show less
Needless Abstraction

Remove only when safe:

  • pass-through wrappers,
  • single-use helpers that obscure behavior,
  • speculative interfaces,
  • factories that only call constructors,
  • config indirection with one value.

Keep abstractions that create a real boundary for testing, platform integration, package layout, or user configuration.

Deep Consideration

Before editing, ask:

  1. What behavior does this code protect?
  2. Is the behavior covered?
  3. Is this clutter or an intentional compatibility path?
  4. Is the code at a boundary?
  5. Would removing it change errors, logs, package output, or docs?
  6. Can I prove the cleanup is safe with a narrow check?

If the answer is uncertain, skip and report. The default action is preserve, not guess.

Detailed Report

For each file:

text
Cleanup Report: <file>
Scope:
Behavior lock:
Removed:
- category:
- before:
- after:
- why safe:
Preserved:
- item:
- reason:
Checks:
Residual risk:

Do not summarize cleanup as "tidied code". Say what category was removed and why behavior stayed the same.

Safety Rules

  • Preserve public APIs.
  • Preserve documented aliases.
  • Preserve config paths.
  • Preserve package contents unless package cleanup is the task.
  • Preserve validation at boundaries.
  • Preserve meaningful error messages.
  • Preserve tests that describe behavior.
  • Preserve generated assets unless regenerated through the real generator.
  • Run the smallest relevant check after risky cleanup.
  • Run package or plugin validation when cleanup touches shipped files.

Never:

  • remove code because it "looks AI-generated",
  • collapse behavior into clever one-liners,
  • delete comments explaining why,
  • remove fallback behavior without version evidence,
  • edit unrelated files during cleanup,
  • use cleanup as a hidden refactor,
  • use cleanup as a hidden feature change.

When No Clutter Is Found

Report that clearly:

text
Cleanup Report: <file>
Result: No cleanup applied.
Inspected:
- comments:
- defensive checks:
- nesting:
- dead code:
- abstractions:
Reason:
Checks:

No-op cleanup is valid when the code is already purposeful.

© wjgoarxiv, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/antigravity-swarm/skills/asw-cleanup of wjgoarxiv/antigravity-swarm.

Open the folder on GitHubat commit a949cb8

Compare with similar skills

Asw Cleanup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Asw Cleanup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Asw Cleanup this skillwjgoarxiv/antigravity-swarm166—~1.2kAutomated safety check: PassMIT
Artifacts Buildernexu-io/open-design100k—~347Automated safety check: PassApache-2.0
Web Artifacts Builderanthropics/skills180k40 repos~769Automated safety check: PassApache-2.0
Cleanupsimstudioai/sim30k—~1.4kAutomated safety check: PassApache-2.0
Web Artifacts Buildernexu-io/open-design100k—~337Automated safety check: PassApache-2.0
Web Artifacts Buildersickn33/agentic-awesome-skills47k3 repos~824Automated safety check: PassApache-2.0

Similar skills

  • Artifacts Builder

    nexu-io/open-design

    Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).

    100k GitHub stars~347 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Web Artifacts Builder

    anthropics/skills

    Official

    Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.

    180k GitHub starsUsed in 40 repos~769 tokens
    Frontend & DesignAuto-check passed
  • Cleanup

    simstudioai/sim

    Run all code quality skills — effects, memo, callbacks, state, React Query, emcn design review, url-state, comments, and test-audit — analyzing in parallel, then applying fixes sequentially

    30k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Web Artifacts Builder

    nexu-io/open-design

    Build complex claude.ai HTML artifacts with React and Tailwind.

    100k GitHub stars~337 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Web Artifacts Builder

    sickn33/agentic-awesome-skills

    To build powerful frontend claude.ai artifacts, follow these steps:

    47k GitHub starsUsed in 3 repos~824 tokens
    Frontend & DesignAuto-check passed
  • Remove AI Slops

    code-yeongyu/oh-my-openagent

    Removes AI-generated code smells from branch changes or an explicit file list behind regression tests.

    70k GitHub stars~5.3k tokensUpdated today
    Testing & QAAuto-check passed

More from wjgoarxiv/antigravity-swarm

All 15 skills in this repo
  • Asw

    wjgoarxiv/antigravity-swarm

    Antigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA.

    166 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Asw Debug

    wjgoarxiv/antigravity-swarm

    Hypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift.

    166 GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed
  • Asw Goal

    wjgoarxiv/antigravity-swarm

    Durable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit.

    166 GitHub stars~905 tokensUpdated 3 mo ago
    Auto-check passed
  • Asw Loop

    wjgoarxiv/antigravity-swarm

    Antigravity Swarm Loop executes RED to GREEN to real-surface QA with cleanup receipts.

    166 GitHub stars~824 tokensUpdated 3 mo ago
    Auto-check passed
  • Asw Plan

    wjgoarxiv/antigravity-swarm

    Antigravity Swarm Plan creates a decision-complete plan before large or ambiguous work.

    166 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Asw Refactor

    wjgoarxiv/antigravity-swarm

    Behavior-preserving Antigravity Swarm refactoring with characterization, impact mapping, diagnostics, and real-surface verification.

    166 GitHub stars~3.9k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Asw Cleanup

What does Asw Cleanup do?

Remove AI-looking clutter and temporary artifacts without changing behavior. Asw Cleanup is an agent skill from wjgoarxiv/antigravity-swarm. Remove AI-looking clutter and temporary artifacts without changing behavior.

How do I install Asw Cleanup in Claude Code?

Run `npx skills add wjgoarxiv/antigravity-swarm --skill asw-cleanup -a claude-code`. Or copy the skill folder (plugins/antigravity-swarm/skills/asw-cleanup in wjgoarxiv/antigravity-swarm) into .claude/skills/asw-cleanup in your project. Claude Code loads it when a task matches its description.

How do I install Asw Cleanup in Codex?

Run `npx skills add wjgoarxiv/antigravity-swarm --skill asw-cleanup -a codex`. Or copy the skill folder (plugins/antigravity-swarm/skills/asw-cleanup in wjgoarxiv/antigravity-swarm) into .agents/skills/asw-cleanup in your project. Codex loads it when a task matches its description.

Can I use Asw Cleanup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wjgoarxiv/antigravity-swarm --skill asw-cleanup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/asw-cleanup, .gemini/skills/asw-cleanup, .github/skills/asw-cleanup and .opencode/skills/asw-cleanup in your project.

What does Asw Cleanup need to run?

SKILL.md names no scripts, command-line tools or credentials: Asw Cleanup is instructions for the agent only.

Does Asw Cleanup access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Asw Cleanup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Asw Cleanup use?

Asw Cleanup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Asw Cleanup use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Asw Cleanup?

Skills that share tags, products or a category with Asw Cleanup: Artifacts Builder (nexu-io/open-design, 100k stars), Web Artifacts Builder (anthropics/skills, 180k stars), Cleanup (simstudioai/sim, 30k stars) and Web Artifacts Builder (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Asw Cleanup?

wjgoarxiv (a GitHub user) maintains it in wjgoarxiv/antigravity-swarm, which has 166 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on June 19, 2026.

Source: wjgoarxiv/antigravity-swarm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.