New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Asw

by wjgoarxiv in wjgoarxiv/antigravity-swarm

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

MITAuto-check passedAgent Workflows

Install Asw

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

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

GitHub CLI
$ gh skill install wjgoarxiv/antigravity-swarm asw --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 .claude/skills/asw && 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
GitHub stars
166
Token cost
~1.1k tokens
SKILL.md length
558 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 7 steps: Define the observable outcome before… → Read repository guidance and the files… → Write a failing automated test for each… → …
  • Tasks that involve Subagents
  • SKILL.md covers Operating Contract, Hook Aliases, Loop Discipline and Completion Gate, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Asw is an agent skill from wjgoarxiv/antigravity-swarm. Antigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. The repository describes itself as: ::A team of AI agents to code for you.::. The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/asw”

Workflow steps

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

  1. Define the observable outcome before editing.
  2. Read repository guidance and the files that own the behavior.
  3. Write a failing automated test for each production behavior change.
  4. Implement the smallest change that makes the test pass.
  5. Run the real user-facing surface through tmux, HTTP, browser, or computer-use QA.
  6. Capture the artifact path or transcript and clean up spawned state.
  7. Use Antigravity subagents for independent research, test, or review lanes.

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 loads about 1.1k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 558 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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). 558 words, ~1,134 tokens.

Download SKILL.mdSave it as .claude/skills/asw/SKILL.md (or your agent's skills folder).
name
asw
description
Antigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA.

Antigravity Swarm Loop

Use this skill when the user asks to complete a non-trivial coding, documentation, packaging, or automation task through Antigravity CLI.

Operating Contract

  1. Define the observable outcome before editing.
  2. Read repository guidance and the files that own the behavior.
  3. Write a failing automated test for each production behavior change.
  4. Implement the smallest change that makes the test pass.
  5. Run the real user-facing surface through tmux, HTTP, browser, or computer-use QA.
  6. Capture the artifact path or transcript and clean up spawned state.
  7. Use Antigravity subagents for independent research, test, or review lanes.

Hook Aliases

The installed PreInvocation hook wakes this mode from asw, asw-loop, and swarmwork.

Loop Discipline

  • Keep a visible success contract near the top of the working notes.
  • Prefer one thin vertical slice over many half-edited files.
  • Spawn explorers for read-only mapping, librarians for current external docs, and reviewers for final verification.
  • Keep dependent edits in the main thread so file ownership stays clear.
  • When the task touches install, hooks, package contents, README, or screenshots, verify the shipped surface instead of only unit tests.
  • Stop and surface a blocker only after local discovery and at least one fallback path fail.

Completion Gate

Before saying the work is done, confirm:

  • requested behavior is present,
  • relevant tests or diagnostics passed,
  • real user-facing surface was exercised,
  • temporary state was cleaned up,
  • git/npm/package boundaries do not include private or generated material,
  • docs describe what was actually verified.

Binding Success Criteria

For non-trivial work, write a compact success contract before editing:

text
Deliverable:
Criteria:
- happy path:
- edge case:
- regression:
Tests:
- file + test id:
Manual QA:
- channel:
- command or action:
- expected observable:
Cleanup:

Each criterion needs automated evidence and real-surface evidence when users can observe the behavior. Tests are necessary; they are not the whole completion proof.

Manual QA Channels

Pick the channel that matches the surface:

  • HTTP call: API endpoints and service contracts.
  • tmux: terminal applications, installers, hooks, CLIs, and status lines.
  • Browser use: web pages and browser-visible flows.
  • Computer use: desktop or IDE surfaces.

Auxiliary checks such as parsed config dumps, package file lists, and stdout inspection are valid supporting evidence for data-shaped work. They do not replace a channel scenario when the user interacts with the surface.

Every scenario must name:

  • exact command or action,
  • concrete input,
  • expected binary pass/fail observable,
  • artifact path or transcript,
  • cleanup receipt.
Show full SKILL.md (185 more words)Show less

Durable Notepad

Keep a durable working note for complex work. Prefer .asw/ runtime state when it belongs to the workflow, or a temp note when the work should not create repo files.

Suggested sections:

text
Plan:
Success criteria + QA scenarios:
Now:
Todo:
Findings:
Learnings:
Evidence:
Cleanup:

Append updates as work progresses. Do not rewrite history in the note; add a correction when assumptions change.

Todo Discipline

Use small todos:

  • one observable criterion at a time,
  • one production edit wave at a time,
  • one active item at a time,
  • mark completion only after evidence exists.

Good todo shape:

text
path: action for criterion — verify by command/artifact

Verification Gate

Trigger a reviewer pass when the work is broad, risky, release-related, package-related, refactor-heavy, or explicitly requested as rigorous.

The reviewer must receive:

  • user goal,
  • success criteria,
  • diff,
  • tests run,
  • manual QA artifacts,
  • package/private scans,
  • residual risks.

Treat reviewer concerns as blockers until fixed or explicitly handed back to the user as a product decision.

Cleanup Receipts

Every spawned resource needs a receipt:

  • tmux session closed,
  • temp directory removed,
  • browser context closed,
  • server stopped,
  • generated preview deleted,
  • config restored or intentionally kept,
  • package tarball removed if produced.

Leftover QA state means the loop is not complete.

Final Report

Return:

text
ASW REPORT
Outcome:
Criteria:
Tests:
Manual QA:
Cleanup:
Package/private surface:
Reviewer:
Commit:
Residual risk:

© 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 of wjgoarxiv/antigravity-swarm.

Open the folder on GitHubat commit a949cb8

Compare with similar skills

Asw 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Asw this skillwjgoarxiv/antigravity-swarm166—~1.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from wjgoarxiv/antigravity-swarm

All 15 skills in this repo

  • Asw Cleanup

    wjgoarxiv/antigravity-swarm

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

    166 GitHub stars~1.2k 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

Categories

Questions about Asw

What does Asw do?

Antigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA. Asw is an agent skill from wjgoarxiv/antigravity-swarm. Antigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA.

When should I use Asw?

Asw fits situations like: tasks that involve Subagents.

How do I install Asw in Claude Code?

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

How do I install Asw in Codex?

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

Can I use Asw 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 -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, .gemini/skills/asw, .github/skills/asw and .opencode/skills/asw in your project.

What does Asw need to run?

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

Does Asw 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 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 use?

Asw 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 use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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?

Skills that share tags, products or a category with Asw: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Asw?

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.