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 Debug

by wjgoarxiv in wjgoarxiv/antigravity-swarm

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

MITAuto-check passedDevelopment

Install Asw Debug

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

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

GitHub CLI
$ gh skill install wjgoarxiv/antigravity-swarm asw-debug --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-debug .claude/skills/asw-debug && 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-debug
GitHub stars
167
Token cost
~1k tokens
SKILL.md length
525 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 6 steps: Reproduce → Hypothesize → Probe → …
  • Tasks that involve Debugging
  • SKILL.md covers Hypothesis Table, Runtime Evidence, Runtime Setup and Specialist Tools, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Asw Debug is an agent skill from wjgoarxiv/antigravity-swarm. Hypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift.

Its SKILL.md is about 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 Development, covering Debugging. 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 Debugging

Example prompts

  • “/asw-debug”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Reproduce
  2. Hypothesize
  3. Probe
  4. Narrow
  5. Fix
  6. Verify

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 Debug loads about 1k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 525 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~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). 525 words, ~1,024 tokens.

Download SKILL.mdSave it as .claude/skills/asw-debug/SKILL.md (or your agent's skills folder).
name
asw-debug
description
Hypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift.

Antigravity Swarm Debug

Use this skill for real runtime failures.

  1. Reproduce the failure before explaining it.
  2. Write at least three plausible hypotheses with distinguishing evidence.
  3. Inspect runtime truth: logs, process state, debugger output, network traces, browser traces, or CLI transcripts.
  4. After two failed investigation rounds, split the search across independent subagents.
  5. Confirm root cause by toggling the suspected cause and observing the behavior change.
  6. Add or update the narrowest regression check.
  7. Fix minimally, then rerun the original reproduction through the real surface.
  8. Remove temporary debugging artifacts and report the cleanup receipt.

Hypothesis Table

Keep a small table while investigating:

HypothesisEvidence that supports itEvidence that falsifies itNext probe

Use probes that distinguish between explanations. Re-running the same failing command without a new observation is not progress.

Runtime Evidence

Choose the surface that matches the bug:

  • CLI: command transcript, exit code, stderr, config paths.
  • Web: browser screenshot, console log, network trace, route state.
  • API: request, response, status, logs, database row if relevant.
  • Desktop/IDE: visible UI state, settings file, extension/plugin registration, logs.

After the fix, rerun the original reproduction first, then the broader regression suite.

Runtime Setup

Before attaching theories to the failure, map the runtime:

  • command or UI entrypoint,
  • working directory,
  • config files read,
  • environment variables used,
  • process tree or server process,
  • logs and where they are written,
  • external services involved,
  • package or plugin install path,
  • user-visible output surface.

Capture the exact reproduction:

text
Command:
Input:
Expected:
Actual:
Exit code:
Stdout:
Stderr:
Files changed:

If the failure is intermittent, record frequency and timing. Do not collapse intermittent behavior into a single deterministic story.

Specialist Tools

Use the tool that can falsify the current hypothesis:

  • process listing for hangs,
  • logs for server or hook failures,
  • browser traces for frontend failures,
  • network traces for API failures,
  • package dry-run for missing shipped files,
  • plugin validation for Antigravity plugin failures,
  • language diagnostics for import/type failures,
  • screenshot inspection for visual failures,
  • temp install smoke for installer failures,
  • git diff for accidental behavior changes.

Do not keep rerunning the same command without a new probe.

Show full SKILL.md (188 more words)Show less

Phase Loop

Use a tight loop:

Phase 1: Reproduce
  • run the failing surface,
  • capture exact output,
  • confirm it fails now,
  • reduce the reproduction if possible.
Phase 2: Hypothesize

Write at least three plausible hypotheses. Each must have a falsifier.

Phase 3: Probe

Choose the cheapest probe that distinguishes hypotheses.

Phase 4: Narrow

Update the table. Remove falsified hypotheses. Add new hypotheses only when the evidence requires them.

Phase 5: Fix

Make the smallest change that addresses the proven cause.

Phase 6: Verify

Run:

  1. the original reproduction,
  2. the new regression check,
  3. relevant diagnostics,
  4. the real user-visible surface.

Safety Invariants

  • Do not change behavior before proving the cause.
  • Do not delete error handling to make a symptom disappear.
  • Do not weaken tests to match broken behavior.
  • Do not hide flaky failures by increasing timeouts unless timing is proven root cause.
  • Do not mutate real user config unless the task is explicitly about install/config and the path is confirmed.
  • Do not leave temporary logs, debug prints, or probe files in the final diff.
  • Do not claim root cause when the evidence only shows correlation.

Debug Report

Return:

text
DEBUG REPORT
Reproduction:
Hypotheses:
Evidence:
Root cause:
Fix:
Regression:
Verification:
Cleanup:
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-debug of wjgoarxiv/antigravity-swarm.

Open the folder on GitHubat commit a949cb8

Compare with similar skills

Asw Debug 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 Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Asw Debug this skillwjgoarxiv/antigravity-swarm167—~1kAutomated safety check: PassMIT
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Aoti Debugpytorch/pytorch104k1 repos~1.7kAutomated safety check: PassCustom licence
Herdr Throwaway Reproductionherdrdev/herdr43k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes

  • Debugging Executions

    n8n-io/n8n

    Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed

  • Herdr Throwaway Reproduction

    herdrdev/herdr

    Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.

    43k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Systematic Debugging

    ultralisp/ultralisp

    A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    258 GitHub starsUsed in 51 repos~2.4k tokens
    DevelopmentAuto-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.

    167 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed

  • Asw Cleanup

    wjgoarxiv/antigravity-swarm

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

    167 GitHub stars~1.2k 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.

    167 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.

    167 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.

    167 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.

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

Categories

Questions about Asw Debug

What does Asw Debug do?

Hypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift. Asw Debug is an agent skill from wjgoarxiv/antigravity-swarm. Hypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift.

When should I use Asw Debug?

Asw Debug fits situations like: tasks that involve Debugging.

How do I install Asw Debug in Claude Code?

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

How do I install Asw Debug in Codex?

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

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

What does Asw Debug need to run?

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

Does Asw Debug 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 Debug 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 Debug use?

Asw Debug 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 Debug use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Debug?

Skills that share tags, products or a category with Asw Debug: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Asw Debug?

wjgoarxiv (a GitHub user) maintains it in wjgoarxiv/antigravity-swarm, which has 167 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.