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 Goal

by wjgoarxiv in wjgoarxiv/antigravity-swarm

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

MITAuto-check passed

Install Asw Goal

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

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

GitHub CLI
$ gh skill install wjgoarxiv/antigravity-swarm asw-goal --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-goal .claude/skills/asw-goal && 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-goal
GitHub stars
166
Token cost
~905 tokens
SKILL.md length
438 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 11 steps: Re-read the newest user request. → Re-read the goal ledger. → Pick one pending criterion. → …
  • SKILL.md covers Goal Files, Success Criteria, Manual QA channels and Ledger, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Asw Goal is an agent skill from wjgoarxiv/antigravity-swarm. Durable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit.

Its SKILL.md is about 910 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-goal”

Workflow steps

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

  1. Re-read the newest user request.
  2. Re-read the goal ledger.
  3. Pick one pending criterion.
  4. Confirm or create the RED test.
  5. Implement the smallest change.
  6. Run GREEN.
  7. Run the manual channel scenario.
  8. Capture evidence.
  9. Clean temporary state.
  10. Record pass, fail, or blocked.
  11. Continue to the next criterion.

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 Goal loads about 905 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 438 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~905

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). 438 words, ~905 tokens.

Download SKILL.mdSave it as .claude/skills/asw-goal/SKILL.md (or your agent's skills folder).
name
asw-goal
description
Durable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit.

Antigravity Swarm Goal

Use this skill when a task spans multiple turns, several deliverables, release surfaces, or strict completion criteria.

The invariant: a goal is complete only when every success criterion has current observable evidence.

Goal Files

Use .asw/goals/<slug>.md for durable local state when needed.

Keep it small:

  • original objective,
  • non-goals,
  • success criteria,
  • evidence ledger,
  • blockers,
  • cleanup receipts,
  • final audit.

Do not store secrets, private transcripts, tokens, or unnecessary personal paths.

Success Criteria

Each criterion must include:

  • id,
  • scenario,
  • expected evidence,
  • automated test or diagnostic,
  • Manual QA channels,
  • adversarial risk,
  • cleanup requirement,
  • pass/fail/block condition.

Use at least:

  • happy path,
  • edge or malformed input,
  • adjacent-surface regression,
  • package or privacy surface when distribution is involved.

Manual QA channels

Choose the channel that matches the surface:

tmux

Use for CLI, installer, terminal HUD, hook-visible behavior, and terminal menus.

Evidence:

  • command sent,
  • captured pane output,
  • cleanup receipt for the session if spawned.
HTTP

Use for APIs and local servers.

Evidence:

  • request,
  • status,
  • headers when relevant,
  • body,
  • server cleanup.
Browser

Use for web pages and README render previews when visual layout matters.

Evidence:

  • action log,
  • screenshot path,
  • browser/context cleanup.
Computer use

Use for desktop or IDE GUI behavior.

Evidence:

  • action log,
  • screenshot,
  • app/window state,
  • cleanup.

Auxiliary CLI output can support a criterion, but it does not replace the real channel for user-visible behavior.

Ledger

Record one entry per criterion attempt:

text
time:
criterion:
status: pass | fail | blocked
automated evidence:
manual channel:
artifact:
cleanup:
notes:

Never record pass without cleanup.

Execution Cycle

  1. Re-read the newest user request.
  2. Re-read the goal ledger.
  3. Pick one pending criterion.
  4. Confirm or create the RED test.
  5. Implement the smallest change.
  6. Run GREEN.
  7. Run the manual channel scenario.
  8. Capture evidence.
  9. Clean temporary state.
  10. Record pass, fail, or blocked.
  11. Continue to the next criterion.
Show full SKILL.md (150 more words)Show less

Dynamic Steering

Revise the goal only with evidence:

  • add a criterion when a real adjacent risk appears,
  • split a criterion that is too broad,
  • reorder work when dependencies are discovered,
  • mark a criterion blocked when external state prevents verification,
  • remove a criterion only when the newest user instruction changes the objective.

Do not mutate goals because the work feels hard.

Completion Audit

Before closing:

  • every criterion is pass,
  • tests and diagnostics are current,
  • manual QA artifacts exist,
  • cleanup receipts exist,
  • package/git/private boundaries are clean,
  • docs match behavior,
  • reviewer has no blockers when review is required.

Failure Handling

If the same criterion fails repeatedly:

  1. Stop editing.
  2. Record attempts.
  3. State the likely cause.
  4. Name the evidence needed.
  5. Ask for user input only when no safe local path remains.

Output

When reporting goal status:

text
Goal:
Criteria:
- id: PASS | FAIL | BLOCKED - evidence
Verification:
Manual QA:
Cleanup:
Remaining risk:
Final status:

Final Rule

Green tests are necessary evidence, not completion. The user-visible surface decides completion.

© 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-goal of wjgoarxiv/antigravity-swarm.

Open the folder on GitHubat commit a949cb8

Compare with similar skills

Asw Goal 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 Goal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Asw Goal this skillwjgoarxiv/antigravity-swarm166—~905Automated safety check: PassMIT
Goalscodewhale-hq/Codewhale41k—~273Automated safety check: PassMIT
Agent Swarmruvnet/ruflo74k2 repos~891Automated safety check: PassMIT
Swarm Initruvnet/ruflo74k—~319Automated safety check: PassMIT
Agent Release Swarmruvnet/ruflo74k2 repos~3.5kAutomated safety check: PassMIT
Agent Swarm Issueruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT

Similar skills

  • Goals

    codewhale-hq/Codewhale

    Set, review, and update the user's goals. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Agent Swarm

    ruvnet/ruflo

    Agent skill for swarm - invoke with $agent-swarm. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~891 tokens
    Agent WorkflowsAuto-check passed

  • Swarm Init

    ruvnet/ruflo

    Initialize a multi-agent swarm with anti-drift configuration.

    74k GitHub stars~319 tokensUpdated yesterday
    SecurityAuto-check passed

  • Agent Release Swarm

    ruvnet/ruflo

    Agent skill for release-swarm - invoke with $agent-release-swarm

    74k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check passed

  • Agent Swarm Issue

    ruvnet/ruflo

    Agent skill for swarm-issue - invoke with $agent-swarm-issue

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Agent WorkflowsAuto-check passed

  • Agent Goal Planner

    ruvnet/ruflo

    Agent skill for goal-planner - invoke with $agent-goal-planner

    74k GitHub starsUsed in 2 repos~842 tokens
    Auto-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 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 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 Goal

What does Asw Goal do?

Durable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit. Asw Goal is an agent skill from wjgoarxiv/antigravity-swarm. Durable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit.

How do I install Asw Goal in Claude Code?

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

How do I install Asw Goal in Codex?

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

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

What does Asw Goal need to run?

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

Does Asw Goal 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 Goal 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 Goal use?

Asw Goal 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 Goal use?

About 905 tokens (SKILL.md is roughly 3.6k 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 Goal?

Skills that share tags, products or a category with Asw Goal: Goals (codewhale-hq/Codewhale, 41k stars), Agent Swarm (ruvnet/ruflo, 74k stars), Swarm Init (ruvnet/ruflo, 74k stars) and Agent Release Swarm (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Asw Goal?

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.