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

Gaia Architecture Comparison

by ruvnet in ruvnet/ruflo

Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap

MITAuto-check: notesDevelopment

Install Gaia Architecture Comparison

skills CLI
$ npx skills add ruvnet/ruflo --skill gaia-architecture-comparison -a claude-code

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

GitHub CLI
$ gh skill install ruvnet/ruflo gaia-architecture-comparison --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/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ruflo-workflows/skills/gaia-architecture-comparison .claude/skills/gaia-architecture-comparison && 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
gaia-architecture-comparison
GitHub stars
74k
Token cost
~1.3k tokens
SKILL.md length
506 words
Files
1
Skills in repo
265
Repo updated
First seen
Licence
MIT

At a glance

Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap

  • Works in 3 steps: Real code execution — many L2/L3… → Full question set — running 53/300 L1… → Real browser — web_browse currently…
  • Tasks that involve Architecture decision records
  • SKILL.md covers When to use, Architecture overview, Gap analysis and Improvement roadmap, plus 2 more sections
  • Calls npx

What it does

Gaia Architecture Comparison is an agent skill from ruvnet/ruflo. Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap

Its SKILL.md is about 1.3k 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 Architecture decision records. It works with Playwright and Python. The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.

When your agent uses it

  • Tasks that involve Architecture decision records

Example prompts

  • “/gaia-architecture-comparison”

Requirements

  • Python 3
  • Node.js
  • Pre-approved tools (allowed-tools): Bash, Read, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_store

Workflow steps

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

  1. Real code execution — many L2/L3 questions require running Python to
  2. Full question set — running 53/300 L1 questions underestimates true
  3. Real browser — web_browse currently fetches raw HTML. Replacing it

What it can do on your machine

Read from SKILL.md and the folder at commit 6c04654. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • mcp__plugin_ruflo-core_ruflo__memory_search
    • mcp__plugin_ruflo-core_ruflo__memory_store

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    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

Gaia Architecture Comparison loads about 1.3k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 506 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_store

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 ruvnet/ruflo at commit 6c04654, republished under its MIT licence (© ruvnet). 506 words, ~1,276 tokens.

Download SKILL.mdSave it as .claude/skills/gaia-architecture-comparison/SKILL.md (or your agent's skills folder).
name
gaia-architecture-comparison
description
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
allowed-tools
Bash, Read, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_store
argument-hint
[--focus=tools|routing|memory|cost]

GAIA Architecture Comparison Skill

Compare ruflo's GAIA benchmark harness against the Princeton HAL reference implementation and other open-source harnesses to understand capability gaps and prioritize improvements.

When to use

  • Planning the next iteration of GAIA work
  • Evaluating which architectural change has the highest pass-rate ROI
  • Onboarding a new contributor to the benchmark codebase

Architecture overview

ruflo harness (current)
gaia-bench run
  └─ gaia-loader.ts      — HF dataset download + cache
  └─ gaia-agent.ts       — multi-turn Anthropic Messages loop
       └─ gaia-tools/    — web_search, file_read, web_browse,
                           image_describe, python_exec
  └─ gaia-voting.ts      — Track A self-consistency (N attempts → majority vote)
  └─ gaia-hardness/      — Track Q difficulty predictor (ADR-136)
  └─ gaia-judge.ts       — two-stage LLM-as-judge scorer
HAL reference (Princeton)

HAL uses a similar loop but with:

  • OpenAI function calling as the tool interface
  • BrowserBase / Playwright for real browser automation
  • Code interpreter sandbox (Jupyter kernel)
  • Larger token budget per turn (4096+)
  • Full 300-question evaluation set
Key differences
DimensionrufloHAL referenceGap
Question count53 (partial L1)300 (full L1)Use --limit 165 for full L1
Web searchDuckDuckGo / Google CSEBrowserBase liveAdd Playwright or Browserless
Code executionpython_exec stubReal Jupyter kernelImplement real sandbox
Image OCRimage_describe (Gemini)GPT-4V / GeminiFunctionally equivalent
File handlingfile_readFull PDF/XLSX/ZIP parserExpand file_read
Self-consistencyvoting.ts (Track A)Not in referenceruflo advantage
Hardness routingpredictor.ts (Track Q)Not in referenceruflo advantage
MemoryAgentDB HNSWNoneruflo advantage
Pass-rate L1~20.8% (iter 23)74.6% (HAL Sonnet 4.5)~54 pp gap

Gap analysis

Primary gaps (high impact)

  1. Real code execution — many L2/L3 questions require running Python to compute a numerical answer. The current python_exec tool is a stub. Implementing a real sandbox (E2B, Pyodide, or subprocess) is the single highest-ROI change.

  2. Full question set — running 53/300 L1 questions underestimates true pass-rate because the first 53 skew easier. Run --limit 165 (full L1) for a comparable HAL score.

  3. Real browser — web_browse currently fetches raw HTML. Replacing it with Playwright/Browserless for JavaScript-rendered pages would unlock many web navigation questions.

Show full SKILL.md (226 more words)Show less
Secondary gaps (medium impact)

  1. Structured file parsing — PDF, XLSX, and ZIP attachments require dedicated parsers. file_read currently handles plain text and images only.

  2. Turn budget — 12 turns may be insufficient for complex multi-step questions. HAL uses up to 20 turns for L3.

  3. System prompt tuning — HAL's system prompt is more elaborate and explicitly instructs the model to use tools before answering.

ruflo advantages

  1. Self-consistency voting (Track A) — running N attempts per question and taking the majority answer reduces variance on borderline questions. HAL does not implement this.

  2. Hardness routing (Track Q) — routing each question to an appropriate model and turn budget based on predicted difficulty. This reduces cost on easy questions while providing more resources for hard ones.

  3. AgentDB memory — storing patterns across runs enables the agent to recall successful strategies for similar question types.

Improvement roadmap

PriorityChangeExpected LiftEffort
P0Real python_exec sandbox (E2B)+15-25 ppHigh
P0Full 165-Q L1 evaluationAccurate baselineLow
P1Playwright-based web_browse+5-10 ppMedium
P1PDF/XLSX file parser+3-8 ppMedium
P2Increase max-turns to 20 for L2/L3+2-5 ppLow
P2System prompt tuning (iter 30 research)+2-5 ppLow
P3Google Grounding via Gemini (iter 32)+3-7 ppMedium
P3Multi-provider routing (Gemini Flash for cheap Q's)Cost reductionMedium

Loading context from past research

bash
npx @claude-flow/cli@latest memory search \
  --namespace gaia-patterns \
  --query "architecture comparison HAL benchmark"

Storing comparison findings

bash
npx @claude-flow/cli@latest memory store \
  --namespace gaia-patterns \
  --key "architecture-comparison-$(date +%Y%m%d)" \
  --value "HAL gap: 54pp. Primary: python_exec stub. Secondary: browser, file parsing."

© ruvnet, 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/ruflo-workflows/skills/gaia-architecture-comparison of ruvnet/ruflo.

Open the folder on GitHubat commit 6c04654

Compare with similar skills

Gaia Architecture Comparison 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.

Gaia Architecture Comparison compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gaia Architecture Comparison this skillruvnet/ruflo74k—~1.3kAutomated safety check: NotesMIT
Merge Dependabot PRsonyx-dot-app/onyx32k1 repos~2.2kAutomated safety check: PassMIT
Design Doc MermaidSpillwaveSolutions/design-doc-mermaid1761 repos~5.6kAutomated safety check: PassNone
Drawio Diagram BuilderWill-hxw/drawio-diagram-builder413—~5.9kAutomated safety check: PassMIT
Create Vibe Featuremistralai/mistral-vibe5.1k—~1.4kAutomated safety check: PassApache-2.0
Docsbrickbots/PiFinder250—~6.2kAutomated safety check: PassGPL-3.0

Similar skills

  • Merge Dependabot PRs

    onyx-dot-app/onyx

    Triages and lands a batch of open Dependabot PRs in the Onyx repo, where main is gated exclusively by GitHub's merge queue: approves and enqueues green PRs, closes superseded duplicates, fixes…

    32k GitHub starsUsed in 1 repo~2.2k tokens
    DevelopmentAuto-check passed

  • Design Doc Mermaid

    SpillwaveSolutions/design-doc-mermaid

    Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code.

    176 GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed

  • Drawio Diagram Builder

    Will-hxw/drawio-diagram-builder

    Create, edit, replicate, and iteratively refine editable research and technical diagrams in diagrams.net/draw.io (.drawio XML) from prompts, papers, repositories, screenshots, or existing diagrams.

    413 GitHub stars~5.9k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Create Vibe Feature

    mistralai/mistral-vibe

    Official

    Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.

    5.1k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Docs

    brickbots/PiFinder

    Author and edit PiFinder's user-facing documentation in the project's house style.

    250 GitHub stars~6.2k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Reviewable Design Doc

    u-ichi/reviewable-html-workbench

    要求・設計・アーキテクチャ・未決事項を整理し、レビュー可能な設計資料HTMLを作りたい時に使う。Use this skill to structure requirements, design, architecture, alternatives, decisions, and unresolved issues into a review-ready HTML design document.

    298 GitHub starsUsed in 1 repo~8.6k tokens
    DevelopmentAuto-check passed

More from ruvnet/ruflo

All 265 skills in this repo

  • AgentDB Pattern Memory

    ruvnet/ruflo

    Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed

  • Security Audit Scanner

    ruvnet/ruflo

    Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed

  • SPARC Development Methodology

    ruvnet/ruflo

    Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed

  • Swarm Orchestration

    ruvnet/ruflo

    Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Auto-check passed

  • Ruflo Multi-Agent Orchestration

    ruvnet/ruflo

    Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed

  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

Works with

Categories

Questions about Gaia Architecture Comparison

What does Gaia Architecture Comparison do?

Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap. Gaia Architecture Comparison is an agent skill from ruvnet/ruflo.

When should I use Gaia Architecture Comparison?

Gaia Architecture Comparison fits situations like: tasks that involve Architecture decision records.

How do I install Gaia Architecture Comparison in Claude Code?

Run `npx skills add ruvnet/ruflo --skill gaia-architecture-comparison -a claude-code`. Or copy the skill folder (plugins/ruflo-workflows/skills/gaia-architecture-comparison in ruvnet/ruflo) into .claude/skills/gaia-architecture-comparison in your project. Claude Code loads it when a task matches its description.

How do I install Gaia Architecture Comparison in Codex?

Run `npx skills add ruvnet/ruflo --skill gaia-architecture-comparison -a codex`. Or copy the skill folder (plugins/ruflo-workflows/skills/gaia-architecture-comparison in ruvnet/ruflo) into .agents/skills/gaia-architecture-comparison in your project. Codex loads it when a task matches its description.

Can I use Gaia Architecture Comparison 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 ruvnet/ruflo --skill gaia-architecture-comparison -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gaia-architecture-comparison, .gemini/skills/gaia-architecture-comparison, .github/skills/gaia-architecture-comparison and .opencode/skills/gaia-architecture-comparison in your project.

What does Gaia Architecture Comparison need to run?

Going by SKILL.md and its folder, Gaia Architecture Comparison needs the command-line tools its instructions call (npx). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Bash, Read, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_store.

Does Gaia Architecture Comparison access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gaia Architecture Comparison safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Gaia Architecture Comparison use?

Gaia Architecture Comparison 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 Gaia Architecture Comparison use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Gaia Architecture Comparison?

Skills that share tags, products or a category with Gaia Architecture Comparison: Merge Dependabot PRs (onyx-dot-app/onyx, 32k stars), Design Doc Mermaid (SpillwaveSolutions/design-doc-mermaid, 176 stars), Drawio Diagram Builder (Will-hxw/drawio-diagram-builder, 413 stars) and Create Vibe Feature (mistralai/mistral-vibe, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gaia Architecture Comparison?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,222 GitHub stars. The repository holds 265 skills in this directory. The repository was last updated on October 10, 2026.

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