Agent skill

Architecture Design Guide

by wentorai in wentorai/research-plugins

Design principles of form, function, sustainability in architecture

MITAuto-check passed

Install Architecture Design Guide

skills CLI
$ npx skills add wentorai/research-plugins --skill architecture-design-guide -a claude-code

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

GitHub CLI
$ gh skill install wentorai/research-plugins architecture-design-guide --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/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/domains/business/architecture-design-guide .claude/skills/architecture-design-guide && 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
architecture-design-guide
GitHub stars
298
Used in
1 other repo
Token cost
~2.8k tokens
SKILL.md length
430 words
Files
1
Skills in repo
405
Repo updated
First seen
Licence
MIT

At a glance

Design principles of form, function, sustainability in architecture

  • SKILL.md covers Overview, Fundamental Design Principles, Structural Systems and Sustainability and Performance, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Architecture Design Guide is an agent skill from wentorai/research-plugins. Design principles of form, function, sustainability in architecture

Its SKILL.md is about 2.8k 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: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

Example prompts

  • “/architecture-design-guide”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. 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 (its code samples are python).

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

  • Network

    Links to these hosts (documentation or services it may open):

    • archdaily.com
    • ladybug.tools
    • architecture.com

    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

Architecture Design Guide loads about 2.8k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 430 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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 wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 430 words, ~2,783 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-design-guide/SKILL.md (or your agent's skills folder).
name
architecture-design-guide
description
Design principles of form, function, sustainability in architecture

Architecture Design Guide

Overview

Architectural research spans the technical, aesthetic, social, and environmental dimensions of the built environment. From structural engineering and building physics to urban theory and computational design, the discipline demands integration across multiple domains. Academic architecture research increasingly focuses on sustainability, computational methods, and evidence-based design -- areas where rigorous methodology is essential.

This guide covers the core principles that inform architectural research: the interplay of form and function, structural logic, environmental performance, and human experience. It also addresses the computational tools (BIM, parametric design, simulation) that have transformed how architects investigate and validate design decisions.

Whether you are conducting research on building performance, urban morphology, computational design methods, or the social impact of built environments, this guide provides the frameworks and tools to ground your work in established architectural theory and current best practices.

Fundamental Design Principles

The Vitruvian Triad (Updated)
Classical framework (Vitruvius, 1st century BCE):

FIRMITAS (Structural Integrity)
- Structural systems: load paths, material behavior, safety factors
- Building physics: thermal, acoustic, moisture performance
- Durability: service life, maintenance, resilience to hazards
- Modern addition: seismic, wind, and climate resilience

UTILITAS (Function)
- Program: spatial organization, adjacency requirements
- Circulation: movement patterns, wayfinding, accessibility
- Flexibility: adaptability to changing uses over time
- Modern addition: Universal design, inclusive environments

VENUSTAS (Delight)
- Proportion, rhythm, scale, materiality
- Light: natural and artificial, atmosphere, perception
- Cultural meaning: symbolism, context, identity
- Modern addition: Biophilic design, multisensory experience

Contemporary additions:
SUSTAINABILITY (since 1990s)
- Energy performance, carbon footprint, resource efficiency
- Lifecycle assessment, circular economy principles
- Passive strategies, renewable energy integration

SOCIAL RESPONSIBILITY (since 2000s)
- Equity, community engagement, participatory design
- Affordable housing, public space, social infrastructure
- Post-occupancy evaluation, evidence-based design
Design Thinking Process
PhaseActivitiesOutputs
ResearchSite analysis, precedent study, user researchBrief, program, constraints
ConceptParti development, diagramming, massingConcept diagrams, parti models
Schematic DesignSpatial organization, form developmentFloor plans, sections, elevations
Design DevelopmentMaterial selection, systems integrationDetailed drawings, specifications
DocumentationConstruction documents, specificationsBuilding permit package
Post-OccupancyPerformance monitoring, user satisfactionPOE report, design feedback

Structural Systems

Structural Logic for Researchers
Primary structural systems and their research applications:

FRAME STRUCTURES
- Material: Steel, reinforced concrete, timber
- Behavior: Moment-resisting frames, braced frames
- Research topics: Connection design, progressive collapse,
  fire resistance, seismic performance

SHELL STRUCTURES
- Types: Vaults, domes, hyperbolic paraboloids
- Behavior: Membrane forces (compression/tension), minimal bending
- Research topics: Form-finding, buckling, computational geometry
- Key method: Thrust network analysis (Block, 2009)

TENSILE STRUCTURES
- Types: Cable-stayed, membrane, tensegrity
- Behavior: Pure tension, anticlastic curvature
- Research topics: Form-finding, wind loading, material durability
- Key method: Dynamic relaxation, force density method

MASS TIMBER
- Types: CLT (cross-laminated timber), glulam, mass plywood
- Behavior: Orthotropic, fire charring provides structural reserve
- Research topics: Tall timber buildings, connections, moisture
- Growing field: embodied carbon advantages over concrete/steel
Structural Analysis Methods
python
# Simple structural analysis for research
# Finite element analysis using Python (for educational purposes)

import numpy as np

def analyze_simply_supported_beam(
    length: float,       # meters
    load: float,         # kN/m (uniform distributed load)
    E: float,            # Young's modulus (GPa)
    I: float,            # Moment of inertia (mm^4)
    n_elements: int = 20,
) -> dict:
    """
    Analyze a simply supported beam under uniform load.
    Returns deflection, moment, and shear diagrams.
    """
    x = np.linspace(0, length, n_elements + 1)
    dx = length / n_elements

    # Analytical solutions
    # Maximum moment: wL^2/8
    max_moment = load * length**2 / 8  # kN-m

    # Moment diagram: M(x) = (w*x/2)*(L-x)
    moment = (load * x / 2) * (length - x)

    # Shear diagram: V(x) = w*(L/2 - x)
    shear = load * (length / 2 - x)

    # Deflection: delta(x) = (w*x)/(24*E*I) * (L^3 - 2*L*x^2 + x^3)
    E_pa = E * 1e9  # Convert GPa to Pa
    I_m4 = I * 1e-12  # Convert mm^4 to m^4
    w_nm = load * 1e3  # Convert kN/m to N/m
    deflection = (w_nm * x) / (24 * E_pa * I_m4) * (
        length**3 - 2 * length * x**2 + x**3
    )
    max_deflection = 5 * w_nm * length**4 / (384 * E_pa * I_m4)

    return {
        "x": x,
        "moment_kNm": moment,
        "shear_kN": shear,
        "deflection_mm": deflection * 1000,
        "max_moment_kNm": max_moment,
        "max_deflection_mm": max_deflection * 1000,
        "span_to_deflection_ratio": length / max_deflection if max_deflection > 0 else float("inf"),
    }

Sustainability and Performance

Building Performance Metrics
MetricUnitBenchmark (Office)Tool
Energy Use Intensity (EUI)kWh/m2/yr< 100 (LEED Gold)EnergyPlus, IES-VE
Embodied carbonkgCO2e/m2< 500 (RIBA 2030)One Click LCA, Tally
Operational carbonkgCO2e/m2/yr< 20 (net zero target)EnergyPlus
Daylight factor%> 2% in 80% of areaRadiance, DIVA
Thermal comfortPMV/PPDPMV -0.5 to +0.5CBE Thermal Comfort Tool
Indoor air qualityCO2 ppm< 800 ppmCONTAM, CFD
Show full SKILL.md (149 more words)Show less
Passive Design Strategies
Climate-responsive design strategies:

HOT-ARID CLIMATE
- Thermal mass: Thick walls absorb daytime heat, release at night
- Courtyard typology: Microclimate creation, stack ventilation
- Shading: Deep overhangs, mashrabiya screens
- Evaporative cooling: Water features, vegetation

HOT-HUMID CLIMATE
- Cross ventilation: Openings on opposite facades
- Elevated structures: Raise above ground for air circulation
- Lightweight construction: Low thermal mass (rapid cooling)
- Solar shading: Extended roofs, louvers

COLD CLIMATE
- Compact form: Minimize surface-to-volume ratio
- Superinsulation: R-40+ walls, R-60+ roof, triple glazing
- Solar gain: South-facing glazing (N hemisphere), thermal storage
- Air tightness: < 0.6 ACH50 (Passive House standard)

TEMPERATE CLIMATE
- Mixed-mode: Natural ventilation + mechanical when needed
- Balanced glazing: Optimize daylight vs. heat gain/loss
- Thermal mass: Moderate mass with night purge ventilation
- Responsive facades: Operable shading, automated louvers

Computational Design Methods

Parametric Design with Grasshopper/Python
python
# Example: Parametric facade panel generation
# (Illustrative -- actual implementation uses Grasshopper + RhinoCommon)

import numpy as np

def generate_parametric_facade(
    width: float,
    height: float,
    panel_count_x: int,
    panel_count_y: int,
    solar_data: np.ndarray,  # Solar radiation per panel position
    min_opening: float = 0.1,
    max_opening: float = 0.8,
) -> list:
    """
    Generate facade panel openings responsive to solar radiation.
    Higher radiation = smaller opening (reduce heat gain).
    """
    panels = []
    for i in range(panel_count_x):
        for j in range(panel_count_y):
            radiation = solar_data[i, j]
            normalized = (radiation - solar_data.min()) / (solar_data.max() - solar_data.min())
            # Inverse: more sun = smaller opening
            opening_ratio = max_opening - normalized * (max_opening - min_opening)

            panels.append({
                "position": (i * width / panel_count_x, j * height / panel_count_y),
                "size": (width / panel_count_x, height / panel_count_y),
                "opening_ratio": round(opening_ratio, 3),
                "solar_radiation": round(radiation, 1),
            })
    return panels
BIM for Research
Building Information Modeling (BIM) in academic research:

APPLICATIONS:
1. Performance simulation integration (energy, daylight, acoustics)
2. Construction logistics and scheduling research
3. Facility management and digital twin studies
4. Heritage documentation and conservation
5. Parametric and generative design exploration

INTEROPERABILITY STANDARDS:
- IFC (Industry Foundation Classes): Open BIM exchange format
- gbXML: Energy simulation data exchange
- COBie: Facility management data
- CityGML: Urban-scale modeling

RESEARCH TOOLS:
- Revit + Dynamo: Parametric BIM authoring
- ArchiCAD + Grasshopper Live Connection
- BlenderBIM: Open-source BIM (IFC native)
- OpenStudio + EnergyPlus: Energy simulation
- Ladybug/Honeybee: Environmental analysis (Grasshopper)

Best Practices

  • Ground design claims in evidence. Post-occupancy evaluation and simulation results strengthen design arguments.
  • Use multiple performance metrics. Energy, daylight, thermal comfort, and embodied carbon often trade off against each other.
  • Document design rationale. The reasoning behind decisions is as important as the decisions themselves.
  • Engage with architectural theory. Computational methods are tools, not substitutes for critical thinking about space, meaning, and experience.
  • Validate simulations against measured data. Calibrated models are far more credible than uncalibrated predictions.
  • Consider the full lifecycle. Embodied carbon in materials can exceed operational carbon over 60 years.

References

  • Ching, F. D. K. (2014). Architecture: Form, Space, and Order, 4th ed. Wiley.
  • ArchDaily -- Architectural project database and analysis
  • Ladybug Tools -- Environmental analysis for Grasshopper
  • Block, P. et al. (2017). Beyond Bending: Reimagining Compression Shells. DETAIL.
  • RIBA 2030 Climate Challenge -- Carbon benchmarks

© wentorai, 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 skills/domains/business/architecture-design-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Architecture Design Guide 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.

Architecture Design Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Design Guide this skillwentorai/research-plugins2981 repos~2.8kAutomated safety check: PassMIT
Form Fillingasgeirtj/system_prompts_leaks69k—~400Automated safety check: PassCC0-1.0
Form Validationthedaviddias/Front-End-Checklist74k—~633Automated safety check: PassMIT
Form Follows Function As Axiomhashgraph-online/awesome-codex-plugins1.3k—~765Automated safety check: PassApache-2.0
Formstrycompai/comp2k—~1kAutomated safety check: PassAGPL-3.0
Form Httpsthedaviddias/Front-End-Checklist74k—~552Automated safety check: PassMIT

Similar skills

  • Form Filling

    asgeirtj/system_prompts_leaks

    Fill out online forms (Google Forms, Typeform and similar) or PDF, Word and DocuSign forms; prepare a reviewable draft and get approval before submitting or sending.

    69k GitHub stars~400 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Form Validation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Validate forms accessibly.

    74k GitHub stars~633 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Form Follows Function As Axiom

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when applying the descriptive form-follows-function interpretation — functional clarity as a source of aesthetic quality.

    1.3k GitHub stars~765 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Forms

    trycompai/comp

    A skill your agent uses when building forms - covers React Hook Form, Zod validation, and form patterns

    2k GitHub stars~1k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Form Https

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing HTML forms, fetch/XHR calls, and form action attributes to ensure data is submitted exclusively over HTTPS.

    74k GitHub stars~552 tokensUpdated 4 days ago
    Auto-check passed

More from wentorai/research-plugins

All 405 skills in this repo
  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Questions about Architecture Design Guide

What does Architecture Design Guide do?

Design principles of form, function, sustainability in architecture. Architecture Design Guide is an agent skill from wentorai/research-plugins.

How do I install Architecture Design Guide in Claude Code?

Run `npx skills add wentorai/research-plugins --skill architecture-design-guide -a claude-code`. Or copy the skill folder (skills/domains/business/architecture-design-guide in wentorai/research-plugins) into .claude/skills/architecture-design-guide in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Design Guide in Codex?

Run `npx skills add wentorai/research-plugins --skill architecture-design-guide -a codex`. Or copy the skill folder (skills/domains/business/architecture-design-guide in wentorai/research-plugins) into .agents/skills/architecture-design-guide in your project. Codex loads it when a task matches its description.

Can I use Architecture Design Guide 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 wentorai/research-plugins --skill architecture-design-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-design-guide, .gemini/skills/architecture-design-guide, .github/skills/architecture-design-guide and .opencode/skills/architecture-design-guide in your project.

What does Architecture Design Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture Design Guide is instructions for the agent only. Our summary lists: Python 3.

Does Architecture Design Guide access the network?

SKILL.md names 3 domains. As links in the text: archdaily.com, ladybug.tools and architecture.com. This is read from the text; nothing was executed.

Is Architecture Design Guide 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 Architecture Design Guide use?

Architecture Design Guide 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 Architecture Design Guide use?

About 2.8k tokens (SKILL.md is roughly 11k 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 Architecture Design Guide?

Skills that share tags, products or a category with Architecture Design Guide: Form Filling (asgeirtj/system_prompts_leaks, 69k stars), Form Validation (thedaviddias/Front-End-Checklist, 74k stars), Form Follows Function As Axiom (hashgraph-online/awesome-codex-plugins, 1.3k stars) and Forms (trycompai/comp, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Design Guide?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 405 skills in this directory. The repository was last updated on June 19, 2026.

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