Algorithmic Art with p5.js
anthropics/skills
Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.
Knowledge base for early-stage architectural design: parti development, massing studies, spatial organization and translating abstract ideas into building form.
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Abhinavbwj/Skills-Architects concept-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/concept-design .claude/skills/concept-design && rm -rf skills-srcUse ~/.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/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .claude/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Abhinavbwj/Skills-Architects concept-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/concept-design .agents/skills/concept-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .agents/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Abhinavbwj/Skills-Architects concept-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/concept-design .cursor/skills/concept-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .cursor/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Abhinavbwj/Skills-Architects.git --path skills/concept-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Abhinavbwj/Skills-Architects concept-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/concept-design .gemini/skills/concept-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .gemini/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Abhinavbwj/Skills-Architects concept-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/concept-design .github/skills/concept-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .github/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Abhinavbwj/Skills-Architects concept-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Skills-Architects.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/concept-design .opencode/skills/concept-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "concept-design" agent skill from https://github.com/Abhinavbwj/Skills-Architects/tree/main/skills/concept-design into .opencode/skills/concept-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "concept-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
concept-designKnowledge base for early-stage architectural design: parti development, massing studies, spatial organization and translating abstract ideas into building form.
This skill is a long reference for the concept phase of architectural design. It covers parti development, massing strategies, spatial organization models, concept-to-form translation and design iteration protocols. It defines a parti as the essential organizational diagram of a building and lists the traits of a strong one, such as being drawable in 30 seconds and generating both plan and section logic.
The first section presents twelve archetypal parti types, each with a diagram description, spatial characteristics, program fit, structural implications and exemplar buildings. The linear type, for example, gives typical depths and bay sizes and cites the Neue Nationalgalerie and the Kimbell Art Museum. Two reference files, parti-strategies.md and massing-methods.md, go deeper. The dimensions quoted are typical ranges, not project-specific figures.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 30a0845. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Architectural Concept Design loads about 11k tokens when it runs, and up to ~31k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 5,810 words of instructions outside code blocks.
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.
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.
The full file from Abhinavbwj/Skills-Architects at commit 30a0845, republished under its MIT licence (© Abhinavbwj). 5,810 words, ~11,246 tokens.
.claude/skills/concept-design/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Comprehensive knowledge base for architectural concept design including parti development, massing strategies, spatial organization models, concept-to-form translation, and design iteration protocols. Invoke this skill when developing early-stage design concepts, evaluating massing options, organizing spatial programs, or translating abstract design ideas into architectural form.
The parti (from French "parti pris" — a decision taken) is the essential organizational diagram of a building. It is the irreducible idea that governs the relationship between program, structure, circulation, and site. Every design decision should be traceable to the parti. If a move does not reinforce the parti, it weakens the design.
A strong parti:
Diagram: A single bar or spine — all rooms arranged along one axis. Circulation runs parallel to the primary volume.
Spatial Characteristics:
Programmatic Best-Fit: Museums and galleries (sequential viewing), hospitals (patient wings), schools (classroom wings), linear transit stations, waterfront promenades
Structural Implications: Repetitive bay structure perpendicular to the spine. Typical bay: 6-9 m wide x 6-12 m deep. Lateral stability via corridor walls or braced bays at intervals (every 30-40 m in steel, every 20-30 m in timber).
Exemplar Buildings:
Diagram: Rooms arranged around one or more enclosed open spaces. The void is the organizing principle.
Spatial Characteristics:
Programmatic Best-Fit: Housing (traditional Islamic house, European palazzo, contemporary apartment blocks), monasteries, schools, museums, offices, civic buildings
Structural Implications: Load-bearing perimeter walls or frame structure with courtyard as structural void. Corner conditions require careful resolution (corner columns or cantilevered slabs). Typical perimeter depth: 6-12 m.
Exemplar Buildings:
Diagram: Discrete volumes grouped by proximity and relationship, without a single dominant axis or center. Spaces are connected by short links or shared edges.
Spatial Characteristics:
Programmatic Best-Fit: University campuses, research parks, housing communities, primary schools, conference centers, healthcare villages
Structural Implications: Each cluster can have independent structure. Connections may be lightweight (glazed links, bridges) or substantial (shared walls). Foundation design varies per cluster, advantageous on sloping or irregular sites.
Exemplar Buildings:
Diagram: Elements radiating from a central point or core. Circulation moves outward from center to periphery or along concentric rings.
Spatial Characteristics:
Programmatic Best-Fit: Airports (central terminal with radiating concourses), hospitals (nursing hub with radiating wings), prisons (panopticon), convention centers, large-scale commercial (central food court with radiating retail wings)
Structural Implications: Central core carries vertical loads and provides lateral stability. Radiating wings can be identical (modular) or differentiated. Structural efficiency decreases at the perimeter (wider spans between radial walls). Ring beams at intersections.
Exemplar Buildings:
Diagram: A regular two-directional matrix of structural bays, typically orthogonal. Program is distributed across the grid; hierarchy emerges through selective void, double-height, or density variation.
Spatial Characteristics:
Programmatic Best-Fit: Offices (6-9 m grids), parking structures (8-10 m grids), warehouse/industrial (10-15 m grids), exhibition halls, libraries, mixed-use buildings
Structural Implications: Highly efficient — repetitive columns, beams, and floor plates. Standard grids: 6 m x 6 m (economic minimum for offices), 7.5 m x 7.5 m (popular for parking below offices), 9 m x 9 m (generous open office), 10.8 m x 10.8 m (maximum economic RC flat slab). Column sizes: 300-600 mm diameter for RC, 200-400 mm for steel, depending on load and height.
Exemplar Buildings:
Diagram: Elements rotating around a central point but not connected at center — like windmill blades or a swastika motif (in its pre-symbolic geometric sense). Four (or three) wings extending and rotating around a pivot.
Spatial Characteristics:
Programmatic Best-Fit: Houses (each wing toward different garden aspect), small cultural buildings, pavilions, visitor centers
Structural Implications: Each wing is structurally semi-independent. Central pivot point may be a column cluster or a core. Wings typically single-story or split-level. Cantilevers at wing terminations create visual dynamism.
Exemplar Buildings:
Diagram: A single rectangular volume, typically elongated (length:width > 3:1). Simpler than the linear parti — the bar is a single mass rather than rooms along a spine.
Spatial Characteristics:
Programmatic Best-Fit: Residential (apartment slabs), offices (commercial bars), laboratories (with service spine), schools (classroom bars)
Structural Implications: Repetitive cross-section. Steel or RC frame with 6-9 m bays. Lateral stability via cores at ends or intervals. For timber: CLT panels at 3.6-6 m bay spacing, typically 5-8 stories maximum.
Exemplar Buildings:
Diagram: A vertical extrusion of a compact floor plate, typically with a central or offset core. Height:width > 3:1.
Spatial Characteristics:
Programmatic Best-Fit: Offices (10-60+ stories), residential (15-80+ stories), hotels, mixed-use towers
Structural Implications: Core provides gravity and lateral resistance (RC shear walls 300-600 mm thick, or braced steel core). Perimeter frame: steel or RC columns at 3-4.5 m centers. Outrigger trusses at intervals for supertall (> 300 m). Floor plate efficiency: 70-82% net-to-gross (compact core = higher efficiency). Structural premium above 50 stories: 15-25% additional cost.
Exemplar Buildings:
Diagram: A horizontal base (podium, 2-6 stories) supporting one or more vertical towers. The podium engages the street; the tower engages the sky.
Spatial Characteristics:
Programmatic Best-Fit: Mixed-use urban development, hotels above retail, residential above commercial, transit-oriented development
Structural Implications: Transfer structure at podium-tower interface: transfer beams (1.2-3.0 m deep) or transfer plates (600-1,200 mm thick RC) redistribute tower column loads to wider podium column grids. Podium columns at 8-10 m grids for parking; tower columns at 6-9 m grids.
Exemplar Buildings:
Diagram: A central void (atrium) surrounded by occupied floors on multiple levels. The void connects all levels visually and provides daylight deep into the plan.
Spatial Characteristics:
Programmatic Best-Fit: Hotels, shopping centers, corporate headquarters, hospitals, universities, libraries, civic buildings
Structural Implications: Long-span roof structure over atrium void (steel trusses, space frames, cable-net, ETFE cushions). Floor plates cantilever or span around the void. Atrium glazing requires careful structural support (spider fittings, cable walls, or mullion systems) and smoke management (minimum 2 m smoke reservoir depth per BS 9999).
Exemplar Buildings:
Diagram: Circulation path spirals upward or outward, with program arranged along the continuous path. The ramp or helical stair is the primary spatial and structural element.
Spatial Characteristics:
Programmatic Best-Fit: Museums and galleries (continuous viewing sequence), parking garages, observation towers, religious/ceremonial buildings, exhibition pavilions
Structural Implications: Helical ramp acts as structural element (inclined slab, typically 200-300 mm RC). Central column or perimeter walls provide vertical support. Torsional loads must be resolved. Foundation receives asymmetric loads.
Exemplar Buildings:
Diagram: Floor plates at half-story offsets, connected by half-flights of stairs. The section is the primary design tool.
Spatial Characteristics:
Programmatic Best-Fit: Houses on sloping sites, small cultural buildings, retail (half-level browsing), libraries, schools
Structural Implications: Staggered floor slabs require careful structural coordination. Bearing walls at half-level offsets act as both gravity and lateral systems. Typical half-level: 1.5 m offset (for 3.0 m floor-to-floor). Foundation steps with the slope.
Exemplar Buildings:
Additive Massing: Building form generated by combining discrete volumes. Each volume is legible as a separate element. The composition is the relationship between parts.
Subtractive Massing: Building form generated by carving voids from a solid. The starting point is a maximum envelope; the final form is what remains after removals.
The relationship between occupied (solid) and unoccupied (void) space defines the character of the building:
| Solid-Void Ratio | Character | Example |
|---|---|---|
| 90% solid / 10% void | Fortress, bunker, introversion | Therme Vals (Zumthor) |
| 70% solid / 30% void | Institutional gravitas, courtyard types | Salk Institute (Kahn) |
| 50% solid / 50% void | Balanced, civic, campus types | IIT Campus (Mies) |
| 30% solid / 70% void | Open, transparent, pavilion types | Farnsworth House (Mies) |
| 10% solid / 90% void | Canopy, shelter, minimal enclosure | Serpentine Pavilions (various) |
Setbacks: Upper floors recessed from lower floors. Creates terraces, reduces perceived bulk, defines a streetwall at lower levels while allowing height above. Zoning-driven setback: New York 1916 Zoning (wedding cake massing). Design-driven setback: VIA 57 West (BIG, 2016).
Cantilevers: Volumes projecting beyond the support structure below. Creates shelter at ground level, visual drama, and architectural assertion. Structural limit for RC: 3-6 m typical; for steel: 6-15 m; for post-tensioned: up to 20 m. Example: CCTV Headquarters (OMA, 2012) — 75 m cantilever at the top connecting two leaning towers.
Terracing: Stepping the building mass with the topography or in response to solar access requirements. Each terrace creates an outdoor room for the floor below. Example: Habitat 67 — each unit has a garden on the roof of the unit below.
Stepping: Incremental vertical offsets creating a stepped profile. Responds to zoning envelopes, reduces shadow impact on neighbors, creates a varied skyline. Example: 8 House, Copenhagen (BIG, 2010) — figure-eight plan with ramping cross-section, 476 apartments.
Orientation for Passive Solar (Northern Hemisphere):
Solar Envelope (Ralph Knowles): The maximum buildable volume that will not shadow adjacent properties beyond specified limits. Defined by: latitude, time of day (typically 10:00-14:00 access required), date (winter solstice for worst case), and shadow fence height on adjacent property. Results in sloped/stepped massing that creates optimal solar access for the neighborhood.
Datum: Align key horizontal lines (cornice, string course, floor levels) with adjacent buildings. The streetwall datum creates visual continuity. Typical datum reference: adjacent cornice height (+/- 300 mm).
Cornice Alignment: Match the cornice height of neighboring buildings for the podium or lower portion. Tower elements can rise above the contextual datum if set back from the streetwall (minimum 3-6 m setback per most zoning codes).
Streetwall: Maintain a continuous building face at the property line for the lower 2-6 stories. Streetwall continuity creates comfortable pedestrian enclosure (target: > 70% of block face built to streetwall line). Gaps in the streetwall should be intentional public spaces, not residual voids.
| Criterion | Weight | Option A | Option B | Option C |
|---|---|---|---|---|
| Solar access (south facade area, m2) | 15% | |||
| Shadow impact on neighbors (hrs/day at equinox) | 10% | |||
| View capture (% units with primary view) | 10% | |||
| Wind comfort (% ground area meeting Lawson sitting) | 10% | |||
| FAR achieved (m2 GFA / site area) | 15% | |||
| Streetwall continuity (% of frontage) | 10% | |||
| Structural efficiency (estimated kg steel/m2) | 10% | |||
| Open space quality (usable outdoor m2) | 10% | |||
| Daylight factor (average across typical floor) | 10% |
Score each option 1-5 per criterion, multiply by weight, sum for total. Select the option with the highest weighted score, then refine.
Definition: A dominant central space surrounded by secondary spaces. The center is the focus; periphery is subordinate.
When to Use: Programs with a single primary gathering space — concert halls, worship spaces, legislatures, courts, sports arenas
Advantages:
Disadvantages:
Programmatic Best-Fit: Concert halls (2,000 m2 floor area at 0.7-0.9 m2/seat), courthouses (central courtroom), religious buildings (nave/sanctuary), libraries (central reading room)
Structural Implications: Long-span roof over central space (steel trusses: 30-60 m; space frame: 40-100 m; cable-net: 50-200 m). Peripheral spaces can use conventional framing. Central space volume: 6-20 m clear height depending on acoustic and programmatic requirements.
Definition: Spaces arranged in a row along a path. The path may be straight, curved, segmented, or branching.
When to Use: Programs that require sequential access — galleries, hospitals, corridors of power, processing plants
Advantages:
Disadvantages:
Programmatic Best-Fit: Museums (100-150 m maximum viewing sequence before fatigue), hospital wards (45-60 m nursing corridor maximum), schools (double-loaded corridor with 60-80 m wing lengths), airport terminals (linear concourses: 500-1,500 m with moving walkways)
Structural Implications: Repetitive bay structure. Expansion joints every 40-60 m in RC and masonry, every 60-90 m in steel (per climate — more frequent in extreme temperature ranges).
Definition: Linear arms extending outward from a central point. Combines the focus of centralized with the directionality of linear.
When to Use: Programs requiring both a central hub and directional extensions — airports, hospitals, conference centers
Advantages:
Disadvantages:
Programmatic Best-Fit: Airport terminals (central check-in, radiating concourses), hospitals (nursing hub with 3-4 wings, maximum 30 beds per wing), campuses (central commons with radiating academic buildings)
Structural Implications: Hub structure carries concentrated loads from multiple arms. Ring beams at hub perimeter distribute loads. Each arm can use independent structural systems. Differential settlement between hub and arms requires movement joints.
Definition: Groups of spaces related by proximity, shared visual or circulatory properties, or common function. No dominant axis or center.
When to Use: Programs with multiple semi-autonomous units — university departments, housing communities, research centers, healthcare villages
Advantages:
Disadvantages:
Programmatic Best-Fit: University campuses (cluster by department), housing (cluster by community group: 20-40 units per cluster per Dunbar-inspired social scaling), healthcare (cluster by patient acuity), research (cluster by discipline with shared equipment zones)
Structural Implications: Each cluster is structurally independent. Connections between clusters can be lightweight (covered walkways: steel or timber, 3-6 m wide) or substantial (shared walls). Variable foundation types per cluster (advantage on mixed soil conditions).
Definition: Spaces organized within a regular, two-dimensional framework of intersecting parallel lines. Program is distributed across grid cells.
When to Use: Programs requiring maximum flexibility, equal access, and systematic expansion — offices, laboratories, museums, storage, industrial
Advantages:
Disadvantages:
Programmatic Best-Fit: Open-plan offices (7.5-9 m grid), laboratories (3.3-3.6 m module perpendicular to lab benches, 6.6-10.8 m bay along corridor), warehouses and distribution centers (10-15 m grid), parking (7.5-8.4 m x 15-16.8 m)
Structural Implications: Highly repetitive and efficient. Standard systems: RC flat slab (spans 6-10 m, depth L/30 to L/26), steel composite (spans 9-18 m, depth L/20), CLT (spans 3.6-7.2 m, depth 140-240 mm). Column drops or capitals for punching shear in flat slabs.
Definition: Two or more organizational models combined in a single building. The hybrid responds to the reality that most complex programs cannot be served by a single model.
When to Use: Almost every building of significant complexity is a hybrid. The skill is in selecting the right combination and managing the transitions.
Common Hybrids:
Design Strategy for Hybrids:
Every architectural concept begins with an abstract idea. The challenge is translating that idea into three-dimensional form. The following eight drivers provide distinct pathways from concept to architecture.
Method: The building tells a story or embodies a metaphor. Form, material, and sequence are composed to communicate meaning.
Process: Define the narrative in one sentence. Identify the key scenes/episodes. Assign architectural moments to each episode (entry = prologue, main space = climax, exit = denouement). Select materials and light conditions that reinforce the narrative mood.
Example: Jewish Museum, Berlin (Libeskind, 2001) — the building is a narrative of absence and displacement. The zigzag plan traces the disconnected addresses of deported Jewish Berliners. Void spaces cut through all floors represent irretrievable loss. The Garden of Exile is disorienting (columns tilted 12 degrees).
Risk: Narrative can become literal or illustrative. The best narrative architecture communicates through spatial experience, not symbolism.
Method: The inherent properties of a material — its strength, weight, texture, weathering, and workability — generate the building's form and detail.
Process: Select the primary material based on site context, budget, and desired atmospheric quality. Study its structural properties (compressive strength, tensile strength, modulus). Design the structural system to express those properties. Detail connections to reveal material behavior.
Example: Therme Vals (Zumthor, 1996) — local Vals gneiss quartzite generates everything: wall thickness (600 mm composite: 2 layers of stone with insulated cavity), coursing rhythm (31/47/63 mm), bath temperatures etched into stone, even the light is filtered through stone edges.
Risk: Material fetishism — the building becomes a material sample board rather than a spatial experience.
Method: Structure is not concealed but becomes the primary architectural expression. The load path is the parti.
Process: Define the span, load, and lateral requirements. Select the structural system that most elegantly resolves these forces. Expose the structure. Detail connections as expressive moments. Celebrate the hierarchy of primary/secondary/tertiary structure.
Example: Sendai Mediatheque (Ito, 2001) — 13 seaweed-like tube-columns of bundled steel pipes support 7 flat steel plates. Structure IS the architecture — there are no walls, no hidden frames, no false ceilings.
Risk: Structural exhibitionism — complexity for its own sake. The best structural expression achieves elegance through economy.
Method: Climate, sun path, wind patterns, and site ecology generate the building's form, orientation, and envelope.
Process: Analyze the site's solar geometry (altitude/azimuth at solstices and equinoxes), prevailing winds (seasonal direction and velocity), rainfall (annual total and peak hourly), and temperature (annual range, diurnal swing). Design the section as a climate-modifying device. Optimize the envelope for thermal performance.
Example: Manitoba Hydro Place, Winnipeg (KPMB, 2009) — extreme continental climate (-35 C winter, +35 C summer). Double-skin curtain wall acts as thermal buffer. 115 m solar chimney drives stack-effect ventilation. South-facing wintergarden preheats ventilation air. Result: 60% energy reduction vs. MNECB.
Method: The relationships between program elements — adjacencies, hierarchies, separations, and flows — directly generate the building's form.
Process: Create a detailed program with areas (m2) for every space. Map adjacency requirements (must be adjacent, should be near, must be separated). Diagram circulation flows (public, staff, service, emergency). Translate the diagram into plan and section. The form is the program made spatial.
Example: Seattle Central Library (OMA/LMN, 2004) — program sorted into 5 "stable" platforms (parking, staff, meeting, book spiral, headquarters) and 4 "unstable" in-between zones (living room, mixing chamber, reading room, viewing room). Each platform is the size its program demands. The form is the section.
Method: The existing urban or landscape context — its geometries, rhythms, materials, scales, and histories — generates the new building's form.
Process: Map the site's contextual grid (street angles, parcel lines, adjacent building footprints). Identify the prevailing scale (cornice heights, floor-to-floor, facade rhythm). Study the material palette within 200 m radius. Design the new building to extend, complete, or strategically contrast with the context.
Example: Kolumba Museum, Cologne (Zumthor, 2007) — built atop the ruins of Gothic St. Kolumba church. New grey brick walls rise from the ruin fragments. Custom perforated "filter brick" creates lace-like walls over the archaeological zone. The new building is simultaneously modern and ancient.
Method: A desired experiential quality — stillness, mystery, weightlessness, warmth — drives all design decisions.
Process: Define the target atmosphere in sensory terms (not formal terms). Specify: light quality (direct/diffuse, warm/cool, 2700K/4000K), acoustic character (reverberant/absorptive, RT60 target), material temperature (warm wood/cool stone), spatial proportion (compressive/expansive). Design every element to achieve that atmosphere.
Example: Bruder Klaus Field Chapel (Zumthor, 2007) — target atmosphere: primal shelter, vertical aspiration, connection to sky. 112 tree trunks stacked as formwork, concrete poured over 24 days, trunks burned out over 3 weeks leaving charred interior. Oculus open to rain and sky. Floor of molten lead. 350 hand-blown glass orbs as light points. Every decision serves the atmosphere.
Method: The way materials are joined — the tectonics of assembly — becomes the primary design content.
Process: Select the construction method (in-situ cast, precast, prefabricated, hand-laid, CNC-cut). Design the joint vocabulary (revealed/concealed, expressed/suppressed, same-material/contrasting). Detail the hierarchy of connections: primary (structure-to-structure), secondary (structure-to-envelope), tertiary (envelope-to-finish).
Example: Castelvecchio Museum renovation (Scarpa, 1973) — every joint between new (steel, concrete) and old (stone, brick, plaster) is a meticulously detailed micro-composition. Steel brackets are expressed, not hidden. Concrete meets stone with a deliberate gap. Each material retains its identity.
START: What is the project's PRIMARY design challenge?
IF the challenge is MEANING/IDENTITY:
→ Narrative/Metaphor (Driver 1) or Contextual Response (Driver 6)
IF the challenge is CONSTRUCTION BUDGET/METHOD:
→ Material Logic (Driver 2) or Tectonic Expression (Driver 8)
IF the challenge is STRUCTURAL SPAN or INNOVATION:
→ Structural Expression (Driver 3)
IF the challenge is CLIMATE/ENERGY PERFORMANCE:
→ Environmental Response (Driver 4)
IF the challenge is COMPLEX PROGRAM with many adjacencies:
→ Programmatic Diagram (Driver 5)
IF the challenge is EXPERIENCE/ATMOSPHERE:
→ Phenomenological Intention (Driver 7)
NOTE: Select ONE primary driver and ONE secondary driver.
The primary driver generates the parti; the secondary
driver refines it. Using more than two drivers
simultaneously dilutes the concept.Develop 3-5 concept options, each exploring a different parti or primary concept driver. The purpose is not to find the "right" answer immediately but to explore the solution space and identify the strongest direction through comparison.
Phase 1: Divergent Generation (3-5 days)
For each option, produce:
Phase 2: Comparative Evaluation (1-2 days)
Score each option against the following criteria using a 1-5 scale:
| Criterion | Weight | Description |
|---|---|---|
| Program Resolution | 20% | Does the option accommodate all program areas within the area budget (+/- 5%)? Are adjacencies correct? |
| Site Response | 15% | Does the option respond to access, views, solar orientation, wind, and context? |
| Structural Feasibility | 10% | Can the option be built with available structural systems and within budget? Span limits respected? |
| Environmental Performance | 15% | Does the option enable passive strategies (daylight, ventilation, solar control)? Estimated EUI? |
| Spatial Quality | 15% | Does the option create memorable spatial experiences? Is there a clear spatial sequence? |
| Budget Alignment | 10% | Is the option achievable within the cost/m2 target? (Simple forms: lower cost; complex forms: higher cost) |
| Flexibility / Adaptability | 5% | Can the option accommodate future program changes? Is the structure adaptable? |
| Client Vision Alignment | 10% | Does the option respond to the client's stated aspirations and values? |
Phase 3: Selection and Justification (1 day)
Phase 4: Convergent Development (5-10 days)
Develop the selected option through iterative refinement:
Cycle 1 — Plan Resolution: Resolve all room layouts at 1:100. Confirm area compliance. Locate all vertical cores (stairs, elevators, risers). Confirm fire egress (maximum 45 m travel distance to exit stair in sprinklered buildings per IBC, or per local code).
Cycle 2 — Section Development: Resolve all floor-to-floor heights. Locate all MEP zones (typically 1.0-1.5 m above structural floor for office, 0.6-0.9 m for residential). Confirm key spatial volumes (double heights, atriums, feature spaces). Coordinate with structural engineer on beam depths.
Cycle 3 — Envelope and Material: Select facade system (curtain wall, rainscreen, masonry, precast, timber cladding). Confirm window-to-wall ratio (25-40% optimal for energy in temperate climates per Arup research). Select 2-3 primary materials. Develop one key detail at 1:20 (the detail that defines the building's tectonic character).
Cycle 4 — Integration: Overlay structural grid, MEP zones, and fire strategy onto the architectural plan. Resolve all conflicts. Confirm that the parti is still legible after technical integration. If technical requirements have compromised the parti, revise the technical approach rather than abandoning the concept.
At the end of each cycle, conduct a 30-minute pin-up review:
© Abhinavbwj, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in skills/concept-design of Abhinavbwj/Skills-Architects.
Open the folder on GitHubat commit 30a0845
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 Abhinavbwj/Skills-Architects, which our catalogue first saw on October 7, 2026.
Architectural Concept Design 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Architectural Concept Design this skillAbhinavbwj/Skills-Architects | 296 | 1 repos | ~11k | Automated safety check: Pass | MIT | |
| Algorithmic Art with p5.jsanthropics/skills | 180k | 38 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Canvas Designanthropics/skills | 180k | 52 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill | 134k | 1 repos | ~3.5k | Automated safety check: Pass | MIT | |
| HyperFrames Animationheygen-com/hyperframes | 59k | 3 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Slack GIF Creatoranthropics/skills | 180k | 29 repos | ~2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.
anthropics/skills
Creates original posters and static art as PNG or PDF by first writing a short design philosophy, then expressing it visually on a canvas.
nextlevelbuilder/ui-ux-pro-max-skill
Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
anthropics/skills
Provides Slack size and frame limits, Python animation helpers and validators for building animated GIFs sized for emoji and messages.
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
Abhinavbwj/Skills-Architects
Seven command-line Python calculators for early architectural checks: area and density, U-value, daylight factor, egress, structural load, energy demand and cost.
Abhinavbwj/Skills-Architects
Compares building types, from detached houses to supertall towers, using plan depth, density and efficiency metrics plus exemplar buildings.
Abhinavbwj/Skills-Architects
Guides architectural programming work: space needs, adjacency matrices, area schedules and net-to-gross checks for project briefs across common building types.
Abhinavbwj/Skills-Architects
Architectural movements, design philosophy, critical theory, precedent analysis, and compositional principles for informed design reasoning
Abhinavbwj/Skills-Architects
Architectural material properties, durability, sustainability, specification, detailing, life-cycle assessment, and material palettes for building design
Abhinavbwj/Skills-Architects
Reference for architects on IBC occupancy classification, construction types, height and area limits, egress, fire protection and plumbing fixtures, with international comparisons.
Categories
Knowledge base for early-stage architectural design: parti development, massing studies, spatial organization and translating abstract ideas into building form. This skill is a long reference for the concept phase of architectural design. It covers parti development, massing strategies, spatial organization models, concept-to-form translation and design iteration protocols.
Architectural Concept Design fits situations like: developing a parti for a new building brief; comparing massing options early in design; organizing a spatial program into a clear diagram; translating an abstract design idea into architectural form.
Run `npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a claude-code`. Or copy the skill folder (skills/concept-design in Abhinavbwj/Skills-Architects) into .claude/skills/concept-design in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a codex`. Or copy the skill folder (skills/concept-design in Abhinavbwj/Skills-Architects) into .agents/skills/concept-design in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Abhinavbwj/Skills-Architects --skill concept-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/concept-design, .gemini/skills/concept-design, .github/skills/concept-design and .opencode/skills/concept-design in your project.
SKILL.md names no scripts, command-line tools or credentials: Architectural Concept Design is instructions for the agent only.
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.
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.
Architectural Concept Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 11k tokens (SKILL.md is roughly 45k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Architectural Concept Design: Algorithmic Art with p5.js (anthropics/skills, 180k stars), Canvas Design (anthropics/skills, 180k stars), Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 134k stars) and HyperFrames Animation (heygen-com/hyperframes, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Abhinavbwj (a GitHub user) maintains it in Abhinavbwj/Skills-Architects, which has 296 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on May 20, 2026.
Source: Abhinavbwj/Skills-Architects on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.