# Architectural

> >

- **Type:** Skill
- **Install:** `agentstack add skill-adeerkhan-vitruvius-architectural`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [adeerkhan](https://agentstack.voostack.com/s/adeerkhan)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [adeerkhan](https://github.com/adeerkhan)
- **Source:** https://github.com/adeerkhan/vitruvius/tree/main/skills/architectural

## Install

```sh
agentstack add skill-adeerkhan-vitruvius-architectural
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Architectural Research

Activate the `/skill:engineering-research` method and run it with this
domain payload. Do not restate the research loop here.

## Evidence landscape

- **Codes/standards:** IBC, local adopted building codes, ADA/ABA, NFPA
  (life safety), ASHRAE (comfort/envelope), ASTM (materials), AIA
  documents. Cite section + edition, and check which edition the
  jurisdiction has adopted.
- **Primary sources:** code text and commentary, manufacturer data sheets and
  ICC-ES/Product-specific evaluation reports for assemblies, material
  property data from the issuing body, peer-reviewed building-science
  literature.
- **Prior art / practice:** documented building failures and enclosure
  forensics, post-disaster reconnaissance, trade association guidance (e.g.
  NIBS, building-science organizations), well-documented built precedents.

## Verification criteria

- **Code provisions:** verify the standard exists and read the actual
  provision; cite section + edition. Do not summarize a provision from
  memory.
- **Assembly claims:** an assembly (wall, roof, glazing) must trace to a
  named system + evaluation report or manufacturer data, not a generic
  "a curtain wall".
- **Units and conventions:** every number carries a unit (R-value vs U-value
  — know which), and the unit system is explicit.
- **Performance values:** thermal, acoustic, fire, and structural values must
  trace to a named standard/test method (ASTM C518, ASTM E90, NFPA 285, ...)
  and the result that test produced.
- **Precedent claims:** a building's attributes must be checkable against a
  named source (architect's record, journal, official project data) — do not
  infer a building's systems from a photo.
- **Sign conventions / orientation:** north arrows, sun paths, and floor
  levels must be explicit when a claim depends on them.

## Deliverable shape

Follow the method's artifact contract. In the final artifact, end with a
**Sources** section citing code + section + edition and named assemblies +
evaluation reports, marking performance values `verified`, `inferred`, or
`blocked`.

## Invocation Flags

Accept `--deep` and `--quick` flags and pass them through to the
`engineering-research` method. See that skill for flag semantics.

## Gap Detection

If research hits an evidence dead-end — no code provision, paper, or dataset
addresses the question after exhausting the discovery layers — suggest running
`/gap-analysis architectural ` to formally validate and document
the gap. Do not invoke gap-analysis automatically; offer it as a next step and
wait for the user to confirm.

## Scope and Boundaries

- This skill produces research — it does NOT produce final designs or construction documents.
- **Research-only, not for final engineering sign-off.** Licensed engineers must review and approve any design based on this research.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [adeerkhan](https://github.com/adeerkhan)
- **Source:** [adeerkhan/vitruvius](https://github.com/adeerkhan/vitruvius)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-adeerkhan-vitruvius-architectural
- Seller: https://agentstack.voostack.com/s/adeerkhan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.