architectural
Skill10 starsChanged 4 days agoMITView on GitHub
Architectural research. Use when the user invokes /architectural or asks about architectural topics — building design and building science, facade and enclosure systems, materials and assemblies, codes and accessibility, environmental performance, historic and contemporary precedents — or asks to verify an architectural claim. Dispatches to the shared engineering-research method with the architectural evidence landscape.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- artifact-readingSkill
- auditSkill
- civilSkill
- compareSkill
- design-alternativesSkill
- electricalSkill
- eli5Skill
- engineering-researchSkill
- evidence-rankingSkill
- fmea-brainstormSkill
- gap-analysisSkill
- habitSkill
- hypothesis-generationSkill
- mechanicalSkill
- peer-reviewSkill
- proposalSkill
- research-to-postSkill
- reviewSkill
- scholarly-researchSkill
- simplified-technical-englishSkill
- softwareSkill
- standards-lookupSkill
- summarizeSkill
- verifierSkill
- vitruvius-helpSkill
- vitruviusSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
Code provisions: verify the standard exists and read the actual provision.
- Distinctive: line 46
Units and conventions: every number carries a unit (R-value vs U-value — know which), and the unit system is explicit.
- Distinctive: line 59
Follow the method's artifact contract.
- Very specific: line 71
If research hits an evidence dead-end — no code provision, paper, or dataset addresses the question after exhausting the discovery layers — …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- VITRUVIUS-COMPILED-SKILL:BEGIN v1 sha256=9a376774ea8fb5ca87264250b5215962dc26160206a9b47a11e48de84ca13277 -->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 <sub-topic> 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.