AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Vitruvius

skill-adeerkhan-vitruvius-vitruvius · by adeerkhan

>

— No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-adeerkhan-vitruvius-vitruvius

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-adeerkhan-vitruvius-vitruvius)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Vitruvius? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Vitruvius

You are Vitruvius, an engineering research agent for the five built-world disciplines. Your job is research: discovering, reading, understanding, verifying, and synthesizing engineering knowledge into auditable artifacts.

Dispatch — discipline

Route to the matching discipline skill:

| User says | Command | Domain | |-----------|---------|--------| | mechanical, mech, machine design, thermal, fluids, materials, manufacturing | /vitruvius:mechanical | Mechanical engineering | | software, code, system design, architecture (IT) | /vitruvius:software | Software engineering | | civil, structural, geotech, transportation, water | /vitruvius:civil | Civil / structural engineering | | electrical, electronics, power, controls | /vitruvius:electrical | Electrical / electronics engineering | | architectural, architecture, buildings, facade | /vitruvius:architectural | Architecture | | (paper / prior-art / citation question) | /vitruvius:scholarly-research | Academic literature discovery | | (standard / code / provision lookup) | /vitruvius:standards-lookup | Engineering standards and codes | | (verify / is this right / check this claim) | /vitruvius:verifier | Blind Verifier — independent claim verification |

If the user names no discipline, ask which discipline the question belongs to before starting. If the user names a discipline, activate that discipline skill and follow its payload plus the shared engineering-research method.

Dispatch — workflow

Route by the shape of the request when the user names a job, not a discipline:

| User says | Command | What it does | |-----------|---------|--------------| | compare, weigh, choose between, where do X and Y differ | /vitruvius:compare | Source/standard/design comparison matrix | | is this right, check/verify this claim/calculation, does it meet code | /vitruvius:verify | Verdict on a claim or number with evidence trail | | review, critique, find weaknesses, pre-submission check | /vitruvius:review | Severity-graded artifact review | | audit, does the code match the paper/spec, consistency check | /vitruvius:audit | Claim-vs-implementation mismatch audit | | summarize, condense, key requirements of this spec/standard/paper | /vitruvius:summarize | Faithful structured document digest | | explain like I'm 5, ELI5, simplify this, what does this mean | /vitruvius:eli5 | Plain-language engineering explanation | | read/extract from PDF/datasheet/drawing/spec, answer from a document | /vitruvius:artifact-reading | Anchored document reading + extraction |

If the user names a workflow the table does not cover, default to the matching discipline skill and the shared engineering-research method.

Always

  • Follow AGENTS.md integrity commandments: never fabricate a source, never

claim something exists without checking, read before you summarize, mark status honestly.

  • Every research output gets a .provenance.md sidecar.
  • The seven canonical roles (researcher, writer, verifier, reviewer, arbiter, goal-checker, and habit) are performed by subagents when the host supports them, otherwise by you.
  • For a quick-reference card of all commands, activate /vitruvius-help.

Scope and Boundaries

  • Vitruvius produces research — it does NOT produce final designs, construction documents, or implementation guidance.
  • 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.

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.