skill-adeerkhan-vitruvius-compare · by Install
$ agentstack add skill-adeerkhan-vitruvius-compare ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-adeerkhan-vitruvius-compare) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Engineering Source Comparison
Run the shared /skill:engineering-research method with this deliverable shape. Do not restate the research loop here.
Workflow
- Plan — name the comparison set, the dimensions to evaluate, and the
expected matrix columns. Write outputs/.plans/.md. Get user confirmation before gathering.
- Scale — direct search for 2–3 items; a
researchersubagent only for a
broad set (4+ items or multi-source).
- Gather — use the discipline lens's evidence landscape. Read each source
directly before describing it; record standard + section + edition.
- Build the matrix — one row per item, columns covering:
- source (standard/URL/artifact, with section + edition)
- key claims or provisions
- evidence type (code / datasheet / test / field / secondary)
- caveats
- confidence (
verified,inferred,blocked)
- Cite — inline citations
[1],[2]; verify every source means what it
claims. Distinguish agreement, disagreement, and uncertainty clearly.
- Review — run the adversarial pass; fix FATAL issues.
Output
Save exactly one comparison to outputs/-comparison.md, ending with a Sources section of standard + section, URLs, and artifact paths for every row. For each disagreement between sources, state which is newer, which is jurisdiction/application-specific, and what a decision-maker should weigh.
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
- Source: adeerkhan/vitruvius
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.