Skip to content
Back to skills

Architrave Tournament

ASecurity

Explicitly compare implementation options for an Architrave run when the user requests a tournament or the lead workflow identifies architectural, security, migration, data-loss, infrastructure, runtime, or recurring-failure risk.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 24, 2026
designgosecurity

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 24, 2026

npx -y skills add dragoshont/architrave --skill architrave-tournament --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Architrave Tournament?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Architrave Tournament
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dragoshont-architrave-tournament/badge)](https://www.skillsdirectory.com/skills/dragoshont-architrave-tournament)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: architrave-tournament
description: Explicitly compare implementation options for an Architrave run when the user requests a tournament or the lead workflow identifies architectural, security, migration, data-loss, infrastructure, runtime, or recurring-failure risk.
---

Request `architrave_tournament` with the user request, numbered acceptance
criteria, governing repository sources, constraints, evidence, and unresolved
assumptions.

Require two to four options with benefits, drawbacks, blast radius, durability,
security/data risk, complexity, and verification burden. The options always
include a "do nothing" baseline and a "smallest viable" option alongside the
others, typed as `DO_NOTHING` and `SMALLEST_VIABLE`, plus `winner` and
`winnerBeatsDoNothing` (`tournament-review --result` checks the shape). Return one recommended plan, explicit non-goals, and why the chosen
option beats doing nothing. The result is advisory; it does not authorize edits
or runtime mutation.

Files in this skill

  • SKILL.md992 B
  • agents/openai.yaml236 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.