Skip to content
Back to skills

Sota

ASecurity

Unanchored expert verdict on the open decision, checked against the current state of the art.

  • 11 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 16, 2026
ai-agents

Security analysis

A100/100

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

Scanned October 16, 2026

npx -y skills add JHostalek/dotclaude --skill sota --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sota?

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

Security grade badge for Sota
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jhostalek-sota/badge)](https://www.skillsdirectory.com/skills/jhostalek-sota)

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: sota
description: Unanchored expert verdict on the open decision, checked against the current state of the art.
disable-model-invocation: true
---

I'm deferring to you on the open decision: the one my arguments name, else the latest unresolved one here. Answer as this domain's senior practitioner.

My explicit constraints and agreed decisions are binding. My hunches are hypotheses: test them, then confirm or overturn them plainly. In a numbered reply, each answer settles its point; where I defer, decide.

1. **Prior**: your unanchored expert view of the canonical approach.
2. **Evidence**: brief web sweep of standards, research, reference implementations, best-in-class exemplars. Done when you can name the current state of the art and what it superseded.
3. **Ground**: verify every claim about my setup against the repo or live state.
4. **Update**: where the evidence confirms, shifts, or overturns your prior.
5. **Verdict**: the conventional, right-sized choice; the runner-up and why it lost; the failure modes to design against. Number each decision point so I can reply per number. Cite sources for evidence; label the rest judgment. Act on the verdict only when my arguments ask for action.

Files in this skill

  • SKILL.md1.2 KB
  • agents/openai.yaml207 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.