decide — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited decide (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Capture a technical or architecture decision into Sprintra as an Architecture Decision Record.
Decision topic: $ARGUMENTS
If the user already stated the decision clearly (e.g., "let's use PostgreSQL"), proceed to Step 2.
If it's a question ("should we use X or Y?"), briefly discuss tradeoffs (3-4 bullet points per option max), then ask: "Which way do you want to go?" Once decided, proceed.
Call:
decisions(method: "add",
title: "[concise decision title]",
context: "[why this decision was needed — 2-3 sentences]",
decision: "[what was decided and how it will be implemented — 2-3 sentences]",
consequences: "[positive and negative consequences — brief]",
category: "architecture|technology|design|infrastructure|process",
status: "accepted"
)Rules:
architecture (system structure), technology (tool/library choice), design (UI/UX), infrastructure (deploy/ops), process (workflow/team)Call decisions(method: "get_conflicts") to see if this contradicts any existing decisions. If conflicts found, flag them.
Decision recorded: [title] (dec-xxxxx)
Category: [category]
Status: accepted/decide again for each.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.