shaping — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited shaping (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.
A thinking-partner dialogue that takes a raw idea and shapes it into a concept document. Guides you through ideating, understanding the problem, and choosing an approach — adapting the flow based on where you are.
ideating)understanding-the-ask)solutioning)Follow this sequence by default. Skip or reorder only when there's a clear signal:
Be a thinking partner, not an interviewer. The dialogue should feel like a conversation between two people shaping something together — not a checklist being worked through.
When the conversation reaches a natural conclusion, produce a concept document and save it to work/<task-id>/concept_v1.md.
Structure:
# <Concept Name>
## What
One paragraph describing what this is.
## Why
The problem or opportunity driving this.
## How
The chosen approach and key decisions made.
## Boundaries
What this is NOT. Scope limits.
## Open Questions
Unresolved items for future exploration.Present the draft to the user for approval before saving.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.