feature — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited feature (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.
The orchestrated path for building a new feature, from idea to PR-ready. This skill is a thin dispatcher — it confirms intent and hands off. Each downstream skill activates on its own.
You want the full SDD pipeline in order without having to remember each step.
diagnose instead.interview-to-spec, spec-approach, tdd, verify).You will pass through these stages in order:
spec/<slug>.md (Goal, Behaviors, Acceptance criteria, Out of scope, Edge cases).If yes, invoke spec-approach to append ## Approach to the spec. If no, skip and move on.
.agents/tdd/test-command.txt is configured on first run, and its Stop hook will gate on green tests + a pass through simplify.tdd until clean. Will not return until the verdict is Ready.Ready, hand off for code review. Then open the PR.This skill ends as soon as you invoke interview-to-spec. It does not stay active across the pipeline. Each downstream skill activates from its own trigger phrasing as the conversation progresses.
If you stop the session midway and resume later, invoke the next stage's skill directly — do not re-invoke feature.
Confirm the user's intent in one sentence ("Kicking off the feature workflow for <short-description>."), then immediately invoke interview-to-spec. Do not attempt the interview yourself — that is interview-to-spec's job.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.