team-level — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited team-level (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.
When this skill is invoked:
Decision Points: At each step transition, use AskUserQuestion to present the user with the subagent's proposals as selectable options. Write the agent's full analysis in conversation, then capture the decision with concise labels. The user must approve before moving to the next step.
tutorial,forest dungeon, hub town, final boss arena).
design/gdd/game-concept.mddesign/gdd/game-pillars.mddesign/levels/design/narrative/Use the Task tool to spawn each team member as a subagent:
subagent_type: narrative-director — Narrative purpose, characters, emotional arcsubagent_type: world-builder — Lore context, environmental storytelling, world rulessubagent_type: level-designer — Spatial layout, pacing, encounters, navigationsubagent_type: systems-designer — Enemy compositions, loot tables, difficulty balancesubagent_type: art-director — Visual theme, color palette, lighting, asset requirementssubagent_type: qa-tester — Test cases, boundary testing, playtest checklistAlways provide full context in each agent's prompt (game concept, pillars, existing level docs, narrative docs).
Spawn the narrative-director agent to:
Spawn the world-builder agent to:
Spawn the level-designer agent to:
Spawn the systems-designer agent to:
Spawn the art-director agent to:
Spawn the qa-tester agent to:
level design template format.
design/levels/[level-name].md.list, narrative beats, and any cross-team dependencies or open questions.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.