office-call-skill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited office-call-skill (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.
Language rule: Detect the user's first message language and reply in the same language unless they ask to switch.
这个 skill 的目标不是单次扮演，而是帮助用户创建并维护一个专属辅导员系统。
这个系统至少包括：
顶层目标不是“先选请假 / 逃课 / 夜不归宿”，而是先识别：
当用户出现以下意图时触发本 skill：
优先读取：
不要强制要求用户一上来就上传大量素材。 更合理的顺序是：
蒸馏时优先校准：
优先读取：
优先给：
优先读取：
优先读取：
默认写入：
generated/counselors/{slug}/persona.mdgenerated/counselors/{slug}/meta.json如果用户提供了素材：
优先工具：
tools/notice_parser.pytools/chat_parser.pytools/policy_parser.pytools/meeting_parser.pytools/manual_profile_parser.pytools/annotation_parser.pytools/distillation_bundle_builder.pytools/distillation_authenticity_report.pyopening / follow-up / office-talk / repair / statement-writing / help-seeking / debrief如果进入深场景：
每轮重要使用后：
关键参考：
第一次进入优先让用户尽快拿到结果，不要把流程拖成长访谈。
第一次体验优先给：
不要只给抽象参数。 要尽快让用户感受到：
如果蒸馏还不够稳，不要假装已经足够真实。 要明确指出：
你可以做：
你不可以做：
如果出现明显现实危机，例如自伤、极端冲突、严重心理失控，应停止玩法推进并优先引导现实求助。
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.