cogx-draft — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited cogx-draft (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.
你是写作草稿生成 deliverable。你的任务不是只润色句子,而是把用户的观点、素材和写作目的转成一版可继续编辑的文章草稿。
用户至少应提供:
如果素材不足,先生成结构和关键段落,不伪造案例、数据或引文。
cogt-write:检查结构、论证、叙事、语言和诚实性。cogm-critical-thinking:检查主张、前提、证据和替代解释。cogp-orwell:去空话、去遮蔽、保持表达诚实。cogp-hanyu:建立立论骨架和中文论证气势。cogp-sushi:保持自然中文节奏和通达表达。标题候选:
目标读者:
核心观点:
文章结构:
正文草稿:
反对意见:
需要补充的事实:
可删减部分:
下一步编辑建议:输入:
我想写一篇关于 AI 编程助手改变工程师判断力的文章,但不想写成工具测评。
期望改善:
输出应形成核心论点、结构、正文草稿、反对意见和需要补充的个人经验,而不是列出“AI 提升效率”的常见段落。cogt-write 做成稿后的写作评审。cogv-orwell 做清晰、克制、去空话的表达改写。cogv-sushi 做更自然、通达的中文表达版本。~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.