.claude/skills/quillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
结构化长文写作框架:把模糊的写作意图整理成有核心论点、证据、受众、风格的长文,不绑定特定 harness。当用户要写博客、通讯、论文、专栏或任何非虚构长文,想把零散想法整理成有论点有证据的文章,或已有草稿却理不清主线时使用——只要意图是把想法变成有论点的长文就应激活本 skill,即使用户没明说「写文章」。不用于小说/诗歌/剧本等虚构创作或邮件/评论/即时消息等短文本。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/quillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/quillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/quillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @cgartlab/cgartlab-quillclawhub inspect @cgartlab/cgartlab-quill --version 0.13.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
curl | bashThis is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:0cda2851f7aa62ae5340caf8a39a17dbfe0ea394ea934e39252d414f7f260cfdAGENTS.mdassets/examples/sample-article/_index.mdassets/examples/sample-article/ai-draft.mdassets/examples/sample-article/audience.mdassets/examples/sample-article/claim.mdassets/examples/sample-article/draft.mdassets/examples/sample-article/evidence.mdassets/examples/sample-article/style.mdassets/logo-inverse.svgassets/logo-tile.svgassets/logo.svgassets/templates/ai-draft.mdassets/templates/audience.mdassets/templates/claim.mdassets/templates/evidence.mdassets/templates/style.mdCHANGELOG.mdLESSONS.mdLICENSEREADME.mdreferences/author-profiling.mdreferences/conception-guide.mdreferences/distribution.mdreferences/draft-routing.mdreferences/environment-detection.mdreferences/evidence-guide.mdreferences/form-guide.mdreferences/framework.mdreferences/obsidian-adaptation.mdreferences/platform-compliance.md**两件事一次发:把「值不值得写、有没有人接得住」补进骨架,把「发出去之后看不看得见」补成发布层。** 这一版的重点其实只有一个:**降低 AI 味、抬高深度长文的下限**——不再只是加检查项,而是让模型在**写的时候**手里就有材料。 ### 对你有什么影响 - 动笔前多问一句「这篇比同题多走了哪一步」。答不出,它会让你换论点、缩成经验分享,或直说「我没有找到同题内容」——不再用「没人讲过」这种听起来像判断、其实是编的话。 - 「读后必须有一个可执行动作」放宽了:解释 / 判断 / 行动 / 情绪 / 身份 / 表达 / 审美,七种回报认一种,不再逼你在结尾硬凑一句「你可以去试试」。 - 标题第一次有完整做法:先写完整句再删词、陌生人单独看得懂、留一个正文会回答的问题、每个限定词都有理由。**标题 / 摘要 / 小标题是三个位置**,不许重复同一句。 - 勾了发布平台,它会先看平台表(读者从哪进来、要什么、发布位在哪)再定标题、摘要、首段、结尾动作。同一篇发多处只换这四样,不制造近义改写凑数量。 - 开头多了三条边界:**判开头只判开头**(后文写得再好也不能给开头加分)、先查会不会被归错类、强断言先查「动到谁的什么」。 - 反驳多一类「读者接不住」,报告只给三种结论:**先改这几处**(内部默认不超过 3 条)、**要你确认**、**可改可不改**;每条带一句「代价」(丢掉哪类读者、少掉哪层解释),并且钉在原句上——`~~删除~~` / 🆕 新增 / ⚠️ 收回自己上一轮的判断。 - 报告里不许出现模型词(主回报 / 关系六型 / 断点形态 / 机器层 / 档位名),换成「读者读完会带走的那句话」这类人话。 - 明确仍不做的:预测播放量、抄平台字数常量、矩阵批量生产、投流、替作者判这篇有没有商业价值。 ### 新增 - **起草期材料会计**(最重要):每写一节之前,先在 `ai-draft.md` 该节标题下写一行 `本节材料:`——这节由哪几件真实的东西构成。写不出这一行就别写这一节。**这是治 AI 味的根**:模型写不出东西时不会停,会用抽象和漂亮句子填…
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:75c5828be3b1e6d4ce76e172cc94e3eaea0f36270456c30f571638df58dacccf