AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Novel Standard

skill-alfredxw-nova-novel-standard · by alfredxw

默认写作流程,由主 Agent 写作和修订,审稿子 Agent 严格审稿,在质量和速度之间取得平衡。

No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-alfredxw-nova-novel-standard

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-alfredxw-nova-novel-standard)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Novel Standard? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

novel-standard

这是 IDE 创作 Agent 的默认写作流程,在质量和速度之间取得平衡。

写作范围判断

  • 从用户的实际指令判断写作范围,例如“续写一段”“写一个场景”“写一章”“写三章”“写一个小剧情段落 / arc”或用户自定义目标。
  • 除非用户明确说“写下一章”,否则不要假设任务一定是下一章。
  • 没有 writing_scope 字段。用户消息是判断范围、目标、约束和输出形态的唯一来源。
  • 当用户要求一次写 N 章或其他多段写作时,先制定整体计划和分章计划。计划要简洁,并用于指导初稿。

流程

主 Agent 写初稿 -> 审稿子 Agent 审稿 -> 主 Agent 修订和更新状态 -> 最终输出

标准流程只使用两个 Agent:主 Agent 和审稿子 Agent(reviewer)。不要启动 writerfixer 或其他额外写作子流程。

  1. 主 Agent 按用户要求的范围和约束生成初稿,通过 write_file 工具写入 chapters/ 下的章节文件,暂不更新进度和角色状态相关文件。
  2. 主 Agent 启动审稿子 Agent(reviewer)审稿,并把新增章节、用户要求、必要上下文和需要重点检查的规则交给 reviewer
  3. reviewer 只审稿并返回结构化问题,不直接改正文;需要严格检查连续性、资料库匹配、节奏、文风、人物动机、剧情逻辑,以及每条创作规则是否遵守;不要输出赞扬。
  4. 主 Agent 接收审稿结论后直接修订章节,只修真正需要修的问题,保留原故事内容、强段落、有效情节节点、人物声线和连续性。
  5. 主 Agent 确认最终修订稿后,更新 setting/progress.mdsetting/character-states.md。只有长期稳定设定发生明确变化时,才提出资料库更新建议或按用户要求更新资料库。

审稿要求

reviewer 审稿时可读取必要前文、CREATOR.md、大纲、进度、角色状态和资料库作为对照依据。重点检查新增章节是否符合任务要求、用户提示词、CREATOR.md、长期大纲、角色设定与当前状态、世界观和已有连续性;评估剧情推进、人物行为动机、设定一致性、节奏、语言质量和可读性。按严重程度输出问题、证据位置、影响和可执行改进建议;如果执行模式不允许写入,只输出审稿结论和修订方案。

最终输出

  • 返回最终正文或用户要求的写作产物。
  • 除非用户要求,不输出 reviewer 报告或内部修订说明。
  • 如果关键约束无法满足,先简短说明阻断问题或请求用户确认。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.