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

Continue

skill-alfredxw-nova-continue · by alfredxw

续写小说章节。当用户要求写下一章、继续写、开始写某一章时使用。

↗ Repository
— No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-alfredxw-nova-continue

✓ 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-continue)

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 Continue? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

章节续写

根据大纲、角色状态、资料库设定和前文内容续写小说章节。

工作流程

  1. 使用 read_file 读取 setting/outline.md 确认长期方向
  2. 使用 read_file 读取 setting/progress.md 获取最近章节摘要，并读取 setting/character-states.md 确认角色当前位置、身体、心理、目标、持有物和关系等当前状态
  3. 如 setting/chapter-groups/ 下存在当前章节组细纲，优先读取对应细纲，确认本章在组内的作用、冲突、信息揭示和钩子
  4. 必须读取前面至少 2 章定稿正文，确保本章与前文自然衔接
  5. 根据大纲方向、章节组细纲、角色当前状态、资料库长期设定和前文正文创作本章内容；如本轮涉及资料库索引中的相关自动加载条目（基于简介判断），先用 readloreitems 读取完整资料
  6. 使用 write_file 将章节写入 chapters/ 下符合系统提示章节文件名模板的位置；非空新章节默认是初稿，由章节状态控制是否成章
  7. 不更改 setting/outline.md
  8. 只有作者明确确认成章或明确要求同步状态后，才更新 setting/progress.md（当前进度 + 本章摘要）和 setting/character-states.md（角色当前状态）；只有长期设定发生明确变化时，才使用 writeloreitems 批量同步资料库条目

写作要求

  • 严格遵循大纲的章节走向和摘要
  • 如有章节组细纲，优先保证本章完成细纲中分配的短期情节功能
  • 大纲只作为长期结构和章节方向参考，续写完成后不要修改大纲文件
  • 写作推进主要通过 setting/progress.md 追踪，记录当前进度、已完成章节摘要和短期衔接提示
  • 角色当前状态通过 setting/character-states.md 追踪，按角色记录最近出场、当前位置、身体状态、心理状态、当前目标、持有物、能力变化、关系变化和待回收伏笔
  • 未确认成章的初稿不写入 progress.md、character-states.md 或资料库
  • 资料库只同步角色身份、人设、长期关系、能力体系、世界规则、地点、势力和物品等稳定设定变化，不记录每章后的状态抖动，不写章节规划
  • 保持角色性格和说话方式一致
  • 与前面至少两章自然衔接（注意情节、时间、地点、人物状态的连贯）
  • 注意伏笔的埋设和呼应
  • 遵循指定的字数要求
  • 章节正文使用纯文本自然段，禁止使用 Markdown 标题、列表、引用、加粗等标记
  • 章节开头直接开始叙事，不要输出章节标题

章节文件格式

正文内容直接使用自然段，段落间空行分隔。

进度文件格式

创作进度

  • 当前进度：第X章已完成
  • 总章节数：Y 章
  • 已完成：Z 章

最近章节摘要

第X章：章节标题

摘要内容（200字以内，概括主要情节和角色变化）

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills