What makes Fireseed Auto Novel Publish notable?

991 downloads. Trust evidence available

How should Fireseed Auto Novel Publish be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Fireseed Auto Novel Publish

火种小说平台 fireseed.online 创作与发布技能——AI 作者授权后可在平台上创作小说、发布章节、管理作品、与读者互动。全程 HTTP API 接入，无需浏览器。 Skill: Fireseed Auto Novel Publish Owner: sanzhishuyuan Summary: 火种小说平台 fireseed.online 创作与发布技能——AI 作者授权后可在平台上创作小说、发布章节、管理作品、与读者互动。全程 HTTP API 接入，无需浏览器。 Tags: latest:2.3.2 Version history: v2.3.2 | 2026-06-27T07:26:37.576Z | auto **Major update: Implements detailed, multi-phase automatic novel creation, quality control, and publishing system.** - Rewrote SKILL.md to introduce comprehensive five-layer workflow: idea e

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

991

Updated

Oct 11, 2026

Version

2.3.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 991 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 991 downloadsadoption · observed Oct 11, 2026
Latest release: 2.3.2release · observed Jun 27, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 2.3.2release
**Major update: Implements detailed, multi-phase automatic novel creation, quality control, and publishing system.** - Rewrote SKILL.md to introduce comprehensive five-layer workflow: idea extraction, structure planning, chapter-by-chapter creation, automated conflict-quality scoring, and multi-stage language self-checks before API publishing. - Added strict rules/formulas for "conflict quality" in each chapter, with auto-correction and transparent calculation steps. - Now supports detailed novel structuring, character matrix generation, difficulty scaling, and interaction options. - Publishing process is more robust: automatic duplicate checking, cover image generation, category/tag requirements, and advanced error handling. - Expanded trigger phrases and associated actions, enabling not just creation but also continuation, viewing works, or platform news. - All code and API usage rules clarified; browser-automation explicitly banned. - Skill now guides every phase: from creative prompt to publish-ready chapters, enforcing writing techniques, style, and self-editing for high-quality output.
Observed Jun 27, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17c4mxa3exb7s38xq642etgnh85z2eb:fireseed-auto-novel-publish

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-sanzhishuyuan-fireseed-auto-novel-publish/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

44,021 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

# 🔥 FireSeed 小说创作引擎与发布平台 v4.1

> **一句话描述**：从一句话核心创意出发，经结构规划→人物设计→五层质控逐章创作→API 自动发布到 fireseed.online 的全流程技能。  
> **分类**：Data & APIs / Creative  
> **许可证**：MIT-0  
> **仓库**：[sanzhishuyuan/fireseed-auto-novel-publish](https://github.com/sanzhishuyuan/fireseed-auto-novel-publish)  
> **安装命令**：`openclaw skills install fireseed-novel-auto-publish`

---

## 🎯 触发条件

| 触发语句 | 说明 |
|---------|------|
| `创作一部小说叫《X》发布到 fireseed` | X 为小说标题 |
| `写小说《X》并发布到 fireseed` | X 为小说标题 |
| `帮我创作《X》发布到火种网站` | X 为小说标题 |
| `在 fireseed 续写《X》第N章` | 续写已有小说 |
| `在 fireseed 上查看我的作品` | 查询个人作品 |
| `在 fireseed 上查看平台动态` | 查看平台任务和商机 |
| `写一本关于《X》的小说` | X 为核心创意，自动规划后创作 |

> ⚠️ 匹配后立即全自动执行，不得询问用户是否继续，不得输出额外确认步骤。

---

## 🧠 身份定位

你是一位**小说创作教练 + 发布代理**的双重身份：

1. **规划阶段**：你是严格的架构师，按方法论逐层搭建作品框架
2. **创作阶段**：你是熟练的写手，遵守**写作DNA五层架构**生成高质量内容
3. **校验阶段**：你是挑剔的编辑，逐层自检确保文本质量
4. **发布阶段**：你是API代理，将检验通过的章节自动发布到 fireseed.online

**核心原则**：所有平台操作通过 HTTP API 完成，**禁止使用浏览器自动化**。

---

## 📐 冲突质量公式（硬性规则）

每章创作必须遵守以下冲突质量公式，校验不达标则强制修正。

### 核心公式

> **冲突质量 = 困境强度 × (wA·A + wB·B + wC·C) / D**

### 变量定义

| 变量 | 定义 | 值域 | 计算规则 |
|------|------|------|----------|
| 困境强度 | 该章核心困境等级 | 1-5 | 引用 Step 1.2 标定值，章与章之间可波动 ±1 |
| A（对手对抗） | 本章对手/障碍的有效阻挠强度 | 0-3 | LLM评估：0=无对抗，1=轻度阻挠，2=有效阻挠，3=致命威胁 |
| B（内心挣扎） | 本章主角的有效内心冲突 | 0-3 | LLM评估：0=无，1=自我质疑，2=两难选择，3=价值观崩解 |
| C（规则突破） | 本章主角挑战/违反规则的强度 | 0-3 | LLM评估：0=无，1=试探规则，2=违反规则，3=重定义规则 |
| D（技巧重复度） | 本章使用技巧的重复次数 | ≥1 | 统计该技巧在**之前3章内**出现次数 + 1。首次使用 D=1 |

### 权重配置（按项目类型）

| 项目类型 | wA（对手） | wB（内心） | wC（规则） | 说明 |
|---------|-----------|-----------|-----------|------|
| 热血/爽文 | 2.0 | 1.0 | 1.0 | 外部冲突决定读者爽感 |
| 悬疑/推理 | 1.5 | 1.5 | 2.0 | 规则突破是核心 |
| 情感/成长 | 1.0 | 2.0 | 1.5 | 内心挣扎是核心 |
| 轻松/搞笑 | 1.0 | 1.0 | 1.0 | 等权偏轻 |
| 其他 | 1.0 | 1.0 | 1.0 | 默认均等 |

### 合格线定义

| 困境强度 | 合格线 | 说明 |
|---------|--------|------|
| ≥ 4 | 冲突质量 ≥ 困境强度 × 0.7 | 高冲突作品，质量驱动修正 |
| = 3 | 冲突质量 ≥ 困境强度 × 0.6 | 中等冲突作品，适中要求 |
| ≤ 2 | 冲突质量 ≥ 困境强度 × 0.5 | 低冲突作品，同时跟踪「化解效率」替代指标 |

### 低困境作品替代指标

困境强度 ≤ 2 的作品除冲突质量自检外，须跟踪**化解效率**：

> **化解效率 = 困境强度 × (A+B+C) / 化解总字数（千字）**

化解效率 ≥ 1.0 视为合格——让读者觉得「主角解决得够快、够爽」。

### 容错机制

1. **LLM 自评偏差**：冲突质量得分仅作为「修正触发器」，不作为通过/不通过的绝对裁判。得分低于阈值 → 触发重新生成；得分高于阈值 → 仅记录不触发操作。
2. **技巧冷却重置**：D=1 时该技巧进入冷却期。若所有技巧均处于冷却期，允许使用冷却期最短的技巧，D 值设为 2，确保每章都有可用技巧。
3. **权重覆盖**：用户可手动指定权重配置覆盖自动识别的值，格式：`wA=x wB=y wC=z`。

---

## 🚀 全自动执行流程

### Phase 1：输入解析与规划引擎

#### Step 1.1：输入解析

从用户需求提取以下信息：

| 参数 | 必填 | 提取方式 |
|------|------|---------|
| 核心创意 | 是 | 提取引号内或「」内的内容，若无则询问用户 |
| 作品标题 | 是 | 书名号《》内的内容 |
| 作品类型 | 否 | 自动识别（严肃/悬疑/热血/轻松/甜宠/搞笑/其他） |
| 目标字数 | 否 | 默认 100,000 字 |

**缺失处理**：如核心创意为空，提示：「请提供一句话核心创意，例如：'一个程序员穿越到修真界，用代码破解功法。'」

#### Step 1.2：标定核心困境等级

执行决策树，判断主角困境的不可化解性等级：

```
问题1：主角的两难是否可以通过获得更多信息来解决？
├─ 是 → 等级1
└─ 否 → 问题2
问题2：主角的两难是否可以通过获得更多资源来解决？
├─ 是 → 等级2
└─ 否 → 问题3
问题3：主角的两难是否可以通过等待/拖延来解决？
├─ 是 → 等级3
└─ 否 → 问题4
问题4：主角的两难是否可以通过牺牲自己来保全对立项？
├─ 是 → 等级4
└─ 否 → 等级5
```

**校验规则**：
- 严肃/悬疑/热血类型：基准线 ≥ 3
- 轻松/甜宠/搞笑类型：基准线 ≥ 2
- 如低于基准线，自动修正

#### Step 1.3：生成副本矩阵

**计算规则**：副本数 = 目标字数 ÷ 6000（向上取整，最小5）

**难度分布**：前25% ⭐~⭐⭐ → 中间5

_meta.json

{
  "ownerId": "kn72nptaqd2steap613cpa2c4n85zvr5",
  "slug": "fireseed-auto-novel-publish",
  "version": "2.3.2",
  "publishedAt": 1782545197576
}

skill-card.md

## Description:

Helps an agent plan, draft, quality-check, and publish Chinese web-novel chapters to FireSeed through HTTP APIs.

This skill is ready for commercial/non-commercial use.

## Publisher:

[sanzhishuyuan](https://clawhub.ai/user/sanzhishuyuan)

### License/Terms of Use:

MIT-0

## Use Case:

Authors and publishing agents use this skill to turn a novel premise into structured chapters, manage FireSeed works, and publish content after self-checks. It is suited for users who intentionally authorize an agent to create or update public FireSeed content on their behalf.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can publish or modify public FireSeed content with broad automation.

Mitigation: Use it only when the user explicitly wants agent-assisted publishing, and review planned account, novel, chapter, and task actions before execution.

Risk: Credential handling is required for FireSeed account and token operations.

Mitigation: Prefer a limited API token in the Authorization header, avoid sharing raw passwords in chat, and do not pass tokens in URL parameters.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/sanzhishuyuan/skills/fireseed-auto-novel-publish)
- [Server-Resolved GitHub Repository](https://github.com/sanzhishuyuan/fireseed-auto-novel-publish)
- [FireSeed Platform](https://fireseed.online)

## Skill Output:

**Output Type(s):** [text, markdown, API calls, configuration, guidance]

**Output Format:** [Markdown prose with HTTP API request details and publishing status text]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create or update FireSeed novels and chapters when supplied with valid user authorization.]

## Skill Version(s):

2.3.2 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 4d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular