# Novel Load Context

> Use when drafting, planning, or reviewing a long-form fiction chapter and the model must load canon facts instead of relying on fragile prompt memory.

- **Type:** Skill
- **Install:** `agentstack add skill-zhao73-xiaoshuo-studio-novel-load-context`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Zhao73](https://agentstack.voostack.com/s/zhao73)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Zhao73](https://github.com/Zhao73)
- **Source:** https://github.com/Zhao73/xiaoshuo-studio/tree/main/.agents/skills/novel-load-context

## Install

```sh
agentstack add skill-zhao73-xiaoshuo-studio-novel-load-context
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# novel-load-context

## Purpose

Build a minimal context pack from project canon before any chapter planning or drafting.

Reference: `docs/local-codex-studio.md`

## Workflow

1. Read the current canon with `GET /api/canon?projectId=`.
2. Build a chapter brief with `POST /api/chapters/brief`.
3. Restate:
   - chapter goal
   - must-use facts
   - forbidden moves
   - style constraints
4. Stop if the canon is missing key facts. Ask for canon repair instead of improvising.

## Guardrails

- Canon facts override vague user memory.
- Treat missing data as a blocker, not an invitation to hallucinate.
- Prefer 8-12 hard facts over dumping raw history.

## Source & license

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

- **Author:** [Zhao73](https://github.com/Zhao73)
- **Source:** [Zhao73/xiaoshuo-studio](https://github.com/Zhao73/xiaoshuo-studio)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zhao73-xiaoshuo-studio-novel-load-context
- Seller: https://agentstack.voostack.com/s/zhao73
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.