How do I install the Xhs Book Reuse Smoke skill?

Run npx skillmds add yanghu819/xhs-book-reuse-smoke in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Xhs Book Reuse Smoke safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Xhs Book Reuse Smoke?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Xhs Book Reuse Smoke free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Xhs Book Reuse Smoke?

yanghu819 (@yanghu819) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Xhs Book Reuse Smoke by yanghu819 — Agent Skill

Name: Xhs Book Reuse Smoke
Rating: 4.2 (5 reviews)
Author: yanghu819

Xhs Book Reuse Smoke

Run a reusable book-swap smoke pipeline for Xiaohongshu cards from outline to evidence assets, markdown, 10-card render, and manifest validation, including optional persona anchor rendering. Use when users ask whether the pipeline can quickly switch books, keep a人物锚点 style, want a new-book dry run, or request 冒烟验证 like 《从0到1》.

yanghu819 a29601e 6 files · 23.5 KB Updated Sep 10, 2026

File contents

xhs-book-reuse-smoke

Use this skill to verify that the XHS pipeline is reusable for a different book without changing core scripts.

Inputs

--preset: zero_to_one or hard_thing_persona (default zero_to_one)
--outline: book_outline.v1.json path (optional; overrides preset default)
--author: author signature for cards
--output-root: run output root directory
--theme: direct renderer theme (editorial_unified_v1 default)
--hero-anchor: optional author/persona image path
--hero-anchor-mode: cover|all|none

Default command

python3 scripts/smoke_book_pipeline.py \
  --preset zero_to_one \
  --outline references/zero_to_one.book_outline.v1.json \
  --author "Hy3" \
  --theme editorial_unified_v1

Persona smoke command (继续之前人物)

python3 scripts/smoke_book_pipeline.py \
  --preset hard_thing_persona \
  --author "Hy3"

Workflow

Validate outline schema (book_outline.v1.json).
Build large-text evidence assets (evidence_01..06.png).
Generate xhs_post.v2.md (fixed 10-card structure).
Render direct cards (1080x1440, optional persona anchor).
Build and verify render_manifest.v1.json.
Emit smoke_report.json with stage logs and pass/fail summary.

Output contract

<run_dir>/xhs_post.zero_to_one.v2.md
<run_dir>/assets/evidence_01.png ... evidence_06.png
<run_dir>/rendered/01-card.png ... 10-card.png
<run_dir>/rendered/render_manifest.v1.json
<run_dir>/smoke_report.json

Quality gates (hard fail)

Rendered card count must be 10.
Every card must be exactly 1080x1440.
Manifest card_count and image filenames must match actual files.
If persona mode is enabled, report must include hero_anchor_exists=true (or explicit warning).

Notes

This skill does not publish notes; it is smoke-only.
Works for Codex and Claude Code because all steps are plain CLI scripts.
When smoke fails, inspect <run_dir>/logs/*.log first.

---name: xhs-book-reuse-smokedescription: Run a reusable book-swap smoke pipeline for Xiaohongshu cards from outline to evidence assets, markdown, 10-card render, and manifest validation, including optional persona anchor rendering. Use when users ask whether the pipeline can quickly switch books, keep a人物锚点 style, want a new-book dry run, or request 冒烟验证 like 《从0到1》.---# xhs-book-reuse-smokeUse this skill to verify that the XHS pipeline is reusable for a different book without changing core scripts.## Inputs- `--preset`: `zero_to_one` or `hard_thing_persona` (default `zero_to_one`)- `--outline`: `book_outline.v1.json` path (optional; overrides preset default)- `--author`: author signature for cards- `--output-root`: run output root directory- `--theme`: direct renderer theme (`editorial_unified_v1` default)- `--hero-anchor`: optional author/persona image path- `--hero-anchor-mode`: `cover|all|none`## Default command```bashpython3 scripts/smoke_book_pipeline.py \ --preset zero_to_one \ --outline references/zero_to_one.book_outline.v1.json \ --author "Hy3" \ --theme editorial_unified_v1```### Persona smoke command (继续之前人物)```bashpython3 scripts/smoke_book_pipeline.py \ --preset hard_thing_persona \ --author "Hy3"```## Workflow1. Validate outline schema (`book_outline.v1.json`).2. Build large-text evidence assets (`evidence_01..06.png`).3. Generate `xhs_post.v2.md` (fixed 10-card structure).4. Render direct cards (`1080x1440`, optional persona anchor).5. Build and verify `render_manifest.v1.json`.6. Emit `smoke_report.json` with stage logs and pass/fail summary.## Output contract- `<run_dir>/xhs_post.zero_to_one.v2.md`- `<run_dir>/assets/evidence_01.png ... evidence_06.png`- `<run_dir>/rendered/01-card.png ... 10-card.png`- `<run_dir>/rendered/render_manifest.v1.json`- `<run_dir>/smoke_report.json`## Quality gates (hard fail)- Rendered card count must be `10`.- Every card must be exactly `1080x1440`.- Manifest `card_count` and image filenames must match actual files.- If persona mode is enabled, report must include `hero_anchor_exists=true` (or explicit warning).## Notes- This skill does not publish notes; it is smoke-only.- Works for Codex and Claude Code because all steps are plain CLI scripts.- When smoke fails, inspect `<run_dir>/logs/*.log` first.

Frequently asked questions