New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Moonlit Book Workflow

by lincwang123-bot in lincwang123-bot/moonlit-stories

Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations…

MITAuto-check passedMedia & Creative

Install Moonlit Book Workflow

skills CLI
$ npx skills add lincwang123-bot/moonlit-stories --skill moonlit-book-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lincwang123-bot/moonlit-stories moonlit-book-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lincwang123-bot/moonlit-stories.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/moonlit-book-workflow .claude/skills/moonlit-book-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
moonlit-book-workflow
GitHub stars
174
Token cost
~1.4k tokens
SKILL.md length
717 words
Files
5 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations…

  • Works in 12 steps: Read workflow-contract.md,… → Run node scripts/book-workflow.mjs list… → Ensure the profile has a separate… → …
  • The user asks to create
  • SKILL.md covers Purpose, Locate The Project, Required Workflow and Resume Discipline, plus 1 more section
  • Calls node

What it does

Moonlit Book Workflow is an agent skill from lincwang123-bot/moonlit-stories. Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations and local authorized-adult voice cloning for narration. Use when the user asks to create, regenerate, resume, validate, or publish a custom Moonlit children's book from child profile data.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/image-generation.md` and `references/tts-and-release.md`).

It sits in Media & Creative, covering Text to speech and voice and Image generation. The repository describes itself as: Reusable AI English picture-book workflow with consistent illustrations and local Chatterbox TTS. The licence is MIT.

When your agent uses it

  • The user asks to create
  • Publish a custom Moonlit childrens book from child profile data

Example prompts

  • “/moonlit-book-workflow”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Read workflow-contract.md, image-generation.md, and tts-and-release.md before acting.
  2. Run node scripts/book-workflow.mjs list first. If the user supplied the job ID returned by the browser form, inspect it with node…
  3. Ensure the profile has a separate Latin-script english_name. If the form supplied only a Chinese name, propose an English name or pinyin…
  4. Create a job from a validated child profile when no job exists.
  5. Draft exactly 12 pages. Each page has one English sentence, one faithful Chinese translation, and one scene prompt. English narration must…
  6. Commit the story and run plan. Review the resulting prompt/task manifest before image generation.
  7. Generate the character sheet first with built-in image generation. Inspect it visually. Record the exact returned file path, then approve…
  8. Generate the cover and pages 1–12 with both the neutral style key and the approved character sheet as references. Inspect every candidate…
  9. Inspect manifest.narration. When it is parent-clone/ready, reuse the normalized profile at private_profile_path inside the job; do not ask…
  10. Record and approve all 12 narration files, assemble book.json, validate the job, and build a self-contained reader HTML.
  11. Before making a shareable HTML, obtain guardian confirmation for the chosen child display name and generated likeness. Keep full profile…
  12. Open the result in the in-app browser and verify desktop and mobile rendering, page navigation, Chinese toggle, and audio playback. Close…

What it can do on your machine

Read from SKILL.md and the folder at commit 2a0b5c0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Moonlit Book Workflow loads about 1.4k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 717 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lincwang123-bot/moonlit-stories at commit 2a0b5c0, republished under its MIT licence (© lincwang123-bot). 717 words, ~1,371 tokens.

Download SKILL.mdSave it as .claude/skills/moonlit-book-workflow/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
moonlit-book-workflow
description
Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations and local authorized-adult voice cloning for narration. Use when the user asks to create, regenerate, resume, validate, or publish a custom Moonlit children's book from child profile data.

Moonlit Book Workflow

Purpose

Produce one personalized English picture book as a resumable local job. Keep story content variable while locking the illustration style with the approved neutral style key and one per-book character sheet. Render narration locally only from an authorized adult voice profile.

This skill orchestrates Codex tools and the project CLI. The browser application does not call Codex image generation directly.

Locate The Project

Use the current workspace when it contains scripts/book-workflow.mjs and workflow/styles/moonlit-watercolor-v1/style.json. Otherwise ask the user to open or provide the Moonlit Stories repository; never guess a user-specific absolute path. Refer to the repository root as PROJECT_ROOT in commands.

Do not put jobs, voice references, model weights, or generated private assets in source control. Use PROJECT_ROOT/.moonlit/jobs and PROJECT_ROOT/.local-models. A form-created job may keep its normalized narrator profile under that job's private/voice/ directory; never move it into public assets.

Required Workflow

  1. Read workflow-contract.md, image-generation.md, and tts-and-release.md before acting.
  2. Run node scripts/book-workflow.mjs list first. If the user supplied the job ID returned by the browser form, inspect it with node scripts/book-workflow.mjs status --job-id JOB_ID and read its manifest.json. Resume that exact job; do not recreate it. For a new job without an ID, derive a filesystem-safe ID such as 20260803-luna-lantern, report it, and use it consistently.
  3. Ensure the profile has a separate Latin-script english_name. If the form supplied only a Chinese name, propose an English name or pinyin and get guardian confirmation before creating the job; never insert Han characters into English narration.
  4. Create a job from a validated child profile when no job exists.
  5. Draft exactly 12 pages. Each page has one English sentence, one faithful Chinese translation, and one scene prompt. English narration must use the child's chosen English name and contain no Han characters.
  6. Commit the story and run plan. Review the resulting prompt/task manifest before image generation.
  7. Generate the character sheet first with built-in image generation. Inspect it visually. Record the exact returned file path, then approve it.
  8. Generate the cover and pages 1–12 with both the neutral style key and the approved character sheet as references. Inspect every candidate before approval.
  9. Inspect manifest.narration. When it is parent-clone/ready, reuse the normalized profile at private_profile_path inside the job; do not ask the user to upload it again and do not expose its transcript or consent file. When it is standard/pending, finish story and illustrations, then stop at the TTS gate and ask for an authorized adult recording. Run local TTS only from an explicitly authorized adult profile. Never clone a child or an unconsenting person.
  10. Record and approve all 12 narration files, assemble book.json, validate the job, and build a self-contained reader HTML.
  11. Before making a shareable HTML, obtain guardian confirmation for the chosen child display name and generated likeness. Keep full profile details in the private manifest and publish only reader-required fields.
  12. Open the result in the in-app browser and verify desktop and mobile rendering, page navigation, Chinese toggle, and audio playback. Close temporary servers and browser sessions started for testing.
Show full SKILL.md (207 more words)Show less

Resume Discipline

  • Treat manifest.json as the source of truth.
  • Never infer image output by modification time. Pass the exact path returned by built-in image generation to record-image.
  • Keep approved tasks. Retry only pending or failed tasks.
  • If the story changes, re-run commit-story and plan; accept the CLI's selective invalidation instead of deleting the job.
  • If the style key, character identity, narration text, voice sample, model revision, or TTS parameters change, regenerate affected artifacts.
  • Never invent an image seed or stable model version. The built-in generator does not expose either.

Completion Gate

Do not report completion until all of the following are true:

  • one approved character sheet, one approved cover, and 12 approved page illustrations exist;
  • each page illustration used the same neutral style key and per-book character sheet;
  • exactly 12 English sentences contain no Han characters and their Chinese translations are faithful;
  • exactly 12 local narration files correspond to the English text;
  • assemble and validate succeed;
  • the custom single-file reader opens without console errors and the assets are embedded;
  • no private voice reference or consent file is embedded in the reader.

If no authorized voice reference is available, stop at the TTS preflight gate and state that illustration/story production can continue but voice cloning is not complete.

© lincwang123-bot, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/moonlit-book-workflow of lincwang123-bot/moonlit-stories.

  • SKILL.md
  • agents/openai.yaml
  • references/image-generation.md
  • references/tts-and-release.md
  • references/workflow-contract.md

Open the folder on GitHubat commit 2a0b5c0

Compare with similar skills

Moonlit Book Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Moonlit Book Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Moonlit Book Workflow this skilllincwang123-bot/moonlit-stories174—~1.4kAutomated safety check: PassMIT
Wedding Video Guided Wizardaaronyi97/wedding-video-guided-wizard310—~1kAutomated safety check: PassMIT
Hbg Life SimulationMr-funny/hbg-life-simulation141—~5.8kAutomated safety check: PassMIT
RunninghubHM-RunningHub/OpenClaw_RH_Skills142—~1.6kAutomated safety check: PassApache-2.0
Media Genclacky-ai/openclacky1.2k—~7.3kAutomated safety check: PassMIT
Ocv Generate Test ScriptsIFRIT-Zhou/One-Click-VidGen113—~1.8kAutomated safety check: PassAGPL-3.0

Similar skills

  • Wedding Video Guided Wizard

    aaronyi97/wedding-video-guided-wizard

    Guide a creator through a real couple's custom wedding video, from a shareable story intake card and Kimi writing pack through narration, external GPT image prompts, image-to-video packs, music and…

    310 GitHub stars~1k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Hbg Life Simulation

    Mr-funny/hbg-life-simulation

    Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga…

    141 GitHub stars~5.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

  • Runninghub

    HM-RunningHub/OpenClaw_RH_Skills

    Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.

    142 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.3k tokensUpdated today
    Media & CreativeAuto-check passed

  • Ocv Generate Test Scripts

    IFRIT-Zhou/One-Click-VidGen

    Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and…

    113 GitHub stars~1.8k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Qwen Edit

    digitalsamba/claude-code-video-toolkit

    AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit.

    2.2k GitHub stars~711 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed

Categories

Questions about Moonlit Book Workflow

What does Moonlit Book Workflow do?

Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations…. Moonlit Book Workflow is an agent skill from lincwang123-bot/moonlit-stories. Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations and local authorized-adult voice cloning for narration.

When should I use Moonlit Book Workflow?

Moonlit Book Workflow fits situations like: the user asks to create; publish a custom Moonlit childrens book from child profile data.

How do I install Moonlit Book Workflow in Claude Code?

Run `npx skills add lincwang123-bot/moonlit-stories --skill moonlit-book-workflow -a claude-code`. Or copy the skill folder (skills/moonlit-book-workflow in lincwang123-bot/moonlit-stories) into .claude/skills/moonlit-book-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Moonlit Book Workflow in Codex?

Run `npx skills add lincwang123-bot/moonlit-stories --skill moonlit-book-workflow -a codex`. Or copy the skill folder (skills/moonlit-book-workflow in lincwang123-bot/moonlit-stories) into .agents/skills/moonlit-book-workflow in your project. Codex loads it when a task matches its description.

Can I use Moonlit Book Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lincwang123-bot/moonlit-stories --skill moonlit-book-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moonlit-book-workflow, .gemini/skills/moonlit-book-workflow, .github/skills/moonlit-book-workflow and .opencode/skills/moonlit-book-workflow in your project.

What does Moonlit Book Workflow need to run?

Going by SKILL.md and its folder, Moonlit Book Workflow needs the command-line tools its instructions call (node).

Does Moonlit Book Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Moonlit Book Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Moonlit Book Workflow use?

Moonlit Book Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Moonlit Book Workflow use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Moonlit Book Workflow?

Skills that share tags, products or a category with Moonlit Book Workflow: Wedding Video Guided Wizard (aaronyi97/wedding-video-guided-wizard, 310 stars), Hbg Life Simulation (Mr-funny/hbg-life-simulation, 141 stars), Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 142 stars) and Media Gen (clacky-ai/openclacky, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Moonlit Book Workflow?

lincwang123-bot (a GitHub user) maintains it in lincwang123-bot/moonlit-stories, which has 174 GitHub stars. The repository was last updated on September 4, 2026.

Source: lincwang123-bot/moonlit-stories on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.