Agent skill

Novel2agent Jp

by kgmkm in kgmkm/novel2agent-jp

A skill your agent uses when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose).

MITAuto-check passedWriting & Content

Install Novel2agent Jp

skills CLI
$ npx skills add kgmkm/novel2agent-jp --skill novel2agent-jp -a claude-code

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

GitHub CLI
$ gh skill install kgmkm/novel2agent-jp novel2agent-jp --agent claude-code

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

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

Facts

Skill name
novel2agent-jp
GitHub stars
105
Token cost
~762 tokens
SKILL.md length
160 words
Files
62 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose).

  • Writing Japanese novels with AI coding agents (Hermes
  • SKILL.md covers 発火条件, 仕組み, 執筆セッション開始時の固定手順 and 参照, plus 2 more sections
  • Tasks that involve Creative writing and fiction

What it does

Novel2agent Jp is an agent skill from kgmkm/novel2agent-jp. Use when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose). File-based, agent-agnostic workflow: settings in TOML, deterministic context packs, validation scripts.

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 63 other files, including scripts and reference files (for example `README.md`, `references/character-design-guide.md` and `references/character-template.md`).

It sits in Writing & Content, covering Creative writing and fiction. The repository describes itself as: AIコーディングエージェントと日本語小説を書くためのスキル。TOML設定+検証スクリプト(旧 novel2hermesjp から改名). The licence is MIT.

When your agent uses it

  • Writing Japanese novels with AI coding agents (Hermes
  • Tasks that involve Creative writing and fiction

Example prompts

  • “/novel2agent-jp”

What it can do on your machine

Read from SKILL.md and the folder at commit 3e34007. 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

    Ships 1 file in scripts/, which the agent can run.

    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

Novel2agent Jp loads about 762 tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 160 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~762
With references · SKILL.md plus every file in references/, read only if the agent opens them
~26k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from kgmkm/novel2agent-jp at commit 3e34007, republished under its MIT licence (© kgmkm). 160 words, ~762 tokens.

Download SKILL.mdSave it as .claude/skills/novel2agent-jp/SKILL.md (or your agent's skills folder). This skill also uses 61 other files; get the full folder from GitHub.
name
novel2agent-jp
description
Use when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose). File-based, agent-agnostic workflow: settings in TOML, deterministic context packs, validation scripts.
version
0.4.7

novel2agent-jp

日本語小説制作のためのエージェント非依存ワークフロースキル。

発火条件

日本語小説の制作・執筆・推敲を AI コーディングエージェントに依頼するとき。

仕組み

TOML(設定・プロット・キャラ・世界観)
  ↓ scripts/validate.py(機械検証)
  ↓ scripts/pack.py(文脈パック生成)
.context/chNN.md(LLM に渡す Markdown・再生成可能)
  • 設定はすべて TOML。本文は novel/chNN.md にのみ書く
  • フェーズ境界は停止する:proposal 承認(proposal_status)→ 世界観・キャラ・プロット各承認 → 企画承認(plan_status+Phase A-4・A-5・C-1・MoAプロット診断)→ 章ごと確認が既定。承認なしに次へ進まない。詳細は planning §7・writing 執筆実行 8
  • 属性変更はキャラ TOML の [[versions]]、出来事は章 TOML の [[established]] に一元化
  • LLM の未確定事実は status = "proposed" で追記し、人間が "confirmed" に変える
  • 伏線の回収実績は [[foreshadowing]] の resolved_at に一本化

執筆セッション開始時の固定手順

手順の本体は references/writing-workflow.md 冒頭。validate → pack --check → 必要なら再生成 → .context/chNN.md を読んで執筆。

参照

ファイル読むとき
schema/toml-schema.mdTOML の必須キー・検証項目・pack.py 出力仕様
references/planning-workflow.md企画フェーズ(proposal / worldbuilding / character / plot の TOML 作成手順)
references/writing-workflow.md執筆セッションの手順(pack 生成 → 執筆 → TOML 反映)
references/revision-workflow.md推敲フェーズ(Phase A/B/C + MoA 4 視点 + proposed 確定手順)
references/moa-manual-orchestration.md4 視点の横並び比較推敲(MoA)の実行手順。エージェント非依存(推敲で複数モデルを使うとき)
references/character-template.mdキャラ TOML の全項目テンプレートと記入例
references/toml-formatting.mdTOML リテラルの機械整形(改行位置を AI に判断させない。TOML 修正後に読む)
references/character-design-guide.mdキャラの発想手順(欠点先行・三層・配置。テンプレを埋める前に)
references/sensory-rotation.md五感ローテーション(シーンごと視覚以外 2 つ以上)
references/metaphor-guide.md比喩の選び方(クリシェ回避・1〜2 個/シーン)
references/pixiv-export.mdpixiv投稿用変換の手順(エクスポート時に読む)
references/illustration-guide.md挿絵生成ワークフロー(挿絵を作るときに読む)
references/vfm-to-pixiv-workflow.md縦読み記法→pixiv変換の記法対比(VFMを使うときに読む)
references/vfm-to-kakuyomu-workflow.md縦読み記法→カクヨム変換の記法対比(カクヨム投稿時に読む)
references/hermes-setup.mdHermes 固有の環境セットアップ(他エージェントでは不要)

本文保存の鉄則(事故対策)

詳細は references/writing-workflow.md「執筆実行」。段落頭の全角空白禁止。保存直後に check_prose.py。

Scripts

CLI の詳細は各参照先。ここは用途の索引。

スクリプト用途詳細
scripts/validate.py設定検証(--index / --log)schema/toml-schema.md §5
scripts/format_toml.pyTOML リテラル整形(--check あり)references/toml-formatting.md
scripts/pack.py文脈パック生成(--chapter / --check / --budget)schema/toml-schema.md §6
scripts/check_prose.py本文品質(空本文・全角空白・禁止語彙)references/writing-workflow.md
scripts/init.pyプロジェクト雛形生成references/planning-workflow.md §0
scripts/pixiv_export.pypixiv 投稿用変換(レガシー NNN-タイトル.md も受理)references/pixiv-export.md
scripts/vfm_to_pixiv.py縦読み記法 → pixiv タグreferences/vfm-to-pixiv-workflow.md
scripts/vfm_to_kakuyomu.py縦読み記法 → カクヨム記法references/vfm-to-kakuyomu-workflow.md

© kgmkm, 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 61 other files (scripts, references) in the repository root of kgmkm/novel2agent-jp.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • references/character-design-guide.md
  • references/character-template.md
  • references/hermes-setup.md
  • references/illustration-guide.md
  • references/metaphor-guide.md
  • references/moa-manual-orchestration.md
  • references/pixiv-export.md
  • references/planning-workflow.md
  • references/revision-workflow.md
  • references/sensory-rotation.md
  • references/toml-formatting.md
  • references/vfm-to-kakuyomu-workflow.md
  • references/vfm-to-pixiv-workflow.md
  • references/writing-workflow.md
  • schema/toml-schema.md
  • … and 43 more

Open the folder on GitHubat commit 3e34007

Compare with similar skills

Novel2agent Jp 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.

Novel2agent Jp compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel2agent Jp this skillkgmkm/novel2agent-jp105—~762Automated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.4k2 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.3k—~1.1kAutomated safety check: NotesApache-2.0
SepiaNanako0129/sepia3.1k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed
  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.4k GitHub starsUsed in 2 repos~1.2k tokens
    Writing & ContentAuto-check passed
  • Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed
  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated 2 days ago
    Writing & ContentAuto-check: notes
  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3.1k GitHub stars~3.6k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Story Toolbox Router

    zenstory-ai/oh-story-claudecode

    Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.

    7.4k GitHub stars~1.7k tokensUpdated today
    Writing & ContentAuto-check passed

Questions about Novel2agent Jp

What does Novel2agent Jp do?

A skill your agent uses when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose). Novel2agent Jp is an agent skill from kgmkm/novel2agent-jp. Use when writing Japanese novels with AI coding agents (Hermes, Claude Code, opencode, goose).

When should I use Novel2agent Jp?

Novel2agent Jp fits situations like: writing Japanese novels with AI coding agents (Hermes; tasks that involve Creative writing and fiction.

How do I install Novel2agent Jp in Claude Code?

Run `npx skills add kgmkm/novel2agent-jp --skill novel2agent-jp -a claude-code`. Or copy the skill folder (the kgmkm/novel2agent-jp repository) into .claude/skills/novel2agent-jp in your project. Claude Code loads it when a task matches its description.

How do I install Novel2agent Jp in Codex?

Run `npx skills add kgmkm/novel2agent-jp --skill novel2agent-jp -a codex`. Or copy the skill folder (the kgmkm/novel2agent-jp repository) into .agents/skills/novel2agent-jp in your project. Codex loads it when a task matches its description.

Can I use Novel2agent Jp 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 kgmkm/novel2agent-jp --skill novel2agent-jp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel2agent-jp, .gemini/skills/novel2agent-jp, .github/skills/novel2agent-jp and .opencode/skills/novel2agent-jp in your project.

What does Novel2agent Jp need to run?

SKILL.md names no scripts, command-line tools or credentials: Novel2agent Jp is instructions for the agent only.

Does Novel2agent Jp 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 Novel2agent Jp 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Novel2agent Jp use?

Novel2agent Jp is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel2agent Jp use?

About 762 tokens (SKILL.md is roughly 3k 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 25k tokens, read only when the agent opens those files.

What are the alternatives to Novel2agent Jp?

Skills that share tags, products or a category with Novel2agent Jp: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel2agent Jp?

kgmkm (a GitHub user) maintains it in kgmkm/novel2agent-jp, which has 105 GitHub stars. The repository was last updated on September 25, 2026.

Source: kgmkm/novel2agent-jp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.