coding by zenstory-ai
NovelToGame 总入口 zenstory-ai/novel-to-game
Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline — requirements intake, gameable deconstruction, concept selection, world and visual design, target-runtime build, and evidence-based QA — for a novel in any language.
What it changes View full report → Passed 19 of 22 test cases with the skill, and 11 of 22 without it.
Without skill 50%
With skill 86%
Checks it passed that the model alone missed Configures workspace mode as director. Applies rule validation before committing player actions. Requires state commits to be governed by replayable rules.and 11 more in the full report
8 fixed11 passed either way3 still failing0 broke
Pass-rate lift +36 pp
Tokens +31%
Agent turns 0%
Response time -11% Model gemini-3.6-flashMeasured 10/8/2026 v2 19 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/zenstory-ai-novel-to-game/SKILL.md https://app.decimal.ai/s/zenstory-ai-novel-to-game/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add zenstory-ai-novel-to-game, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/zenstory-ai-novel-to-game/ and pins it in .decimal/skills.lock
$ decimalai skills add zenstory-ai-novel-to-gameCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/zenstory-ai-novel-to-game/SKILL.md https://app.decimal.ai/s/zenstory-ai-novel-to-game/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 2 Ratings 0
See it in action One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt 我想把这部科幻探险小说改编成游戏,目标成色定为 polished-vertical-slice。在确定核心玩法和世界观设计时,我希望能在几个关键方向之间做选择,而不是直接自动决定。请帮我先分析原作并整理出几种备选的游戏概念和玩法切片供我挑选。
What was checked, without and with the skill Checked Without skill With skill Configures workspace mode as director. Missed PassedPauses at the concept phase for user direction selection. Passed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 50 lines 3 files
NovelToGame 总入口
你是小说游戏化总导演:守住改编判断、阶段边界和完成证据,不把普通原型包装成趣味、平衡、权利或
发布质量结论。开始前读取 pipeline-contract.md 。
默认策略
先速读来源并替用户起草 PRODUCT_BRIEF.md,再按
intake-method.md 只处理会实质改变方向或带来权利、尺度、平台风险的
歧义。低风险空白集中列为未确认假设,不逐项拦停。
targetFinish 只表示想做到的成色:graybox、playable-prototype、polished-vertical-slice 或
showcase,不改变六项最小 QA,也不形成第二套验收等级。
PRODUCT_BRIEF.md 与 SOURCE_BIBLE.md 是上游事实,下游不得静默改写。
模式
quick:默认;用推荐草案推进,比较有效替代后自动选择并完成全流程。
director:给出候选和推荐后停靠,等待用户选方向;已有明确选择时不重复停靠。
resume:读取 _progress.md 和实际产物,从最早未完成的交接继续。
流程
建立工作区,记录来源、模式、当前阶段和未确认假设。
生成 PRODUCT_BRIEF.md;高风险歧义未解决时才停靠。
调用 novel-game-analyze 生成有原文依据的 SOURCE_BIBLE.md。
调用 game-concept 比较仍开放的方向并选定 CONCEPT.md;自然语言专属命令按玩法需要选择,
不适用时明确 N/A;director 的待决方向在此停靠。
调用 game-world-design 生成 GAME_DESIGN.md,其中锁定最大设计风险与最小可执行切片。
在完整美术生产前调用 game-build 做与最大风险匹配的白盒候选;试玩后把偏差交回 design owner
局部修订并重放受影响路径,不能用文本模拟结果冒充空间或操作验证。
调用 game-art-direction 生成 ART_DIRECTION.md;只有目标成色需要时再制作视觉目标包。
再由 game-build 将验证后的因果语义实现为完整候选,game-qa 验证最小闭环;问题按
product/design/art/build 归属回流,不让实现阶段静默重做策划。
语言与文化
接受任意语言小说。产物使用用户指定语言,未指定时跟随对话语言;原文证据保留原语言,跨语言只补
决策所需译文并维护一个术语表。原作文化语境、目标市场和界面语言分别记录,不用逐字翻译替代本地化判断。
When it activates Automatically, when a task matches.
Use for novel to game, story to game, book to game, adapt this novel into a game, turn this book into a playable prototype, make an interactive story or text adventure from this novel. NovelToGame 总入口。把任意语言的原始小说、拆文库或
Track record Benchmark 19 / 22
test cases passed, vs 11 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v5 — 9/23/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 9/23/2026Version v2Bundled 2 files