Individual skill

tavern2agent

0upvotes

用户提供 SillyTavern 角色卡（PNG/JSON）并要求转换、迁移、移植到 pi coding agent 时使用；覆盖纯 prompt、世界书、MVU、骰子、战斗、好感度、经济、隐藏信息、多 agent 场景。

SKILL.md

Read pinned source

Source commit 601b1c3f447ae5472e7bc5b59fc17771129293c1

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 119
Repository last updated: Jul 11, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.gitignoreasset · 29 bytes
LICENSEasset · 1,065 bytes
README.mddoc · 5,689 bytes
README_ZH.mddoc · 4,893 bytes
SKILL.mdcore · 11,825 bytes
SKILL.mdcore · 11,825 bytes
SKILL.mdcore · 11,825 bytes
docs/developing-cards.mddoc · 2,639 bytes
docs/epistemic-audit-2026-07.mddoc · 12,047 bytes
docs/tooling.mddoc · 1,713 bytes
references/card-ir.mddoc · 4,034 bytes
references/codeact.mddoc · 3,280 bytes
references/data-layer.mddoc · 4,517 bytes
references/decision-tree.mddoc · 4,799 bytes
references/design-principles.mddoc · 4,241 bytes
references/engineering-discipline.mddoc · 6,556 bytes
references/event-packs.mddoc · 5,141 bytes
references/evented-runtime.mddoc · 8,481 bytes
references/multi-agent-architecture.mddoc · 11,682 bytes
references/mvu-mapping.mddoc · 9,569 bytes
references/pi-integration.mddoc · 7,297 bytes
references/prompt-composition.mddoc · 10,119 bytes
references/script-analysis.mddoc · 2,499 bytes
references/setup.mddoc · 2,534 bytes
references/state-schema-migrations.mddoc · 2,771 bytes
references/storytelling.mddoc · 1,314 bytes
references/tool-abstraction.mddoc · 21,580 bytes
references/ts-engine.mddoc · 8,816 bytes
references/two-pass-rendering.mddoc · 11,692 bytes
references/validation.mddoc · 13,485 bytes
scripts/extract_card.pyruns · 9,752 bytes
scripts/get_entry.pyruns · 2,087 bytes
scripts/list_entries.pyruns · 3,242 bytes
scripts/start.shruns · 3,784 bytes

Read excerpt


# Tavern → Agent

把 SillyTavern 卡编译成 pi-native 互动叙事 runtime。还原作者想做的游戏：prompt 描述世界，领域事件改变世界，engine/reducer 维护正确性，session 保存存档。不复刻 ST 宏、COT、JSON Patch、HTML 状态栏，不把状态栏字段搬进 `patch_state`。

## 开工

1. 解包卡片，确认输出目录。目录存在时先问：覆盖、增量、另建？
2. 先读 `references/evented-runtime.md`、`references/card-ir.md`、`references/event-packs.md`、`references/design-principles.md`。
3. 全量审计 `data` 字段、世界书、TH scripts、regex scripts、开场白。
4. 先输出或草拟 `world-data/card-ir.json`；不要直接从原卡文本生成代码。
5. 从 IR 形成 Runtime Plan：archetype、event packs、state roots、visibility policy、fact sources、tool surface、subagent roles、prompt modules、validation plan。
6. 写代码前先给用户看 Runtime Plan；复杂卡还要给 state schema、event catalog、reducer/API 清单、事实源边界和子代理边界。

增量更新：先看 `git log -20` + `git diff`。只改本次需求相关文件；不碰 `sessions/`、`runtime/`、`.pi/agent/`。