live2d-layering SKILL.md skillA
live2d-layering from wu-tian807/astralayering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wu-tian807/astralayering/live2d-layering@git:20261019.7a3a2cePins git:20261019.7a3a2ce in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wu-tian807/astralayering
- Path
archive/skills/live2d-layering/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261019.7a3a2ce, committed Oct 19, 2026
- Size
- 7,473 bytes
- Repository stars
- 66
- License
- LGPL-3.0
根据角色参考图制作或续跑可编辑、具备隐藏补全的分层 SVG 素体；按节点配置调度参考准备、部件制作和声明的独立审查。用于角色分层、指定部件细化或已有案例续跑。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 人物分层工作流调度规则 本文件只规定通用执行与交接方式；任务顺序由编号目录决定，输入、选项和产物由各级 `流程.yaml` 声明，具体制作要求写在对应节点提示词中。 任务资料以本 `SKILL.md` 所在目录为根。通用工具放在本技能的 [tools](tools/readme.md)，仅供单个步骤使用的工具放在该编号步骤的 `tools/`；不引用技能目录之外或另一技能内的资源。所有 `流程.yaml` 中的 `run`、`asset`、`prompt` 都从本技能根目录解析，路径不得越过 `SKILL.md` 所在目录。总控解析为绝对路径后交接，用户产物仍写入工作根目录。 ## 调用与输入 读取[根配置](流程.yaml)，绑定用户提供的必要素材和绝对输出目录；仅集中询问必需项中的缺项，可选素材按实际提供情况绑定。输入文件与技能资料只读，产物和临时文件写入本轮工作根目录；用户仅要求规划或修改流程时，不启动制作任务。 已有选项从工作根目录的平级 `options.json` 读取，按根配置核对类型；用户本轮明确选择优先，由负责判断的 worker 写入。旧运行仅有 `options.yaml` 时，由该 worker 按[选项工具说明](tools/readme.md)迁移已有值。用户可以指定起止节点；默认执行实际建立的编号节点。 ## 读取与绑定 - 按目录编号逐级展开、按数字排序，例如 `1.2` 在 `1.10` 前；同编号且带 `.parallel.` 的节点并行，全部完成后继续下一编号。容器只组织子任务，不额外执行父任务。 - 每个节点先读取自己的 `流程.yaml`；实际任务显式写 `run`，其值是从技能根目录到执行目录的路径，再读取该目录提示词与 `.model`。条件任务把 `run` 放在执行分支；单任务循环写 `foreach.run` 指向执行目录，逐项执行任务及其 review，不重新进入自身循环。无 `run` 的纯容器仅展开编号子步骤，输出别名分支仅发布路径；不能按目录里的模型文件隐式派发。 - 普通 `inputs.<名称>` 引用根输入；循环内部引用当前循环已绑定的输入。`nodes.<id>.<名称>` 引用已完成节点产物，`asset` 从技能根目录解析，普通产物路径相对工作根目录；`required: false` 缺项标为“未提供”。 - `if / then / else` 按声明条件选择分支，分支继承节点输入并加入自身输入。条件读取已绑定输入或 `options.<名称>`；字段缺失或类型错误时交原负责 worker 补正，不自行猜测。 - 输出中的 `inputs.*`、`nodes.*` 发布已绑定的路径；其他输出相对工作根目录。分支另行声明保存路径和格式时，按声明保存复用输入。 …
Read the whole file at its exact version.
How to install
mdr add wu-tian807/astralayering/live2d-layering@sha256:2f91edcd0cd37beaThe line at the top of this page pins the label git:20261019.7a3a2ce, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6ondzpccgwzko7sq)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 19, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7473 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wu-tian807/astralayering · 66 stars · license LGPL-3.0 · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6ondzpccgwzko7sq GET https://markdownregistry.com/api/v1/resolve?ref=wu-tian807/astralayering/live2d-layering GET https://markdownregistry.com/api/v1/blob/2f91edcd0cd37bea20282dc638d7b4da35dd160a2ead0e71df1f27a9a6b1c420
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.