lora-pipeline SKILL.md skillB
lora-pipeline from rinne414/lora-training-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add rinne414/lora-training-skill/lora-pipeline@git:20261026.def0accPins git:20261026.def0acc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- rinne414/lora-training-skill
- Path
lora-pipeline/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261026.def0acc, committed Oct 26, 2026
- First version recorded
- Jul 27, 2026
- Size
- 10,122 bytes
- Repository stars
- 13
- License
- MIT
Build an Anima LoRA from a single-character or style name, from Danbooru collection through curation, section-ordered WD14 captions, dataset checks, confirmed training, fixed-seed checkpoint validation, and a staged Civitai draft. Use for requests such as make a LoRA of X, collect images and train a character LoRA, train and upload to Civitai, or build a dataset from scratch and publish. Delegate training to lora-trainer and structural checks to dataset-doctor; never train without confirmation…
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
# lora-pipeline — 从「角色名字」到「Civitai 草稿」的端到端流水线 把「帮我做一个 X 的 LoRA」变成一条受控流水线:**收图 → 精修 → 打标/复查 → 体检 → 训练 → 验证 → 打包上传(停在 Draft)**。本 skill 是**总指挥**——真正的训练交给 [`lora-trainer`](../lora-trainer/SKILL.md),质量交给 [`dataset-doctor`](../dataset-doctor/SKILL.md),自己负责把两端(收集/精修/打标 和 验证/发布)接起来。默认 **Anima 优先**。 > **两道人类闸门,不可移动:** > 1. **训练前必须出「确认卡」** 并取得明确同意(继承 `lora-trainer` 的规则)——训练慢、占显存、难回退。 > 2. **绝不自动发布。** 全流程可以自动到 **Draft(草稿)**为止;点 Publish 是公开行为、会被索引,**必须由用户亲自点**。没有用户当场明说「发布」,绝不传 `--publish`。 ## 依赖的本地工具(环境相关) 这些是外部本地工具；表中路径/端口是惯例默认值，脚本都可用 flag/env 覆盖。契约细节见两份参考文档。 | 工具 | 用途 | 默认位置 | |---|---|---| | DanbooruDownload | 按 tag 下载图 | `C:\tools\DanbooruDownload`(env `DANBOORU_DL_DIR`) | | sd-image-sorter | WD14 打标 FastAPI | [Rinne414/sd-image-sorter](https://github.com/Rinne414/sd-image-sorter),`:8487`,兼容版本见 `collect-and-tag.md` | | SD-Trainer | 训练后端 mikazuki API | `http://127.0.0.1:28000`,`run_gui.bat` 启动 | | ComfyUI | 验证出图 | `http://127.0.0.1:8188`(env `COMFY_URL`) | | civitai-uploader | 填 Civitai 上传向导 | `<repo>\tools\civitai-uploader`(安装见其 README) | `<PY>` = 任意带 Pillow 的 Python 3.10+(如 `<DanbooruDownload>\.venv\Scripts\python.exe`)。管线脚本在 `scripts/`,纯 stdlib + Pillow。 ## 工作目录布局 …
Read the whole file at its exact version.
How to install
mdr add rinne414/lora-training-skill/lora-pipeline@sha256:ccdae092fd6b4a90The line at the top of this page pins the label git:20261026.def0acc, 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_udhiegqnjl77vvc4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 27, 2026 and Oct 26, 2026, about one every 30 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.def0acc latest | 2026-10-26 | def0acc | 10,122 B | B | view · diff |
| git:20260727.7eaa03a | 2026-07-27 | 7eaa03a | 9,818 B | B | view · diff |
| git:20260727.8262efb | 2026-07-27 | 8262efb | 9,915 B | B | view · diff |
| git:20260727.807afb6 | 2026-07-27 | 807afb6 | 9,913 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:28000)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10122 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
rinne414/lora-training-skill · 13 stars · license MIT · pushed 2026-10-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_udhiegqnjl77vvc4 GET https://markdownregistry.com/api/v1/resolve?ref=rinne414/lora-training-skill/lora-pipeline GET https://markdownregistry.com/api/v1/blob/ccdae092fd6b4a903a7a0784201db71ab8d0f91a4d634371b7bc40e19472bc92
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.