跳到正文
cccskills
免费在 GitHub 公开

scan-ingest

Preserve and inventory scan archives while retaining capture variants, hashes, calibration, and frame provenance.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Use for ZIP or extracted scan intake. Copy archives without altering them, hash source files, and produce an inventory and frame index. Preserve raw and cleaned depth plus raw and corrected poses as explicit variants; retain units, calibration, native pixels, frame IDs, and capture coordinates. Never overwrite source material with a derived product.

Read evidence-workflow.md for provenance and formats.md when emitting records. Use package scripts with caller supplied paths; never bake in an address, home directory, or capture index.

Run scripts/ingest.py with the ZIP or extracted directory and project paths. Directory intake reads the existing keyframes/ in place and writes its index and contact sheets outside the source directory; no wrapper script or ZIP conversion is needed. Inspect its actual inventory and variant counts, including any failed audit. Use the returned capture root when a ZIP contains an enclosing directory. Inspect the overview and every full contact sheet, and reopen native frames for important boundaries or uncertain identities. A clean inventory establishes that paired files can be read, not that every room was examined.

Run scripts/reference.py with explicit raw/Clean and raw/corrected choices. Check finite coordinates, confidence/range filtering and source-frame/pixel identity. Keep the raw source untouched and the derived reference separately named. Repeated ingestion should verify the same bytes and refuse conflicting files; investigate a refusal instead of deleting the evidence.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Build and review evidence tagged Blender architectural candidates, preserve unrelated scene content, and produce requested photographic materials, stills and portable model deliveries.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

Inspect native RGB, depth, confidence, calibration, and poses to make finite, source traceable reference points and surface measurements.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

Fit and independently validate rigid scan alignment from named, source traceable correspondences.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

Coordinate evidence based reconstruction from scans, photos, plans, and measurements into a reviewable Blender architectural model, with photographic appearance, renders and portable browser delivery when requested.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

Use when cataloging or annotating visible construction in photographs or scan RGB, especially before registration or while the base model may be replaced.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

Collect and verify Google Street View exterior references for a building reconstruction, preserving panorama identity, imagery dates, attribution and viewpoint separately from calibrated scan evidence.

中文简介正在准备中。当前显示原文说明。

obra/scan-to-model72026年9月27日 更新

查看 obra 的全部技能

报告此技能的问题