Token导航 LogoToken导航

Agent Skill · 效率

hitem3d(hitem3d 图像)

hitem3d 用于处理图像、截图、视觉识别或图片素材相关工作,适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

hitem3d 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在效率类的 21,003 个 Skill 里排第 2,863。

总安装 21,336周安装 898GitHub Stars 1下载 7,471核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.2.2

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hitem3d(hitem3d 图像)
来源仓库:https://github.com/lihuihui-bj/hitem3d
安装命令:
openclaw skills install hitem3d
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install hitem3d

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

将图像转换为生产级 3D 模型,支持产品镜头与概念艺术处理。适用于电商建模、游戏资产或工业设计前期制作。输入图片需清晰无遮挡,人物肖像需获得授权。hitem3d 属于效率类 Skill,可作为该场景下的辅助能力补充。输出模型可用于商业用途,但应遵守平台分发政策。建议预览多角度渲染效果,确保几何精度满足需求。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install hitem3d;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

hitem3d 怎么安装?

在终端执行 openclaw skills install hitem3d。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

hitem3d 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

hitem3d 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

hitem3d 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

hitem3d 用的人多吗?

公开数据是累计安装 21,336 次,近一周安装 898 次,下载 7,471 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

hitem3d 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
hitem3d

hitem3d 图像 · 本页

21,3361接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
hitem3d
description
Generate production-grade 3D models from images with the Hitem3D API. Use when the user wants to turn product shots, concept art, character images, portraits, or multi-view image sets into downloadable 3D assets; create printable STL files; export AR-ready GLB/USDZ; batch-convert folders of images; check Hitem3D balance/credits; or wait for and download finished task results. Supports intent-based mode selection, cost-aware defaults, multi-view vs batch routing, portrait/bust generation, quality/format control, and end-to-end submit→wait→download workflows.
metadata
{"openclaw":{"emoji":"🧊","homepage":"https://hitem3d.ai","requires":{"bins":["curl","python3","base64"],"env":["HITEM3D_AK","HITEM3D_SK"]},"primaryEnv":"HITEM3D_AK"}}

Hitem3D

Use this skill to turn images into downloadable 3D models via scripts/hitem3d.sh.

Use the script

Resolve all relative paths against this skill directory.

  • Script: scripts/hitem3d.sh
  • API reference: references/api.md
  • Product guide / positioning: references/product-guide.md
  • ClawHub-style description: references/clawhub-description.md
  • Release checklist: references/release-checklist.md
  • Live validation notes: references/live-validation.md

If the user asks for a normal one-off generation, prefer the full pipeline:

  1. submit task
  2. wait for completion
  3. download result
  4. report output path, format, model, and estimated credit cost

Do not leave the user with only a task ID unless they explicitly want async handling.

Operator standard

Act like a production 3D operator, not a thin API wrapper.

  • Infer likely intent from the request instead of asking obvious questions.
  • Distinguish single-image, portrait, multi-view, and batch every time.
  • Prefer finishing the workflow over handing back raw JSON.
  • Surface cost, output path, format, and caveats in plain language.
  • Stop early on ambiguous expensive jobs, invalid inputs, or unsafe assumptions.
  • Never echo secrets, bearer tokens, or raw Authorization headers.

Required setup

Runtime requirements

  • Binaries: curl, python3, base64
  • Required env vars: HITEM3D_AK, HITEM3D_SK
  • Optional env var: HITEM3D_TOKEN

The user must provide credentials through environment variables:

export HITEM3D_AK="your_access_key"
export HITEM3D_SK="your_secret_key"

If credentials are missing, stop and tell the user exactly which variables are not set.

Default operating policy

When the user says “turn this image into 3D” without more detail, use these defaults:

  • model: hitem3dv2.0
  • request type: 3 (geometry + texture)
  • resolution: 1536
  • format: 2 (GLB)
  • face count: unset

Why: this is the best general-purpose quality/output tradeoff.

Choose the right mode

Single-image general object

Use when the input is one product shot, concept image, illustration, object render, furniture photo, toy, packaging, or other non-portrait asset.

Default command pattern:

scripts/hitem3d.sh run input.png

Portrait / bust generation

Use portrait models when the user explicitly wants a person, face, bust, avatar head, or half-body likeness.

Preferred defaults:

  • model: scene-portraitv2.1
  • resolution: 1536pro
  • format: GLB unless user asks otherwise

Command pattern:

scripts/hitem3d.sh run face.jpg --model scene-portraitv2.1 --resolution 1536pro

3D printing

If the user mentions 3D printing, printer, slicer, or STL, prefer:

  • format: 3 (STL)
  • request type: 1 for mesh-only when texture is irrelevant
  • optionally set higher face count for smoother geometry

Command pattern:

scripts/hitem3d.sh run object.png --format 3 --type 1 --face 500000

AR / Apple preview

If the user mentions Apple AR, Quick Look, Vision Pro, AR preview, or iPhone preview, prefer format 5 (USDZ).

Fast / cheap draft

If the user wants a rough draft, cheap test, or low-cost preview, prefer:

  • model: hitem3dv1.5
  • resolution: 512
  • type: 1 or 3 depending on whether texture matters

Multi-view reconstruction

Use multi-view when the user provides 2-4 images of the same subject from different angles.

Use:

  • generate-multi or run-multi
  • pass a bitmap describing which views are present

Bitmap order is:

  • front
  • back
  • left
  • right

Examples:

  • front + left = 1010
  • front + back + left + right = 1111
  • front + right = 1001

Do not use multi-view mode for unrelated images.

Batch processing

Use batch mode only when the user wants to process many separate images independently. Do not confuse batch with multi-view.

Batch means:

  • one task per image
  • submit all
  • wait/download each
  • return a concise summary of successes/failures and output paths

Cost policy

Before batch jobs or obviously expensive jobs, tell the user the expected cost and ask for confirmation.

Must confirm before proceeding when either is true:

  • batch job with more than 5 images
  • likely cost exceeds 100 credits total
  • the request implies repeated retries, alternative variants, or multiple output formats that would multiply spend

For one-off standard jobs, confirmation is not required unless the user has asked to be cost-cautious.

Reference pricing in references/api.md.

Practical heuristics:

  • cheapest draft: hitem3dv1.5 + 512 + mesh-only = 5 credits
  • default general result: hitem3dv2.0 + 1536 + textured = 50 credits
  • premium portrait / 1536pro textured = about 70 credits

When estimating cost, say whether the number is per task or total batch cost.

Output policy

Prefer saving downloads into a user-relevant folder under the current workspace unless the user provides a destination.

Suggested defaults:

  • one-off tasks: ./output/hitem3d/
  • batch tasks: ./output/hitem3d/<batch-name>/

When reporting completion, include:

  • task ID
  • final status
  • saved file path
  • output format
  • model used
  • resolution
  • estimated credit cost

If the API returns a preview/cover URL, include it when useful.

Common commands

Check balance

scripts/hitem3d.sh balance

Submit only

scripts/hitem3d.sh generate photo.png

Full one-shot pipeline

scripts/hitem3d.sh run photo.png

For long jobs, explicitly raise the timeout instead of assuming 10 minutes is enough:

scripts/hitem3d.sh run photo.png --timeout-seconds 3600 --poll-seconds 8

Full one-shot pipeline with custom options

scripts/hitem3d.sh run photo.png --model hitem3dv1.5 --resolution 1024 --format 3 --type 1 --download-dir ./output/hitem3d/

Multi-view submit

scripts/hitem3d.sh generate-multi front.png left.png --views 1010

Multi-view full pipeline

scripts/hitem3d.sh run-multi front.png back.png left.png right.png --views 1111 --model hitem3dv2.0 --download-dir ./output/hitem3d/multi/

Long-running jobs

If a job is likely to take a while, set explicit polling and timeout values:

scripts/hitem3d.sh run-multi front.png left.png --views 1010 --timeout-seconds 3600 --poll-seconds 8

Wait for an existing task and download

scripts/hitem3d.sh wait <task_id> --download ./output/hitem3d/

For slow tasks:

scripts/hitem3d.sh wait <task_id> --download ./output/hitem3d/ --timeout-seconds 3600 --poll-seconds 8

Batch folder processing

scripts/hitem3d.sh batch ./images --glob '*.png' --download-dir ./output/hitem3d/batch/

Decision rules

If the user does not specify format:

  • use GLB by default
  • use STL for 3D printing intent
  • use USDZ for Apple AR intent

If the user does not specify model:

  • use scene-portraitv2.1 for portraits
  • otherwise use hitem3dv2.0

If the user does not specify resolution:

  • use 1536 for general work
  • use 1536pro for portrait premium output
  • use 512 for cheap drafts

If the user says “highest quality”:

  • general object: hitem3dv2.0 + 1536
  • portrait: scene-portraitv2.1 + 1536pro
  • mention expected credit usage before running

Failure handling

Missing credentials

Stop and ask the user to set HITEM3D_AK and HITEM3D_SK.

Bad input images

Reject unsupported formats and files larger than 20MB before calling the API.

Auth failure

Tell the user credentials are invalid or expired. Do not keep retrying.

Generation failure

If API error is 50010001, tell the user the image likely could not be parsed and credits should be refunded automatically.

Token expiry

The script auto-fetches tokens. Retry once if a token-related request fails.

URL expiry

If the returned download URL has expired, re-query task status to fetch a fresh URL before declaring failure.

Multi-view mismatch

If the user labels images as multi-view but the set is missing the front view, warn that Hitem3D expects the front view and that results may fail or degrade.

Security rules

  • Never print or store AK/SK in user-visible output.
  • Treat callback URLs as advanced usage; do not invent or auto-fill webhooks.
  • Do not claim full production validation unless live API runs have been completed with real credentials.
  • If credentials are unavailable, say the skill is design-validated but not fully live-validated.

Download URL expiry

If the result URL expired, re-query task status to obtain a fresh result URL if available, then download again.

Unsupported combination

Reject obviously bad combos before calling the API, especially:

  • request type 2 with hitem3dv2.0
  • multi-view without a valid 4-bit view bitmap
  • face count outside 100000-2000000

Notes for good judgment

  • A user saying “folder of 30 product renders” means batch, not multi-view.
  • A user sending front/back/left/right of the same object means multi-view, not batch.
  • For printing intent, geometry matters more than texture.
  • For showcase/demo intent, textured GLB is usually the right default.
  • Prefer completing the full task over dumping raw API responses.
  • Keep user-visible replies concise and outcome-focused.

平台分布

OpenClaw

76.78%
按下载量换算5,736

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills