Skip to content

스킬 검색.../

Agent Skill Search Engine

검색

검색
카테고리
직업

About

About
Privacy
Terms

© 2026 Skills Pool. All rights reserved.

Cadquery Builder | Skills Pool

스킬 파일

Cadquery Builder

Use this skill when you need to implement a 3D model from the drawing image with optional preprocessed views and verifier guidance.

neka-nat5 스타2026. 4. 7.

직업
카테고리: 머신러닝

스킬 내용

Goal

Produce executable CadQuery code and CAD artifacts.

Required inputs

/input/reference.png

Optional inputs

/preprocessed/outline_only.png
/preprocessed/*.png
/review/fix_plan.json
/templates/model_template.py

Required outputs

/generated/model.py
/artifacts/model.step

Optional outputs

/artifacts/model.stl
/artifacts/projections/front.svg
/artifacts/projections/top.svg
/artifacts/projections/right.svg
/artifacts/projections/front.png
/artifacts/projections/top.png
/artifacts/projections/right.png
/artifacts/build_report.json

관련 스킬

빠른 설치

Cadquery Builder

npx skillvault add neka-nat/neka-nat-agent3dify-src-agent3dify-resources-skills-builder-skill-md

Skill 다운로드 저장소 열기

작성자: neka-nat
스타: 5
업데이트: 2026. 4. 7.
직업

이 페이지의 내용

Workflow

Read /input/reference.png with read_file
Read optional preprocessed images when they exist
If /review/fix_plan.json exists, read it before revising the model and treat it as the detailed source of revision edits
Either start from /templates/model_template.py or write from scratch
Write /generated/model.py
Execute: python generated/model.py --out-dir artifacts
If it fails, inspect the error, patch the code, and rerun
First make sure /artifacts/model.step is produced
Add STL, projections, or reports only when they are clearly useful for the next step

Important

Use absolute paths with file tools, for example /input/reference.png and /generated/model.py
Use relative paths only for shell execution commands
Treat the drawing image as the primary source of truth
Preprocessed images are optional guidance, not mandatory prerequisites
If /review/fix_plan.json exists, it is the primary source for detailed revision targets
The supervisor task description may summarize the current revision focus, but it is not a substitute for reading /review/fix_plan.json
A first working STEP export matters more than polished reporting or full projection coverage
The template is optional. Do not force yourself to fit the shape into it if starting fresh is simpler.
Do not return success without actually executing the script

Required inputs

03Optional inputs

04Required outputs

05Optional outputs

Mechanical Drafters

Continuous Learning V2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Continuous Learning V2

Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.

Continuous Learning V2

훅을 통해 세션을 관찰하고, 신뢰도 점수가 있는 원자적 본능을 생성하며, 이를 스킬/명령어/에이전트로 진화시키는 본능 기반 학습 시스템. v2.1에서는 프로젝트 간 오염을 방지하기 위한 프로젝트 범위 본능이 추가되었습니다.

Continuous Learning

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

Continuous Learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Pytorch Patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Mechanical Drafters