New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Forgecad Reconstruct From Images

by ForgeCAD in ForgeCAD/forgecad-public-kit

Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.

MITAuto-check passedDevelopment

Install Forgecad Reconstruct From Images

skills CLI
$ npx skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-from-images -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ForgeCAD/forgecad-public-kit forgecad-reconstruct-from-images --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ForgeCAD/forgecad-public-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/forgecad-reconstruct-from-images .claude/skills/forgecad-reconstruct-from-images && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
forgecad-reconstruct-from-images
GitHub stars
941
Token cost
~1.3k tokens
SKILL.md length
635 words
Files
3 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.

  • Works in 9 steps: Stage references in… → Read each image as evidence, recording:… → Write a Real Object Brief — a hard gate… → …
  • Development work in your project
  • SKILL.md covers Companion Skills, Core Rule, Workflow and Comparison Boards, plus 1 more section
  • Runs Python scripts from its folder; calls uv

What it does

Forgecad Reconstruct From Images is an agent skill from ForgeCAD/forgecad-public-kit. Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/compare_images.py`).

It sits in Development. The repository describes itself as: Public companion kit for ForgeCAD: examples, agent skills, docs links, and issue tracking. The hosted CAD app and core source live elsewhere. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/forgecad-reconstruct-from-images”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Stage references in /tmp/-replicate/refs, keeping originals and adding view names where possible (front, side, rear-iso, top, detail).
  2. Read each image as evidence, recording: visible facts; scale cues; camera cues; unknowns (hidden/occluded geometry); conflicts across…
  3. Write a Real Object Brief — a hard gate before modeling: (a) artifact identity + operating story; (b) assumed scale and units; (c) process…
  4. Build a coarse 3D blockout — model the object, not the image: large volumes, axes, symmetry, side depth, rear form, underside, hidden…
  5. Calibrate one camera per usable reference, only after the blockout makes sense from canonical views. Use the object center as target…
  6. Render comparison boards: render the model from each calibrated reference camera and place it next to the original. Never compare from…
  7. Iterate one class of change at a time, in order: object hypothesis → major proportions → canonical geometry → camera → details →…
  8. Use every image as a constraint. Never pick one target image and ignore the rest: assign each image a camera, evidence list, and…
  9. Validate the final object: forgecad run, reference comparison boards, canonical renders, and targeted inspections via…

What it can do on your machine

Read from SKILL.md and the folder at commit 7523f68. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Forgecad Reconstruct From Images loads about 1.3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 635 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ForgeCAD/forgecad-public-kit at commit 7523f68, republished under its MIT licence (© ForgeCAD). 635 words, ~1,261 tokens.

Download SKILL.mdSave it as .claude/skills/forgecad-reconstruct-from-images/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
forgecad-reconstruct-from-images
description
Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.
forgecad-public
true

Reconstruct From Images

The reference image is evidence, not the deliverable. The deliverable is a real parametric object that holds up from front, back, side, top, bottom, and reference camera views — a model that matches one image but falls apart from other angles has failed, even if the comparison board looks close. Cutaway, sectioned, exploded, or transparent references are evidence about the complete object: build the closed artifact and recreate explanatory views with viewer/inspection tools (the main forgecad skill's closed-artifact rule applies).

Companion Skills

  • forgecad — API docs, model authoring, renderer behavior.
  • forgecad-design-spec — when the images underdetermine artifact family, process posture, scale, operating story, or validation boundary.
  • forgecad-build-model — file placement, project structure, decomposition, definition of done.
  • forgecad-inspect-model — pre-delivery inspection for multi-part, internal, mechanical, thin-wall, or fit-sensitive objects.

Core Rule

Infer the real object before matching any camera — identity, manufacture, scale, what hidden sides must contain, what geometry must exist for physical coherence. Reference matching is a validation step after the object exists; never start by chasing pixels or the prettiest view.

Workflow

  1. Stage references in /tmp/<slug>-replicate/refs, keeping originals and adding view names where possible (front, side, rear-iso, top, detail).
  2. Read each image as evidence, recording: visible facts; scale cues; camera cues; unknowns (hidden/occluded geometry); conflicts across images or stylization.
  3. Write a Real Object Brief — a hard gate before modeling: (a) artifact identity + operating story; (b) assumed scale and units; (c) process posture + part/BOM boundary (real geometry vs purchased vs ghost vs omitted); (d) inferred hidden-side geometry + expected canonical front/back/left/right/top/bottom forms; (e) validation views and inspection evidence. Use forgecad-design-spec when these are underdetermined.
  4. Build a coarse 3D blockout — model the object, not the image: large volumes, axes, symmetry, side depth, rear form, underside, hidden continuations. Render canonical views before any reference-camera comparison. Follow forgecad-build-model for project structure.
  5. Calibrate one camera per usable reference, only after the blockout makes sense from canonical views. Use the object center as target; estimate azimuth/elevation/distance/FOV from visible faces and perspective cues; use orthographic when parallel edges stay parallel with no perspective convergence.
  6. Render comparison boards: render the model from each calibrated reference camera and place it next to the original. Never compare from memory.
  7. Iterate one class of change at a time, in order: object hypothesis → major proportions → canonical geometry → camera → details → presentation. If improving one reference view makes another view or a canonical render worse, the object hypothesis is wrong — fix the model, not the camera illusion.
  8. Use every image as a constraint. Never pick one target image and ignore the rest: assign each image a camera, evidence list, and confidence; optimize one shared geometry against the whole set; state how distorted or decorative images were weighted.
  9. Validate the final object: forgecad run, reference comparison boards, canonical renders, and targeted inspections via forgecad-inspect-model.
Show full SKILL.md (169 more words)Show less

Comparison Boards

Render with exact --camera specs (see the forgecad CLI doc for supported forms). If exact full camera specs do not render, fix the renderer before continuing — never substitute guesses from default iso renders.

Build side-by-side boards with the bundled self-contained uv helper (installs Pillow on demand). Resolve scripts/compare_images.py relative to the installed forgecad-reconstruct-from-images skill directory:

bash
uv run <skill-dir>/scripts/compare_images.py refs/front.png render-front.png compare-front.png

Use --fit contain (default); use --fit cover only when both images already share the same crop and aspect. Run with --help for other options.

Done and Report

Done means: a written Real Object Brief; real parametric geometry (not a billboard, facade, or one-view shell) that makes sense from all canonical views; honest hidden-side assumptions where images are silent; passes forgecad run; comparison boards plus canonical renders exist. The result fails if it only works from the original camera — one render is never enough; expect several render/compare/inspect iterations.

Report: model path; Real Object Brief summary + assumptions; per-reference camera spec, weighting, and board path; canonical render paths; inspection evidence; remaining mismatches or downgraded confidence.

© ForgeCAD, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/forgecad-reconstruct-from-images of ForgeCAD/forgecad-public-kit.

  • SKILL.md
  • agents/openai.yaml
  • scripts/compare_images.py

Open the folder on GitHubat commit 7523f68

Compare with similar skills

Forgecad Reconstruct From Images next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Forgecad Reconstruct From Images compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Forgecad Reconstruct From Images this skillForgeCAD/forgecad-public-kit941—~1.3kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from ForgeCAD/forgecad-public-kit

All 10 skills in this repo

  • Forgecad Verify Mujoco

    ForgeCAD/forgecad-public-kit

    Verify a ForgeCAD MJCF export in MuJoCo with dynamics, contacts, controls, joint travel, and rendered evidence before calling it simulation-ready.

    941 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Forgecad Design Spec

    ForgeCAD/forgecad-public-kit

    Create a ForgeCAD design brief, HLD, or LLD before coding by walking through use, assembly, interfaces, decisions, and verification.

    941 GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Forgecad

    ForgeCAD/forgecad-public-kit

    ForgeCAD model authoring, editing, debugging, and execution guidance for .forge.js, SVG-import, assembly, and CLI workflows.

    941 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Forgecad Grade Model

    ForgeCAD/forgecad-public-kit

    Grade a ForgeCAD or CAD-as-code model against a requirement, brief, prompt, reference, or acceptance criteria with evidence and a 0-10 score.

    941 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Forgecad Image Prompt

    ForgeCAD/forgecad-public-kit

    Write builder-honest AI image prompts from a concrete ForgeCAD model, build brief, HLD, or LLD without hiding how the artifact is built.

    941 GitHub stars~981 tokensUpdated 3 mo ago
    Auto-check passed

  • Forgecad Inspect Model

    ForgeCAD/forgecad-public-kit

    Select, run, and interpret ForgeCAD inspection evidence for collisions, sections, wall thickness, components, masks, depth, normals, surface continuity, and fit.

    941 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Forgecad Reconstruct From Images

What does Forgecad Reconstruct From Images do?

Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade. Forgecad Reconstruct From Images is an agent skill from ForgeCAD/forgecad-public-kit. Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.

When should I use Forgecad Reconstruct From Images?

Forgecad Reconstruct From Images fits situations like: development work in your project.

How do I install Forgecad Reconstruct From Images in Claude Code?

Run `npx skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-from-images -a claude-code`. Or copy the skill folder (skills/forgecad-reconstruct-from-images in ForgeCAD/forgecad-public-kit) into .claude/skills/forgecad-reconstruct-from-images in your project. Claude Code loads it when a task matches its description.

How do I install Forgecad Reconstruct From Images in Codex?

Run `npx skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-from-images -a codex`. Or copy the skill folder (skills/forgecad-reconstruct-from-images in ForgeCAD/forgecad-public-kit) into .agents/skills/forgecad-reconstruct-from-images in your project. Codex loads it when a task matches its description.

Can I use Forgecad Reconstruct From Images in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-from-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forgecad-reconstruct-from-images, .gemini/skills/forgecad-reconstruct-from-images, .github/skills/forgecad-reconstruct-from-images and .opencode/skills/forgecad-reconstruct-from-images in your project.

What does Forgecad Reconstruct From Images need to run?

Going by SKILL.md and its folder, Forgecad Reconstruct From Images needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Forgecad Reconstruct From Images access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Forgecad Reconstruct From Images safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Forgecad Reconstruct From Images use?

Forgecad Reconstruct From Images is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Forgecad Reconstruct From Images use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Forgecad Reconstruct From Images?

Skills that share tags, products or a category with Forgecad Reconstruct From Images: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Forgecad Reconstruct From Images?

ForgeCAD (a GitHub organization) maintains it in ForgeCAD/forgecad-public-kit, which has 941 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on June 15, 2026.

Source: ForgeCAD/forgecad-public-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.