Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
Find existing PartCAD parts and assemblies in the catalog that match a natural-language query, using the PartCAD CLI (pc search), then present the matches and optionally inspect or render a chosen…
$ npx skills add partcad/partcad --skill search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install partcad/partcad search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai-agents/common/skills/search .claude/skills/search && rm -rf skills-srcUse ~/.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/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .claude/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add partcad/partcad --skill search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install partcad/partcad search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ai-agents/common/skills/search .agents/skills/search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .agents/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add partcad/partcad --skill search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install partcad/partcad search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ai-agents/common/skills/search .cursor/skills/search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .cursor/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/partcad/partcad.git --path ai-agents/common/skills/search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add partcad/partcad --skill search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install partcad/partcad search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ai-agents/common/skills/search .gemini/skills/search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .gemini/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install partcad/partcad searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add partcad/partcad --skill search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .github/skills && cp -r skills-src/ai-agents/common/skills/search .github/skills/search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .github/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add partcad/partcad --skill search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install partcad/partcad search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/partcad/partcad.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ai-agents/common/skills/search .opencode/skills/search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "search" agent skill from https://github.com/partcad/partcad/tree/devel/ai-agents/common/skills/search into .opencode/skills/search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
searchFind existing PartCAD parts and assemblies in the catalog that match a natural-language query, using the PartCAD CLI (pc search), then present the matches and optionally inspect or render a chosen…
Search is an agent skill from partcad/partcad. Find existing PartCAD parts and assemblies in the catalog that match a natural-language query, using the PartCAD CLI (pc search), then present the matches and optionally inspect or render a chosen one. Use for /pc:search or when the user asks to search, find, look up, or discover a part or assembly.
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Game Development. It works with Python. The repository describes itself as: Package manager for things. Start designing modular hardware! PartCAD is the standard for documenting manufacturable physical products (a.k.a. Digital Thread or TDP). It comes… The licence is Apache-2.0.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e08683a. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Search loads about 960 tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 452 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from partcad/partcad at commit e08683a, republished under its Apache-2.0 licence (© partcad). 452 words, ~960 tokens.
.claude/skills/search/SKILL.md (or your agent's skills folder).Find existing PartCAD parts and assemblies that match a query, using
PartCAD's own pc search. The text after the command ($ARGUMENTS) is what to
look for — a natural-language description or a set of keywords. Present the
matches and, when the user points at one, act on it (inspect or render). This
searches the existing catalog; it does not create anything — to generate a
new object, use /pc:gen instead.
$ARGUMENTS is the query. pc search matches a single keyword as a
case-insensitive substring against each object's name, its configured fields
(desc, type, path, …), and the contents of its source file. It does not
parse natural language and does not rank by relevance.standoff, hex, m3 — search each, then union the results yourself.//); the public
PartCAD registry and other imported packages are only reached by naming the
package with a ... suffix, which means that package and every package
below it.Resolve a command as /pc:init does (pc, then partcad, then
python -m partcad_cli.click.command). If none is found, stop and run
/pc:setup executable first.
Run one search per object kind you care about — parts and assemblies — for each
keyword. The keyword is the required -k/--keyword option (quote
multi-word terms):
pc search parts -k "<keyword>" # search parts
pc search assemblies -k "<keyword>" # search assembliesWiden the scope when the local package has no match — a ... suffix on the
package walks every package below it (the public registry and any dependencies),
which is where most catalog items live:
pc search parts -k "<keyword>" -P //... # all imported packages
pc search parts -k "<keyword>" -P //pub/std... # scope to one package subtreeSibling commands share the same flags if the query is broader: pc search all
(parts, sketches, interfaces, assemblies, and packages at once), plus
pc search sketches, pc search interfaces, and pc search packages.
Each match prints as <package> <name> followed by its description, and the run
ends with Matches: N (or <none>). Read both columns — the package tells you
where the object lives, which you need in order to act on it.
Collect the matches across all the keywords you tried, drop duplicates, and show
the user a short list: the qualified name (<package> <name>) and its
description, best-fit first (you judge fit from the description — the tool does
not order results). If nothing matched, say so and suggest widening with
-P //...,
trying different terms, or generating it with /pc:gen.
When the user picks a match, reference it by the two columns the search printed —
-P <package> plus the object name; add -a when it is an assembly:
pc ide view -P <package> <name> # view a part; add -a for an assembly
mkdir -p /tmp/pc-render # the -O directory must already exist
pc render -t png -O /tmp/pc-render -P <package> <name> # writes a PNG under /tmp/pc-render; add -a for an assemblyThen follow up as the user asks — for example describe it with /pc:describe,
or add it to their project.
© partcad, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in ai-agents/common/skills/search of partcad/partcad.
Open the folder on GitHubat commit e08683a
Search 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Search this skillpartcad/partcad | 503 | — | ~960 | Automated safety check: Pass | Apache-2.0 | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| 2D Map and Scene Generator0x0funky/agent-sprite-forge | 4.4k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Bambu Studio AIheyixuan2/bambu-studio-ai | 220 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Spine AnimationGenielabsOpenSource/spine-animation-ai | 518 | — | ~17k | Automated safety check: Pass | CC-BY-NC-4.0 | |
| Unreal BridgeTornLux/UnrealBridge | 305 | — | ~8.4k | Automated safety check: Notes | MIT |
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
0x0funky/agent-sprite-forge
Plans and builds 2D game maps and scenes, from tilemaps and parallax backgrounds to HD-2D plates, with collision checks, a playable HTML preview and Tiled, Godot or LDtk export.
heyixuan2/bambu-studio-ai
End-to-end 3D printing for Bambu Lab printers. An agent skill from heyixuan2/bambu-studio-ai.
GenielabsOpenSource/spine-animation-ai
Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image).
TornLux/UnrealBridge
Execute Python scripts inside a running Unreal Engine 5.3+ editor via TCP bridge.
0x0funky/agent-sprite-forge
Produces game-ready 2D characters, creatures, props, icons and effects as master stills, sheets or clips, and exports frames for common game engines.
partcad/partcad
Enrich an existing PartCAD part with connection interfaces and ports (mating metadata) so it can be mated to other parts automatically.
partcad/partcad
Convert a CAD file or a PartCAD object to another geometry format - STEP, BREP, STL, 3MF, OBJ, IGES, glTF, three.js, SVG, DXF, URDF, ASSY - with pc convert for an object a package declares (which…
partcad/partcad
Write a narratable, accessibility-oriented text description of an existing PartCAD part, assembly, or sketch from its measured bounding box and volume, from renders taken at several viewing angles…
partcad/partcad
Write a CAD file out of an object a PartCAD package declares - STEP, BREP, STL, 3MF, OBJ, IGES, glTF, three.js, URDF for 3D, SVG or DXF for a sketch, or a file type the package implements itself -…
partcad/partcad
Generate a PartCAD part from a natural-language description (and optional reference images/requirements) by authoring a CAD script and validating it with the PartCAD CLI.
partcad/partcad
Generate a PartCAD 2D sketch from a natural-language description by authoring the sketch (build123d / cadquery / dxf / svg / basic) and validating it with the PartCAD CLI.
Works with
Categories
Find existing PartCAD parts and assemblies in the catalog that match a natural-language query, using the PartCAD CLI (pc search), then present the matches and optionally inspect or render a chosen…. Search is an agent skill from partcad/partcad. Find existing PartCAD parts and assemblies in the catalog that match a natural-language query, using the PartCAD CLI (pc search), then present the matches and optionally inspect or render a chosen one.
Search fits situations like: the user asks to search; discover a part.
Run `npx skills add partcad/partcad --skill search -a claude-code`. Or copy the skill folder (ai-agents/common/skills/search in partcad/partcad) into .claude/skills/search in your project. Claude Code loads it when a task matches its description.
Run `npx skills add partcad/partcad --skill search -a codex`. Or copy the skill folder (ai-agents/common/skills/search in partcad/partcad) into .agents/skills/search in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add partcad/partcad --skill search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search, .gemini/skills/search, .github/skills/search and .opencode/skills/search in your project.
Going by SKILL.md and its folder, Search needs the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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. Review the folder before installing.
Search is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 960 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Search: Image to Three.js Model (img2threejs/img2threejs, 18k stars), 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars), Bambu Studio AI (heyixuan2/bambu-studio-ai, 220 stars) and Spine Animation (GenielabsOpenSource/spine-animation-ai, 518 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
partcad (a GitHub organization) maintains it in partcad/partcad, which has 503 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 8, 2026.
Source: partcad/partcad on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.