Threejs World Generation
calesthio/OpenMontage
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.
Create concise, dataset-agnostic physical state plans from video prompts.
Install Physical State Planner
$ npx skills add micky-li-hd/VideoCoCo --skill physical-state-planner -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install micky-li-hd/VideoCoCo physical-state-planner --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/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/physical-state-planner .claude/skills/physical-state-planner && 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 "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .claude/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-plannerType 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 micky-li-hd/VideoCoCo --skill physical-state-planner -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install micky-li-hd/VideoCoCo physical-state-planner --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill/physical-state-planner .agents/skills/physical-state-planner && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .agents/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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 micky-li-hd/VideoCoCo --skill physical-state-planner -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install micky-li-hd/VideoCoCo physical-state-planner --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill/physical-state-planner .cursor/skills/physical-state-planner && 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 "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .cursor/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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/micky-li-hd/VideoCoCo.git --path skill/physical-state-planner--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 micky-li-hd/VideoCoCo --skill physical-state-planner -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install micky-li-hd/VideoCoCo physical-state-planner --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill/physical-state-planner .gemini/skills/physical-state-planner && 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 "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .gemini/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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 micky-li-hd/VideoCoCo physical-state-plannerInstalls 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 micky-li-hd/VideoCoCo --skill physical-state-planner -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill/physical-state-planner .github/skills/physical-state-planner && 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 "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .github/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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 micky-li-hd/VideoCoCo --skill physical-state-planner -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install micky-li-hd/VideoCoCo physical-state-planner --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/micky-li-hd/VideoCoCo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill/physical-state-planner .opencode/skills/physical-state-planner && 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 "physical-state-planner" agent skill from https://github.com/micky-li-hd/VideoCoCo/tree/main/skill/physical-state-planner into .opencode/skills/physical-state-planner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-state-planner", 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.
Facts
- Skill name
physical-state-planner- GitHub stars
- 117
- Token cost
- ~1.8k tokens
- SKILL.md length
- 699 words
- Files
- 4 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- None found
At a glance
Create concise, dataset-agnostic physical state plans from video prompts.
- Works in 7 steps: Extract the core physical event from the… → Identify scene objects → Create semantic keyframes → …
- Codex needs to decompose a prompt
- SKILL.md covers Purpose, Inputs, Workflow and Output Schema, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Physical State Planner is an agent skill from micky-li-hd/VideoCoCo. Create concise, dataset-agnostic physical state plans from video prompts. Use when Codex needs to decompose a prompt, optional physical hints, or optional evaluation questions into scene objects, semantic keyframes, transitions, causal constraints, must-show requirements, and must-avoid failures before any video, Blender, simulation, or animation implementation.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/oil-water-layering.json` and `references/output-schema.json`).
It sits in Game Development. It works with Blender. The repository describes itself as: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System.
When your agent uses it
- Codex needs to decompose a prompt
- Optional physical hints
- Optional evaluation questions into scene objects
- Semantic keyframes
Example prompts
- “/physical-state-planner”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Extract the core physical event from the prompt
- Identify scene objects
- Create semantic keyframes
- Create transitions between keyframes
- Write lightweight causal constraints
- Extract visual requirements
- Record uncertain assumptions
What it can do on your machine
Read from SKILL.md and the folder at commit 4afce26. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Physical State Planner loads about 1.8k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 699 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.
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); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 699 words (~1,770 tokens).
“Use this skill to turn a video prompt into a lightweight physical process plan. The output is an implementation-neutral sequence of semantic keyframes and transitions for later Coder, Blender, simulation, or audit agents.”
- name
- physical-state-planner
Files
SKILL.md and 3 other files (references) in skill/physical-state-planner of micky-li-hd/VideoCoCo.
- SKILL.md
- agents/openai.yaml
- references/oil-water-layering.json
- references/output-schema.json
Open the folder on GitHubat commit 4afce26
Compare with similar skills
Physical State Planner 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 |
|---|---|---|---|---|---|---|
| Physical State Planner this skillmicky-li-hd/VideoCoCo | 117 | — | ~1.8k | Automated safety check: Pass | None | |
| Threejs World Generationcalesthio/OpenMontage | 66k | — | ~2k | Automated safety check: Pass | AGPL-3.0 | |
| 3Dviz Pro Max Scene Builderviettranx/3dviz-pro-max | 697 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Asset Pipelinerehan-remade/universal-modder | 5.8k | — | ~2k | Automated safety check: Pass | MIT | |
| Blender Image To 3Dmajidmanzarpour/blender-game-skills | 135 | — | ~5.7k | Automated safety check: Pass | MIT | |
| Text To 3D AssetLaurentiuGabriel/unreal-game-assets-creation-skill | 148 | — | ~2.1k | Automated safety check: Pass | None |
Similar skills
3Dviz Pro Max Scene Builder
viettranx/3dviz-pro-max
Guides building an expressive 3D scene in Three.js or Blender by reasoning through intent, object construction and scientific grounding before using a catalog of recipes and kits.
Asset Pipeline
rehan-remade/universal-modder
Turn generated or hand-made art into exactly what a game engine loads.
Blender Image To 3D
majidmanzarpour/blender-game-skills
Build a game-ready 3D asset in Blender from reference images (concept art, photos, turnarounds, sketches, screenshots) for any category, including characters, creatures, architecture, vehicles…
Text To 3D Asset
LaurentiuGabriel/unreal-game-assets-creation-skill
Generate a game-ready 3D asset by running the local AI pipeline sequentially: Fooocus (SDXL text-to-image) - Hunyuan3D-2 (image-to-textured-GLB) - optional Blender FBX convert + Unreal import.
Game Build From Design
zenstory-ai/novel-to-game
Builds a risk-matched whitebox or an approved production game candidate from a game design for its target runtime, with replayable evidence.
More from micky-li-hd/VideoCoCo
Physical Video Blender Implementer
micky-li-hd/VideoCoCo
Convert physical-state-planner outputs into standalone Blender Python preview videos.
Blender MCP Video
micky-li-hd/VideoCoCo
A skill your agent uses for Blender MCP or Blender CLI video-generation work, especially when rendering scripted Blender scenes, debugging MCP port 9876, checking why blender is not on PATH…
Related
Works with
Categories
Questions about Physical State Planner
What does Physical State Planner do?
Create concise, dataset-agnostic physical state plans from video prompts. Physical State Planner is an agent skill from micky-li-hd/VideoCoCo. Create concise, dataset-agnostic physical state plans from video prompts.
When should I use Physical State Planner?
Physical State Planner fits situations like: Codex needs to decompose a prompt; optional physical hints; optional evaluation questions into scene objects; semantic keyframes.
How do I install Physical State Planner in Claude Code?
Run `npx skills add micky-li-hd/VideoCoCo --skill physical-state-planner -a claude-code`. Or copy the skill folder (skill/physical-state-planner in micky-li-hd/VideoCoCo) into .claude/skills/physical-state-planner in your project. Claude Code loads it when a task matches its description.
How do I install Physical State Planner in Codex?
Run `npx skills add micky-li-hd/VideoCoCo --skill physical-state-planner -a codex`. Or copy the skill folder (skill/physical-state-planner in micky-li-hd/VideoCoCo) into .agents/skills/physical-state-planner in your project. Codex loads it when a task matches its description.
Can I use Physical State Planner 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 micky-li-hd/VideoCoCo --skill physical-state-planner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/physical-state-planner, .gemini/skills/physical-state-planner, .github/skills/physical-state-planner and .opencode/skills/physical-state-planner in your project.
What does Physical State Planner need to run?
SKILL.md names no scripts, command-line tools or credentials: Physical State Planner is instructions for the agent only.
Does Physical State Planner access the network?
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.
Is Physical State Planner 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. Review the folder before installing.
What licence does Physical State Planner use?
No licence was found for Physical State Planner or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Physical State Planner use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
What are the alternatives to Physical State Planner?
Skills that share tags, products or a category with Physical State Planner: Threejs World Generation (calesthio/OpenMontage, 66k stars), 3Dviz Pro Max Scene Builder (viettranx/3dviz-pro-max, 697 stars), Asset Pipeline (rehan-remade/universal-modder, 5.8k stars) and Blender Image To 3D (majidmanzarpour/blender-game-skills, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Physical State Planner?
micky-li-hd (a GitHub user) maintains it in micky-li-hd/VideoCoCo, which has 117 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 6, 2026.
Source: micky-li-hd/VideoCoCo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.