Figma Design System Builder
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md.
Install Cp Refine
$ npx skills add tangziwen/CubeMiniGame --skill cp-refine -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tangziwen/CubeMiniGame cp-refine --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/tangziwen/CubeMiniGame.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cp-refine .claude/skills/cp-refine && 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 "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .claude/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refineType 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 tangziwen/CubeMiniGame --skill cp-refine -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tangziwen/CubeMiniGame cp-refine --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/cp-refine .agents/skills/cp-refine && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .agents/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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 tangziwen/CubeMiniGame --skill cp-refine -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tangziwen/CubeMiniGame cp-refine --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/cp-refine .cursor/skills/cp-refine && 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 "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .cursor/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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/tangziwen/CubeMiniGame.git --path .agents/skills/cp-refine--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 tangziwen/CubeMiniGame --skill cp-refine -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tangziwen/CubeMiniGame cp-refine --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/cp-refine .gemini/skills/cp-refine && 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 "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .gemini/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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 tangziwen/CubeMiniGame cp-refineInstalls 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 tangziwen/CubeMiniGame --skill cp-refine -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/cp-refine .github/skills/cp-refine && 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 "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .github/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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 tangziwen/CubeMiniGame --skill cp-refine -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tangziwen/CubeMiniGame cp-refine --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/cp-refine .opencode/skills/cp-refine && 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 "cp-refine" agent skill from https://github.com/tangziwen/CubeMiniGame/tree/master/.agents/skills/cp-refine into .opencode/skills/cp-refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cp-refine", 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
cp-refine- GitHub stars
- 359
- Token cost
- ~512 tokens
- SKILL.md length
- 247 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md.
- Works in 2 steps: ../_shared/codeplan/core.md → ../_shared/codeplan/step-contract.md
- The user asks to detail
- SKILL.md covers Shared Contract, Purpose, Idempotency and Workflow
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Cp Refine is an agent skill from tangziwen/CubeMiniGame. Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md. Use when the user asks to detail, refine, decompose, split, or prepare a CodePlan for implementation by weaker or cheaper models.
Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Frontend & Design, covering Design tokens. The repository describes itself as: HomeBrew C++ 3D Game Engine based on OpenGL & Vulkan. The licence is MIT.
When your agent uses it
- The user asks to detail
- Prepare a CodePlan for implementation by weaker
Example prompts
- “/cp-refine”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- ../_shared/codeplan/core.md
- ../_shared/codeplan/step-contract.md
What it can do on your machine
Read from SKILL.md and the folder at commit 33b364c. 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.
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
Cp Refine loads about 512 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 247 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
The full file from tangziwen/CubeMiniGame at commit 33b364c, republished under its MIT licence (© tangziwen). 247 words, ~512 tokens.
Download SKILL.mdSave it as
.claude/skills/cp-refine/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- cp-refine
- description
- Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md. Use when the user asks to detail, refine, decompose, split, or prepare a CodePlan for implementation by weaker or cheaper models.
- disable-model-invocation
- true
CodePlan Refine
Shared Contract
Before acting, read:
../_shared/codeplan/core.md../_shared/codeplan/step-contract.md
Purpose
Turn design.md into precise, executable stepX.md files and a durable progress.md checklist. Steps must be detailed enough for a lower-capability model to execute with minimal guessing.
Do not implement source code while refining.
Idempotency
Before generating or updating steps:
- Check whether
step*.mdalready exists. - If no steps exist, generate them.
- If steps exist and
design.mdis not newer than any existingstep*.md, tell the user steps already exist and ask whether to overwrite, append, or leave them unchanged. - If steps exist and
design.mdis newer than one or morestep*.md, tell the user the steps may be stale and ask whether to regenerate all steps, update only affected steps, append new steps, or cancel. - Never silently overwrite completed step notes or
progress.mdsummaries.
Compare modification times using design.md against all step*.md. Preserve user-written notes when possible.
Workflow
- Resolve the target CodePlan directory.
- Read
design.md. - Inspect existing
step*.mdandprogress.mdif present. - Apply the idempotency rules.
- Refine coarse phases into concrete implementation steps.
- Create or update
step1.mdthroughstepX.md. - Create or update
progress.mdwith the step checklist, completed summaries, and blockers or notes.
Use the exact English headings and detail standard from step-contract.md for every generated step and progress.md.
Let agents infer the next step from the first unchecked item in Step Status.
When updating an existing plan, preserve completed summaries and manual notes.
© tangziwen, 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 1 other file in .agents/skills/cp-refine of tangziwen/CubeMiniGame.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 33b364c
Compare with similar skills
Cp Refine 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 |
|---|---|---|---|---|---|---|
| Cp Refine this skilltangziwen/CubeMiniGame | 359 | — | ~512 | Automated safety check: Pass | MIT | |
| Figma Design System Builderwarpdotdev/warp | 65k | 2 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| MCP Developmentcoollabsio/coolify | 63k | 1 repos | ~949 | Automated safety check: Pass | MIT | |
| Design SystemOhh-889/skyroc | 795 | 11 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Design Dnazanwei/design-dna | 1.9k | 1 repos | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
Design System
Ohh-889/skyroc
Token architecture, component specifications, and slide generation.
Design Dna
zanwei/design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects…
Figma Design to Code
warpdotdev/warp
Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.
More from tangziwen/CubeMiniGame
All 12 skills in this repoCp Plan
tangziwen/CubeMiniGame
Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent.
Build Project
tangziwen/CubeMiniGame
Build the project using the CMake presets defined for this repository.
Cp Apply
tangziwen/CubeMiniGame
Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates.
Cp Explore
tangziwen/CubeMiniGame
Explore and clarify a prospective CodePlan before writing design.md.
Cp Review
tangziwen/CubeMiniGame
Review CodePlan documents, including explored requirements, design.md, progress.md, and step files.
Engine Codemap Sync
tangziwen/CubeMiniGame
Assess whether completed engine code changes should be reflected in Doc/EngineCodeMap.
Related
Categories
Questions about Cp Refine
What does Cp Refine do?
Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md. Cp Refine is an agent skill from tangziwen/CubeMiniGame.md.
When should I use Cp Refine?
Cp Refine fits situations like: the user asks to detail; prepare a CodePlan for implementation by weaker.
How do I install Cp Refine in Claude Code?
Run `npx skills add tangziwen/CubeMiniGame --skill cp-refine -a claude-code`. Or copy the skill folder (.agents/skills/cp-refine in tangziwen/CubeMiniGame) into .claude/skills/cp-refine in your project. Claude Code loads it when a task matches its description.
How do I install Cp Refine in Codex?
Run `npx skills add tangziwen/CubeMiniGame --skill cp-refine -a codex`. Or copy the skill folder (.agents/skills/cp-refine in tangziwen/CubeMiniGame) into .agents/skills/cp-refine in your project. Codex loads it when a task matches its description.
Can I use Cp Refine 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 tangziwen/CubeMiniGame --skill cp-refine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cp-refine, .gemini/skills/cp-refine, .github/skills/cp-refine and .opencode/skills/cp-refine in your project.
What does Cp Refine need to run?
SKILL.md names no scripts, command-line tools or credentials: Cp Refine is instructions for the agent only.
Does Cp Refine 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 Cp Refine 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 Cp Refine use?
Cp Refine 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 Cp Refine use?
About 512 tokens (SKILL.md is roughly 2k 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 Cp Refine?
Skills that share tags, products or a category with Cp Refine: Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), MCP Development (coollabsio/coolify, 63k stars) and Design System (Ohh-889/skyroc, 795 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cp Refine?
tangziwen (a GitHub user) maintains it in tangziwen/CubeMiniGame, which has 359 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 19, 2026.
Source: tangziwen/CubeMiniGame on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.