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

Cp Apply

by tangziwen in tangziwen/CubeMiniGame

Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates.

MITAuto-check passed

Install Cp Apply

skills CLI
$ npx skills add tangziwen/CubeMiniGame --skill cp-apply -a claude-code

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

GitHub CLI
$ gh skill install tangziwen/CubeMiniGame cp-apply --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/tangziwen/CubeMiniGame.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cp-apply .claude/skills/cp-apply && 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
cp-apply
GitHub stars
359
Token cost
~566 tokens
SKILL.md length
263 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates.

  • Works in 2 steps: ../_shared/codeplan/core.md → ../_shared/codeplan/step-contract.md
  • The user asks to execute
  • SKILL.md covers Shared Contract, Purpose, Required Reads and Preflight Idempotency, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cp Apply is an agent skill from tangziwen/CubeMiniGame. Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates. Use when the user asks to execute, apply, continue, or implement a specific step or the next unchecked step.

Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

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 execute
  • Implement a specific step
  • The next unchecked step

Example prompts

  • “/cp-apply”

Workflow steps

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

  1. ../_shared/codeplan/core.md
  2. ../_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 Apply loads about 566 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 263 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~566

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). 263 words, ~566 tokens.

Download SKILL.mdSave it as .claude/skills/cp-apply/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
cp-apply
description
Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates. Use when the user asks to execute, apply, continue, or implement a specific step or the next unchecked step.
disable-model-invocation
true

CodePlan Apply

Shared Contract

Before acting, read:

  1. ../_shared/codeplan/core.md
  2. ../_shared/codeplan/step-contract.md

Purpose

Implement exactly one stepX.md at a time. Run preflight checks first to detect repeated or partially-applied work before editing.

Required Reads

Before editing, read:

  1. AGENTS.md
  2. CodePlan/<PlanName>/design.md
  3. CodePlan/<PlanName>/progress.md
  4. the requested or inferred stepX.md

Read other step files only when the current step explicitly depends on them.

Preflight Idempotency

Use the shared step-contract.md preflight state rules before editing.

Apply Rules

  • Implement only the current step.
  • Do not do future-step work.
  • Do not perform opportunistic refactors.
  • Do not compile or build this repository unless the user explicitly asks.
  • Do not revert user changes.
  • Do not run destructive git commands.

Progress Updates

Use the shared step-contract.md progress update shape.

Plan Completion

After marking the current step complete, check whether all steps in progress.md are now checked.

If this was the final step:

  1. State explicitly in the final response that the entire CodePlan is now complete (CodePlan/<PlanName> 的所有步骤已完成).
  2. Ask whether to verify the whole plan (是否需要对当前 CodePlan 进行校验？) and wait for the user's answer before starting verification.

If this was not the final step, continue normally and do not ask for whole-plan verification.

Verification

Prefer non-build verification:

  • inspect changed code paths
  • search for stale references with rg
  • check CMake target names and paths textually
  • review headers and include relationships
  • run lightweight static commands only if they do not build

If compilation would be the only strong verification, say it was intentionally not run.

Final Response

Summarize:

  • selected plan and step
  • preflight classification
  • files changed
  • progress update
  • verification performed or skipped

© 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-apply of tangziwen/CubeMiniGame.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 33b364c

Compare with similar skills

Cp Apply 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.

Cp Apply compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cp Apply this skilltangziwen/CubeMiniGame359—~566Automated safety check: PassMIT
Running CI PreflightPostHog/posthog40k—~1.5kAutomated safety check: PassCustom licence
Azure Deployment Preflightgithub/awesome-copilot40k1 repos~1.9kAutomated safety check: PassMIT
Preflightopenwpm/OpenWPM1.4k—~670Automated safety check: PassCustom licence
Preflightopenfootmanager/openfootmanager1.1k—~1.3kAutomated safety check: PassGPL-3.0
Arxiv Preflightaipoch/medical-research-skills1.9k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Running CI Preflight

    PostHog/posthog

    Official

    Catch the deterministic CI failures reachable from your diff before pushing, with hogli ci:preflight.

    40k GitHub stars~1.5k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Azure Deployment Preflight

    github/awesome-copilot

    Official

    Performs comprehensive preflight validation of Bicep deployments to Azure, including template syntax validation, what-if analysis, and permission checks.

    40k GitHub starsUsed in 1 repo~1.9k tokens
    DevOps & CloudAuto-check passed

  • Preflight

    openwpm/OpenWPM

    Use BEFORE implementing code in a crosslink-tracked project — loads .crosslink/rules/global.md, the language rules for detected manifests, the project rules, and the active tracking-<mode.md.

    1.4k GitHub stars~670 tokensUpdated 6 days ago
    Auto-check passed

  • Preflight

    openfootmanager/openfootmanager

    Verify a pull request with the frontend scripts, default and MCP backend tests and clippy, formatting, architecture checks and review evidence.

    1.1k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Arxiv Preflight

    aipoch/medical-research-skills

    Run a submission-readiness preflight on a manuscript before arXiv upload.

    1.9k GitHub stars~1.8k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed

  • Dicom Series Preflight

    NVIDIA/skills

    Official

    Used for header-only preflight of one DICOM series folder before conversion or inference.

    3.6k GitHub stars~864 tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from tangziwen/CubeMiniGame

All 12 skills in this repo

  • Cp Plan

    tangziwen/CubeMiniGame

    Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent.

    359 GitHub stars~928 tokensUpdated 21 days ago
    Auto-check passed

  • Build Project

    tangziwen/CubeMiniGame

    Build the project using the CMake presets defined for this repository.

    359 GitHub stars~407 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Explore

    tangziwen/CubeMiniGame

    Explore and clarify a prospective CodePlan before writing design.md.

    359 GitHub stars~535 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Refine

    tangziwen/CubeMiniGame

    Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md.

    359 GitHub stars~512 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Review

    tangziwen/CubeMiniGame

    Review CodePlan documents, including explored requirements, design.md, progress.md, and step files.

    359 GitHub stars~475 tokensUpdated 21 days ago
    Auto-check passed

  • Engine Codemap Sync

    tangziwen/CubeMiniGame

    Assess whether completed engine code changes should be reflected in Doc/EngineCodeMap.

    359 GitHub stars~936 tokensUpdated 21 days ago
    Auto-check passed

Questions about Cp Apply

What does Cp Apply do?

Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates. Cp Apply is an agent skill from tangziwen/CubeMiniGame.md updates.

When should I use Cp Apply?

Cp Apply fits situations like: the user asks to execute; implement a specific step; the next unchecked step.

How do I install Cp Apply in Claude Code?

Run `npx skills add tangziwen/CubeMiniGame --skill cp-apply -a claude-code`. Or copy the skill folder (.agents/skills/cp-apply in tangziwen/CubeMiniGame) into .claude/skills/cp-apply in your project. Claude Code loads it when a task matches its description.

How do I install Cp Apply in Codex?

Run `npx skills add tangziwen/CubeMiniGame --skill cp-apply -a codex`. Or copy the skill folder (.agents/skills/cp-apply in tangziwen/CubeMiniGame) into .agents/skills/cp-apply in your project. Codex loads it when a task matches its description.

Can I use Cp Apply 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-apply -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-apply, .gemini/skills/cp-apply, .github/skills/cp-apply and .opencode/skills/cp-apply in your project.

What does Cp Apply need to run?

SKILL.md names no scripts, command-line tools or credentials: Cp Apply is instructions for the agent only.

Does Cp Apply 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 Apply 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 Apply use?

Cp Apply 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 Apply use?

About 566 tokens (SKILL.md is roughly 2.3k 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 Apply?

Skills that share tags, products or a category with Cp Apply: Running CI Preflight (PostHog/posthog, 40k stars), Azure Deployment Preflight (github/awesome-copilot, 40k stars), Preflight (openwpm/OpenWPM, 1.4k stars) and Preflight (openfootmanager/openfootmanager, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cp Apply?

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.