Agent skill

Create

Create a new Licia utility module following project conventions.

Install Create

skills CLI

$ npx skills add liriliri/licia --skill create -a claude-code

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

GitHub CLI

$ gh skill install liriliri/licia create --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/liriliri/licia.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/create .claude/skills/create && 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/

Paste into Claude Code

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .claude/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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

$skill-installer install https://github.com/liriliri/licia/tree/master/.agents/skills/create

Type 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.

skills CLI

$ npx skills add liriliri/licia --skill create -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install liriliri/licia create --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/liriliri/licia.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/create .agents/skills/create && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .agents/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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.

skills CLI

$ npx skills add liriliri/licia --skill create -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install liriliri/licia create --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/liriliri/licia.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/create .cursor/skills/create && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .cursor/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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

$ gemini skills install https://github.com/liriliri/licia.git --path .agents/skills/create

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add liriliri/licia --skill create -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install liriliri/licia create --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/liriliri/licia.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/create .gemini/skills/create && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .gemini/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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.

GitHub CLI

$ gh skill install liriliri/licia create

Installs 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).

skills CLI

$ npx skills add liriliri/licia --skill create -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/liriliri/licia.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/create .github/skills/create && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .github/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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.

skills CLI

$ npx skills add liriliri/licia --skill create -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install liriliri/licia create --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/liriliri/licia.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/create .opencode/skills/create && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "create" agent skill from https://github.com/liriliri/licia/tree/master/.agents/skills/create into .opencode/skills/create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create", 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: create
GitHub stars: 2.4k
Token cost: ~879 tokens
SKILL.md length: 277 words
Files: 1
Skills in repo: 1
Repo updated: Oct 4, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Create a new Licia utility module following project conventions.

Works in 6 steps: Prepare → Source — src/.js → Test — test/.js → …
Adding a new module
SKILL.md covers Checklist, 1. Prepare, 2. Source — src/.js and 3. Test — test/.js, plus 4 more sections
Calls npm and node

What it does

Create is an agent skill from liriliri/licia. Create a new Licia utility module following project conventions. Use when adding a new module, scaffolding src/test/i18n/benchmark files, or when the user asks to 增加/新增/创建模块.

Its SKILL.md is about 880 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 Frontend & Design, covering Internationalization and Project scaffolding. It works with npm. The repository describes itself as: Useful utility collection with zero dependencies. The licence is MIT.

When your agent uses it

Adding a new module
Scaffolding src/test/i18n/benchmark files
The user asks to 增加/新增/创建模块

Example prompts

“/create”

Requirements

Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Prepare
Source — src/.js
Test — test/.js
i18n — i18n/.md (manual)
Benchmark (optional)
Finish

What it can do on your machine

Read from SKILL.md and the folder at commit 199a789. 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
Shell commands in SKILL.md call:
- npm
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, 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

Create loads about 879 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 277 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~45
When it runs · the whole SKILL.md, loaded when a task matches: ~879

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 liriliri/licia at commit 199a789, republished under its MIT licence (© liriliri). 277 words, ~879 tokens.

Download SKILL.mdSave it as .claude/skills/create/SKILL.md (or your agent's skills folder).

name: create
description: Create a new Licia utility module following project conventions. Use when adding a new module, scaffolding src/test/i18n/benchmark files, or when the user asks to 增加/新增/创建模块.

Create Licia Module

Scaffold and finish a new Licia module end-to-end. Do not hand-edit generated metadata.

Checklist

- [ ] Pick reference module(s) and `since` version
- [ ] Write src/<name>.js
- [ ] Write test/<name>.js
- [ ] Write i18n/<name>.md (required for DOC_CN)
- [ ] Optional: benchmark/<name>.js
- [ ] format → lint → test → update
- [ ] Verify generated files include the module

1. Prepare

Find a similar module in src/ (same env / API shape) and mirror its style.
Confirm src/<name>.js does not already exist.
Set since to the next semver after package.json version (e.g. package 1.48.1 → since: 1.49.0).

CLI: prefer licia <cmd> <moduleName>. If licia is missing, use node bin/licia.js.

2. Source — `src/<name>.js`

javascript

/* Short description.
 *
 * |Name  |Desc        |
 * |------|------------|
 * |arg   |Arg meaning |
 * |return|Return value|
 */

/* example
 * name('input'); // -> 'output'
 */

/* module
 * env: all
 * since: X.Y.Z
 */

/* typescript
 * export declare function name(...): ...;
 */

_('dep1 dep2');

exports = function(...) { ... };

Rules:

Header blocks are required: description table, example, module, typescript.
env: all | node | browser (as needed).
Declare deps with _('a b'), not npm imports. Node builtins via eval('require')('...') only when mirroring existing modules (e.g. md5 / sha1).
Table cells: no trailing spaces before |. Align columns; longest cell sets width (see md5.js).
Prefer pure JS that works in browser; optional Node fast-path only when peers do (crypto hashes).

3. Test — `test/<name>.js`

Mirror peers. Simple APIs use tests([...]):

javascript

tests([
    ['input', 'expected'],
    [util.strToBytes('input'), 'expected']
]);

Cover string / bytes / edge cases that the reference module covers.

4. i18n — `i18n/<name>.md` (manual)

update does not create this file. Without it, DOC_CN.md has no Chinese section.

markdown

## CN

简短中文描述。

|参数名|说明|
|-----|---|
|arg|参数说明|
|返回值|返回值说明|

Match tone of a peer under i18n/ (e.g. md5.md, fnv1a.md).

5. Benchmark (optional)

Add benchmark/<name>.js only if similar modules have one (md5, crc32, …).

javascript

/* scripts
 * before: npm i --prefix .licia <compare-pkg>
 */

benchmark({
    name() { name(content); }
    // optional: other libs / node crypto
});

6. Finish

Run in order:

bash

licia format <name>
licia lint <name>
licia test <name> -s --ts
licia test <name> -bs          # if env includes browser
npm run update                 # or: licia update

npm run update regenerates (do not edit by hand):

File	Role
`index.json`	Module metadata / deps
`DOC.md`	English docs
`DOC_CN.md`	Chinese docs (needs `i18n/<name>.md`)
`cspell.json`	Spell dictionary

After update, confirm index.json has the module and DOC.md / DOC_CN.md show it.

Do / Don't

Do copy structure from the closest existing module.
Do create i18n/<name>.md before npm run update.
Don't manually patch index.json, DOC.md, DOC_CN.md, or cspell.json.
Don't leave trailing spaces inside doc tables.
Don't commit unless the user asks.

Files

Just SKILL.md in .agents/skills/create of liriliri/licia.

Open the folder on GitHubat commit 199a789

Compare with similar skills

Create 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.

Create compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Create this skillliriliri/licia	2.4k	—	~879	Automated safety check: Pass	MIT	4 days ago
Create Docsvictorgarciaesgi/nuxt-typed-router	413	2 repos	~2.8k	Automated safety check: Pass	MIT	yesterday
Frontend Build Timing Auditopenops-cloud/openops	1.1k	—	~2.3k	Automated safety check: Pass	Custom licence	today
Rtdfany-tdf/any-tdf	779	—	~1.1k	Automated safety check: Pass	MIT	today
Stdfany-tdf/any-tdf	779	—	~1.1k	Automated safety check: Pass	MIT	today
Declarative Agent Developermicrosoft/work-iq	1k	—	~3.2k	Automated safety check: Pass	Custom licence	yesterday

Similar skills

Create Docs
victorgarciaesgi/nuxt-typed-router
Create complete documentation sites for projects. An agent skill from victorgarciaesgi/nuxt-typed-router.
413 GitHub starsUsed in 2 repos~2.8k tokens
Frontend & DesignAuto-check passed
Frontend Build Timing Audit
openops-cloud/openops
Detects and diagnoses chunk-evaluation timing bugs in the Vite/rolldown production build of react-ui (works-in-dev / broken-in-build i18n regressions, missing UI labels, module-scope t()…
1.1k GitHub stars~2.3k tokensUpdated today
Frontend & DesignAuto-check passed
Rtdf
any-tdf/any-tdf
Build, review, and troubleshoot RTDF React applications using exact component APIs, themes, icons, localization, and scaffolding.
779 GitHub stars~1.1k tokensUpdated today
Frontend & DesignAuto-check passed
Stdf
any-tdf/any-tdf
Build, review, and troubleshoot STDF Svelte 5 applications using exact component APIs, themes, icons, localization, and scaffolding.
779 GitHub stars~1.1k tokensUpdated today
Frontend & DesignAuto-check passed
Declarative Agent Developer
microsoft/work-iq
Official
Create, build, deploy, and localize declarative agents for M365 Copilot and Teams.
1k GitHub stars~3.2k tokensUpdated yesterday
Frontend & DesignAuto-check passed
Vtdf
any-tdf/any-tdf
Build, review, and troubleshoot VTDF Vue 3 applications using exact component APIs, themes, icons, localization, and scaffolding.
779 GitHub stars~1.1k tokensUpdated today
Frontend & DesignAuto-check passed

Works with

Questions about Create

What does Create do?

Create a new Licia utility module following project conventions. Create is an agent skill from liriliri/licia. Create a new Licia utility module following project conventions.

When should I use Create?

Create fits situations like: adding a new module; scaffolding src/test/i18n/benchmark files; the user asks to 增加/新增/创建模块.

How do I install Create in Claude Code?

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

How do I install Create in Codex?

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

Can I use Create 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 liriliri/licia --skill create -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create, .gemini/skills/create, .github/skills/create and .opencode/skills/create in your project.

What does Create need to run?

Going by SKILL.md and its folder, Create needs the command-line tools its instructions call (npm and node). Our summary lists: Node.js.

Does Create access the network?

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

Is Create 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 Create use?

Create 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 Create use?

About 879 tokens (SKILL.md is roughly 3.5k 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 Create?

Skills that share tags, products or a category with Create: Create Docs (victorgarciaesgi/nuxt-typed-router, 413 stars), Frontend Build Timing Audit (openops-cloud/openops, 1.1k stars), Rtdf (any-tdf/any-tdf, 779 stars) and Stdf (any-tdf/any-tdf, 779 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create?

liriliri (a GitHub organization) maintains it in liriliri/licia, which has 2,381 GitHub stars. The repository was last updated on October 4, 2026.

Source: liriliri/licia on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Create

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Create Licia Module

Checklist

1. Prepare

2. Source — src/<name>.js

3. Test — test/<name>.js

4. i18n — i18n/<name>.md (manual)

5. Benchmark (optional)

6. Finish

Do / Don't

Files

Compare with similar skills

Similar skills

Create Docs

Frontend Build Timing Audit

Rtdf

Stdf

Declarative Agent Developer

Vtdf

Related

Questions about Create

2. Source — `src/<name>.js`

3. Test — `test/<name>.js`

4. i18n — `i18n/<name>.md` (manual)