Agent skill

Create Smart App

by wecode-ai in wecode-ai/Wegent

Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation…

Apache-2.0Auto-check: notesAgent Workflows

Install Create Smart App

skills CLI
$ npx skills add wecode-ai/Wegent --skill create-smart-app -a claude-code

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

GitHub CLI
$ gh skill install wecode-ai/Wegent create-smart-app --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/wecode-ai/Wegent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/wework/resources/bundled-plugins/wework-personal/plugins/smart-app-builder/skills/create-smart-app .claude/skills/create-smart-app && 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
create-smart-app
GitHub stars
868
Token cost
~927 tokens
SKILL.md length
448 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation…

  • Works in 8 steps: Run inspect first. If it returns stale,… → Read plugin-manifest.json,… → Run doctor, then use search only when an… → …
  • Agent Workflows work in your project
  • SKILL.md covers Contract, Workflow and Commands
  • Calls node

What it does

Create Smart App is an agent skill from wecode-ai/Wegent. Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation handoff.

Its SKILL.md is about 930 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 Agent Workflows. It works with DeepSeek. The repository describes itself as: Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation. The licence is Apache-2.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/create-smart-app”

Workflow steps

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

  1. Run inspect first. If it returns stale, failed, or no report, read the
  2. Read plugin-manifest.json, smart-app.verify.json, the package declarations,
  3. Run doctor, then use search only when an additional DSH plugin is needed.
  4. Implement the smallest capability-specific change. Do not inject harness,
  5. Run verify after every meaningful edit. It performs the managed project checks,
  6. Use the Wework built-in preview for the primary path, one invalid-input path,
  7. Run pack only after the current report passes. It creates and re-verifies the
  8. For a linked directory, refresh 应用 → 智能工作台 → 我的. For ZIP-only

What it can do on your machine

Read from SKILL.md and the folder at commit 428f207. 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:

    • node

    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

Create Smart App loads about 927 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 448 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~927

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:47
    ZIP; it excludes credentials, `.env`, `node_modules`, VCS metadata, test output,

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 wecode-ai/Wegent at commit 428f207, republished under its Apache-2.0 licence (© wecode-ai). 448 words, ~927 tokens.

Download SKILL.mdSave it as .claude/skills/create-smart-app/SKILL.md (or your agent's skills folder).
name
create-smart-app
description
Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation handoff.

Create a Wework Smart app

Use this workflow when the user wants to build, modify, test, add plugins to, or package a Wework Smart app. A Smart app is an external DeepSeek Harness plugin bundle; never modify the DeepSeek Harness source tree to add the app.

Contract

  • Keep the Smart app in the user's workspace or a directory they explicitly chose.
  • When Wework supplies an existing Smart app directory, treat it as the durable project. Inspect and edit it in place; never replace it with a new scaffold.
  • Pin the DSH version in plugin-manifest.json and package dependencies.
  • Treat Wework's selected model as the runtime model. Do not bake model credentials into the package.
  • A distributable ZIP must contain plugin-manifest.json, PLUGIN.md, INSTALL.zh-CN.md, the profile bundle cordis.patch.yml, source, and built output.
  • Installation into Wework always ends with the native preview and model-selection confirmation. Do not bypass that confirmation by editing Wework data files.
  • For a Wework-linked project, Wework Host is the only authority for Smart app inspection, verification, and distributable ZIP creation. Do not replace it with local manifest checks, ad-hoc DSH commands, or a fallback packer.

Workflow

Use this state machine: inspect → contract → doctor → verify → preview → pack.

  1. Run inspect first. If it returns stale, failed, or no report, read the structured error code and fix that exact boundary; do not guess from UI text.
  2. Read plugin-manifest.json, smart-app.verify.json, the package declarations, source, built output, and cordis.patch.yml. Keep capabilities minimal and declare each new Host, Client, or Remote capability in the contract.
  3. Run doctor, then use search only when an additional DSH plugin is needed. Record chosen package names and exact compatible versions.
  4. Implement the smallest capability-specific change. Do not inject harness, llm, filesystem, or network services unless the app declares and uses them.
  5. Run verify after every meaningful edit. It performs the managed project checks, artifact checks, isolated DSH cold start, ready-selector probe, and Remote probe when declared. Fix the structured error code, then verify again until passed.
  6. Use the Wework built-in preview for the primary path, one invalid-input path, and recovery. Save screenshots only when the user requests evidence.
  7. Run pack only after the current report passes. It creates and re-verifies the ZIP; it excludes credentials, .env, node_modules, VCS metadata, test output, and the development verification contract.
  8. For a linked directory, refresh 应用 → 智能工作台 → 我的. For ZIP-only delivery, use the native preview and model-selection confirmation before install.
Show full SKILL.md (44 more words)Show less

Commands

Resolve this plugin root from the selected skill path, then run:

bash
node <plugin-root>/scripts/smart-app-tool.mjs doctor
node <plugin-root>/scripts/smart-app-tool.mjs search "<keywords>"
node <plugin-root>/scripts/smart-app-tool.mjs inspect <smart-app-directory>
node <plugin-root>/scripts/smart-app-tool.mjs verify <smart-app-directory>
node <plugin-root>/scripts/smart-app-tool.mjs pack <smart-app-directory> [output.zip]

If the Host returns a DSH or plugin compatibility error, show its exact structured error code. Do not silently widen version ranges, bypass verification, or copy code from the DSH source tree.

© wecode-ai, 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

Files

Just SKILL.md in wework/resources/bundled-plugins/wework-personal/plugins/smart-app-builder/skills/create-smart-app of wecode-ai/Wegent.

Open the folder on GitHubat commit 428f207

Compare with similar skills

Create Smart App 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 Smart App compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Smart App this skillwecode-ai/Wegent868—~927Automated safety check: NotesApache-2.0
Mindmemos CLImindscale-noah/MindMemOS1k—~3.4kAutomated safety check: PassNone
Spec Driven Developzhu1090093659/deepseek-pp1.9k—~6.9kAutomated safety check: PassApache-2.0
Remember Learningsdyad-sh/dyad22k—~1.1kAutomated safety check: PassCustom licence
Codex Deepseek Subagentoil-oil/codex-deepseek-subagent376—~673Automated safety check: PassMIT
OpenGUI Installer for DSHCore-Mate/OpenGUI1.8k—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Mindmemos CLI

    mindscale-noah/MindMemOS

    Give an AI agent persistent, cross-session long-term memory through MindMemOS.

    1k GitHub stars~3.4k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Spec Driven Develop

    zhu1090093659/deepseek-pp

    Automates pre-development workflow for large-scale complex tasks.

    1.9k GitHub stars~6.9k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Codex Deepseek Subagent

    oil-oil/codex-deepseek-subagent

    配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

    376 GitHub stars~673 tokensUpdated 27 days ago
    Agent WorkflowsAuto-check passed
  • OpenGUI Installer for DSH

    Core-Mate/OpenGUI

    Installs and verifies the latest stable OpenGUI release in a DeepSeek Harness web profile on macOS without disturbing existing plugins or settings.

    1.8k GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Obelisk

    tommy0103/obelisk

    Search and query past Claude Code, Codex, Kimi Code, OMP, and Pi session history.

    567 GitHub stars~6.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from wecode-ai/Wegent

All 8 skills in this repo
  • Wework Plugin Creator

    wecode-ai/Wegent

    Create or extend Wework plugins, including native Connector login and account authentication for reuse on cloud devices.

    868 GitHub stars~990 tokensUpdated 2 days ago
    Auto-check passed
  • Develop Wework Plugin

    wecode-ai/Wegent

    Create, extend, and debug Wework Core DSH plugins and their optional nested Codex plugins.

    868 GitHub stars~3.5k tokensUpdated 2 days ago
    Auto-check passed
  • Interactive

    wecode-ai/Wegent

    Ask the user questions or present choices via an interactive form.

    868 GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Subscription Manager

    wecode-ai/Wegent

    Create and manage scheduled subscription tasks. An agent skill from wecode-ai/Wegent.

    868 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Browser

    wecode-ai/Wegent

    Complete real user web tasks end-to-end via browser-tool, navigate, interact, wait for page state, extract results, and provide evidence when needed.

    868 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Wework Notifications

    wecode-ai/Wegent

    Send Wework in-app notifications when a user requests an alert, greeting, or automation notification.

    868 GitHub stars~604 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Create Smart App

What does Create Smart App do?

Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation…. Create Smart App is an agent skill from wecode-ai/Wegent. Create or update a Wework Smart app based on DeepSeek Harness, including environment preparation, DSH plugin discovery, composition, built-in-browser verification, packaging, and local installation handoff.

When should I use Create Smart App?

Create Smart App fits situations like: agent Workflows work in your project.

How do I install Create Smart App in Claude Code?

Run `npx skills add wecode-ai/Wegent --skill create-smart-app -a claude-code`. Or copy the skill folder (wework/resources/bundled-plugins/wework-personal/plugins/smart-app-builder/skills/create-smart-app in wecode-ai/Wegent) into .claude/skills/create-smart-app in your project. Claude Code loads it when a task matches its description.

How do I install Create Smart App in Codex?

Run `npx skills add wecode-ai/Wegent --skill create-smart-app -a codex`. Or copy the skill folder (wework/resources/bundled-plugins/wework-personal/plugins/smart-app-builder/skills/create-smart-app in wecode-ai/Wegent) into .agents/skills/create-smart-app in your project. Codex loads it when a task matches its description.

Can I use Create Smart App 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 wecode-ai/Wegent --skill create-smart-app -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-smart-app, .gemini/skills/create-smart-app, .github/skills/create-smart-app and .opencode/skills/create-smart-app in your project.

What does Create Smart App need to run?

Going by SKILL.md and its folder, Create Smart App needs the command-line tools its instructions call (node).

Does Create Smart App 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 Create Smart App safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Create Smart App use?

Create Smart App 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.

How many tokens does Create Smart App use?

About 927 tokens (SKILL.md is roughly 3.7k 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 Smart App?

Skills that share tags, products or a category with Create Smart App: Mindmemos CLI (mindscale-noah/MindMemOS, 1k stars), Spec Driven Develop (zhu1090093659/deepseek-pp, 1.9k stars), Remember Learnings (dyad-sh/dyad, 22k stars) and Codex Deepseek Subagent (oil-oil/codex-deepseek-subagent, 376 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Smart App?

wecode-ai (a GitHub organization) maintains it in wecode-ai/Wegent, which has 868 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 5, 2026.

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