codeartsagent

@codeartsagent source repo

7 skills
0 followers
6 hours ago last updated

▌
Brainstorming · codeartsagent bundle
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

0
installs
▌
Code Arena Cn · codeartsagent bundle
评测/对比同一需求(或同一代码仓多个分支)的多个代码实现并打分。当用户要『开始一轮评测/评估项目』『对比同一需求下的多个实现』『对比一个仓库的多个分支』『按 basic + round rubric 打分』『跑 API/视觉/SAST/架构/治理/覆盖率评测并出中英双语报告』时使用。

0
installs
▌
Code Arena En · codeartsagent bundle
Evaluate, score, and compare multiple implementations of the same requirement — different builds, or multiple branches of one repo. Use when the user asks to start/run an evaluation round, compare several implementations, compare branches of a repo, score projects against the basic + round rubrics, or run API / visual / SAST / architecture / governance / coverage checks and produce a bilingual (English + Chinese) report.

0
installs
▌
Codebase Arena · codeartsagent bundle
Build, execute, and judge human-reviewed Chinese-English bilingual codebase capability benchmarks. Use when an agent must generate a repository-specific evalset, run an approved evalset inside a tested desktop coding agent through fresh single-case subagents, or independently judge and compare completed raw runs. Route to the generation, execution, or report workflow; require structured human intake at the start of every new workflow; keep private result-verification material unavailable to evaluated agents; generate only read-only code-understanding cases with no code-generation load while preserving legacy execution/report compatibility; produce one 0-10 score per system and case; and never install or change dependencies without explicit user approval.

0
installs
▌
Skill Installer · codeartsagent bundle
Single entry point to install, update, delete, or check the status of any supported CodeArts skill/tool installer. Consolidates four installers behind one skill: superpowers, office-mcp, playwright-cli, and openspec. OpenSpec and other tools don't natively support CodeArts; this meta-installer bridges them. Specify the target via --target <name> (or positionally). Use whenever the user wants to install/update/delete any of these targets, or to list what's supported. Triggers on: install superpowers, install office-mcp, install playwright-cli, install openspec, 一键安装技能, 安装技能, skill installer, update skills, uninstall skills, 安装openspec, 安装office文档工具, 安装浏览器自动化工具.

0
installs
▌
Sdlc Agentic Pipeline · codeartsagent bundle
Orchestrate a complete multi-agent SDLC pipeline powered by Huawei Cloud CodeArts Agent. 8 agents (PM, Backend, Frontend, Code Reviewer, Tester, DevOps, Architect, Figma Design) across 10 steps from requirements through deployment. Integrates GitHub, Jira, SonarCloud, Semgrep, JFrog, Playwright, Huawei Cloud ECS, Azure DevOps, Figma. Trigger: "start agentic flow", "SDLC pipeline", "agentic DevOps pipeline", "multi-agent development workflow", "figma to code".

0
installs
▌
Postman · codeartsagent bundle
Connects CodeArts Agent to Postman's official MCP server for API testing, collection, and workspace management - run collections with test results, create/update workspaces, collections, environments, mocks, and specs, generate collections from OpenAPI specs, and search across your Postman resources, without opening the Postman app. Also supports projects whose Postman collection was never synced to a cloud account (offline / local-only), by editing the exported collection JSON file directly instead of using MCP. Use whenever the user asks to run a Postman collection, test an API via Postman, create or update a Postman collection/environment/workspace/mock/spec, sync code with an OpenAPI spec, search for an existing API/collection, list their Postman workspaces, or edit a local/offline Postman collection file.

0
installs

7 published skills