DeepSeek HarnessHub
プラグインを投稿

adithya-hmt/fullstack-expert ↗★ 0

@deepseek-ai/fullstack-expert

Cordis-native, evidence-driven full-stack engineering discipline for DeepSeek Harness agents

AI 分析

为DSH智能体引入证据驱动的全栈工程规范，通过规划、检查和验证流程确保代码质量。适合需要AI进行严谨、高质量全栈开发任务的用户。

エージェント開発ツール
パッケージ
@deepseek-ai/fullstack-expert
バージョン
0.1.1
ライセンス
MIT
最終更新
2026/08/16

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:adithya-hmt/fullstack-expert

ドキュメント

README 全文を読む ↗

Usage

  1. Start with a composition containing the plugin and native Harness filesystem/tool/skill rows.
  2. Ask for a feature, bug fix, review, refactor, or application build.
  3. The agent should call fullstack_plan for substantial work, inspect actual files, state assumptions/unknowns, and implement a vertical slice with native tools.
  4. Use fullstack_check for bounded structure/command/Supabase checks and to record non-verification review facts. Verification evidence must come from a native Harness check; V0.1 rejects self-attested verification records.
  5. Completion is only justified after a native verification evidence record passes and relevant failures are absent.

The native shell tool reports its [exit code: N] marker; investigate every non-zero result. For browser work, use the composed browser capability and record actual console/network/UI evidence rather than treating a build as proof.