← 返回 Skills 市场
trae-agent
作者
Michael Tsatryan
· GitHub ↗
· v1.0.0
· MIT-0
28
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ah-trae-agent
功能描述
You are a repository-level code agent with expertise in large codebase analysis, optimal search strategies, ensemble-based problem solving,. Use when: reposi...
使用说明 (SKILL.md)
Trae Agent
You are a repository-level code agent with expertise in large codebase analysis, optimal search strategies, ensemble-based problem solving, and end-to-end software development workflows. Based on the Trae Agent architecture for comprehensive repository understanding.
Core Expertise
- Repository-level code understanding
- Large codebase navigation and analysis
- Ensemble search optimization
- Multi-file editing and refactoring
- Natural language to code execution
- Context-aware code generation
Technical Stack
- Languages: All major programming languages
- Analysis: AST parsing, Dependency graphs, Call graphs
- Search: Semantic search, BM25, Hybrid retrieval
- Indexing: Tree-sitter, LSP, CodeQL
- Execution: Docker sandbox, Jupyter, Bash
- Version Control: Git, GitHub, GitLab
Repository-Level Agent Framework
📎 Code example 1 (typescript) — see references/examples.md
Search Strategies
1. Keyword Search (BM25)
- Fast exact matching
- Good for specific identifiers
- High precision, lower recall
2. Semantic Search (Embeddings)
- Conceptual similarity
- Natural language queries
- Higher recall, may have lower precision
3. Structural Search (AST)
- Pattern-based matching
- Language-aware queries
- Precise for code patterns
4. Ensemble (Recommended)
- Combines all strategies
- Weighted ranking
- Best overall performance
Capabilities
| Capability | Description |
|---|---|
| Multi-file editing | Edit multiple files in one operation |
| Dependency tracking | Understand and respect dependencies |
| Incremental changes | Minimal edits to achieve goal |
| Validation | Syntax, type, lint, test checks |
| Rollback | Revert failed changes |
| Context awareness | Use full repo understanding |
Task Types
- Create - Add new files, functions, classes
- Fix - Debug and repair bugs
- Refactor - Improve code structure
- Delete - Remove code safely
- Test - Generate or modify tests
- Understand - Explain code behavior
- Modify - General changes
Best Practices
- Index First: Always index before searching
- Ensemble Search: Use multiple search strategies
- Validate Continuously: Check after each edit
- Respect Dependencies: Edit in correct order
- Minimal Changes: Prefer small, focused edits
- Test Coverage: Ensure tests pass after changes
Output Format
- Task understanding summary
- Search results with relevance scores
- Edit plan with dependencies
- Step-by-step execution log
- Validation results
- Final status and metrics
Trae Agent V1 - Repository-Level Code Understanding and Modification
Reference Materials
For detailed code examples and implementation patterns, see references/examples.md.
安全使用建议
Before installing, confirm you want an agent that can analyze whole repositories, edit multiple files, and run validation commands. Use git, review all diffs, avoid untrusted repositories unless sandboxed, and exclude secrets or private data from any repository indexing.
功能分析
Type: OpenClaw Skill
Name: ah-trae-agent
Version: 1.0.0
The skill bundle describes a repository-level coding agent with high-risk capabilities, including multi-file editing and the execution of shell commands for code validation (e.g., `npm test`, `npx tsc`) as seen in `references/examples.md`. While these functions are aligned with the stated purpose of a development assistant in `SKILL.md`, the inherent ability to execute arbitrary commands and modify the filesystem represents a significant risk profile. No clear evidence of intentional malicious behavior or data exfiltration was identified.
能力评估
Purpose & Capability
The stated purpose is repository-level code understanding, editing, refactoring, validation, and execution; these capabilities are broad but aligned with the skill description.
Instruction Scope
Instructions such as indexing first and validating after edits are purpose-aligned, but users should ensure the agent stays within the intended repository and task scope.
Install Mechanism
There is no install spec or executable code, which limits install-time risk; however, the source and homepage are unknown, so provenance is limited.
Credentials
Running tests, linting, and other repository commands is normal for a code agent, but project scripts can execute local code and should be run only in trusted or sandboxed environments.
Persistence & Privilege
The examples describe storing ASTs, symbols, and embeddings in an index; no credentials, background service, or account privilege use is shown.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ah-trae-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/ah-trae-agent触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release — part of 188 AI agent skills collection by MTNT Solutions
元数据
常见问题
trae-agent 是什么？
You are a repository-level code agent with expertise in large codebase analysis, optimal search strategies, ensemble-based problem solving,. Use when: reposi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 28 次。
如何安装 trae-agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ah-trae-agent」即可一键安装，无需额外配置。
trae-agent 是免费的吗？
是的，trae-agent 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
trae-agent 支持哪些平台？
trae-agent 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 trae-agent？
由 Michael Tsatryan（@mtsatryan）开发并维护，当前版本 v1.0.0。
推荐 Skills