paper2code

Converts an arxiv paper into a minimal, citation-anchored Python implementation. Trigger when user runs /paper2code with an arxiv URL or paper ID, says "implement this paper", or pastes an arxiv link asking for implementation. Flags all ambiguities honestly. Never invents implementation details not stated in the paper.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "paper2code" with this command: npx skills add prathamlearnstocode/paper2code/prathamlearnstocode-paper2code-paper2code

paper2code — Orchestration

You are executing the paper2code skill. This file governs the high-level flow. Each stage dispatches to a detailed reasoning protocol in pipeline/. Do NOT skip stages. Do NOT combine stages. Execute them in order.

Parse arguments

Extract from the user's input:

  • ARXIV_ID: the arxiv paper ID (e.g., 2106.09685). Strip any URL prefix.
  • MODE: one of minimal (default), full, educational.
  • FRAMEWORK: one of pytorch (default), jax, numpy.

If the user provided a full URL like https://arxiv.org/abs/2106.09685, extract the ID 2106.09685. If the user provided a versioned ID like 2106.09685v2, keep the version.

Set up working directory

Create a temporary working directory: .paper2code_work/{ARXIV_ID}/ This is where intermediate artifacts go. The final output goes in the current directory under {paper_slug}/.

Install dependencies

Run via Bash:

pip install pymupdf4llm pdfplumber requests pyyaml

Execute pipeline

Stage 1 — Paper Acquisition and Parsing

Read and follow: pipeline/01_paper_acquisition.md

Run the helper script to fetch and parse the paper:

python skills/paper2code/scripts/fetch_paper.py {ARXIV_ID} .paper2code_work/{ARXIV_ID}/

Then run structure extraction:

python skills/paper2code/scripts/extract_structure.py .paper2code_work/{ARXIV_ID}/paper_text.md .paper2code_work/{ARXIV_ID}/

Verify the outputs exist before proceeding. If extraction failed, follow the fallback protocol in pipeline/01_paper_acquisition.md.

The script also searches for official code repositories (in the paper text and on the arxiv page) and saves any found links to paper_metadata.json under the official_code key. Verify these links before relying on them — see Step 8 in pipeline/01_paper_acquisition.md.

Stage 2 — Contribution Identification

Read and follow: pipeline/02_contribution_identification.md

Read the parsed paper sections. Identify the single core contribution. Classify the paper type. Write the contribution statement. Save it to .paper2code_work/{ARXIV_ID}/contribution.md.

Stage 3 — Ambiguity Audit

Read and follow: pipeline/03_ambiguity_audit.md

Before reading this stage, also read: guardrails/hallucination_prevention.md

Go through every implementation-relevant detail. Classify each as SPECIFIED, PARTIALLY_SPECIFIED, or UNSPECIFIED. Save the audit to .paper2code_work/{ARXIV_ID}/ambiguity_audit.md.

Stage 4 — Code Generation

Read and follow: pipeline/04_code_generation.md

Before writing code, read:

  • guardrails/scope_enforcement.md — to determine what's in and out of scope
  • guardrails/badly_written_papers.md — if the paper is vague or inconsistent
  • The relevant knowledge files in knowledge/ for the paper's domain
  • The scaffold templates in scaffolds/ for the expected file structure

Determine the paper_slug from the paper title (lowercase, underscores, no special chars). Generate all files under {paper_slug}/ in the current working directory.

Stage 5 — Walkthrough Notebook

Read and follow: pipeline/05_walkthrough_notebook.md

Generate the walkthrough notebook that connects paper sections to code with runnable sanity checks. Save to {paper_slug}/notebooks/walkthrough.ipynb.

Cleanup

Remove the .paper2code_work/ directory after successful completion.

Final output

Print a summary:

✓ paper2code complete for: {paper_title}
  Output directory: {paper_slug}/
  Files generated: {list of files}
  Unspecified choices: {count} (see REPRODUCTION_NOTES.md)
  Mode: {MODE} | Framework: {FRAMEWORK}

Mode-specific behavior

  • minimal (default): Core contribution only. Training loop only if contribution involves training. No data pipeline beyond Dataset skeleton.
  • full: Core contribution + full training loop + data pipeline + evaluation pipeline. More code, same citation rigor.
  • educational: Same as minimal but with extra inline comments explaining ML concepts, expanded walkthrough notebook with theory sections, and a PAPER_GUIDE.md that walks through the paper section by section.

Guardrails — always active

These apply at ALL stages. Read them if you haven't already:

  • guardrails/hallucination_prevention.md — the most important file in this skill
  • guardrails/scope_enforcement.md — what to implement and what to skip
  • guardrails/badly_written_papers.md — what to do when the paper is unclear

Knowledge base — consult as needed

Before implementing any of these components, read the corresponding knowledge file:

  • Transformer layers, attention, positional encoding → knowledge/transformer_components.md
  • Optimizers, LR schedules, batch size semantics → knowledge/training_recipes.md
  • Cross-entropy, contrastive loss, diffusion loss, ELBO → knowledge/loss_functions.md
  • Framework-specific pitfalls, notation mismatches → knowledge/paper_to_code_mistakes.md

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHubOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Coding

CodeBuddy Coding

# CodeBuddy Coding Skill **版本：** 1.0.0 **创建时间：** 2026-03-31 **作者：** OpenClaw Team --- ## 📋 Skill 概述 **CodeBuddy Coding Skill** 是一个通用的 AI 编程能力扩展，让任何 OpenClaw agent 都能调用 CodeBuddy CLI 的强大功能。 ### 核心能力 - ✅ **AI 编程** - 代码生成、重构、调试、优化 - ✅ **文件操作** - 创建、修改、删除文件 - ✅ **命令执行** - 运行构建、测试、部署命令 - ✅ **进度监控** - 实时报告任务进度和状态 - ✅ **结构化输出** - JSON 格式的可解析输出 ### 适用场景 - **Developer Agent** - 编写代码、修复 Bug - **Architect Agent** - 生成项目脚手架 - **Tester Agent** - 编写测试用例 - **任何需要编程能力的 Agent** - 通用编程支持 --- ## 🚀 快速开始 ### 基本用法 ```javascript // 1. 加载 Skill const codebuddy = require('./skill'); // 2. 执行编程任务 const result = await codebuddy.execute({ task: '创建一个用户登录页面', context: { projectPath: '/path/to/project', techStack: 'Vue 3 + TypeScript' }, options: { outputFormat: 'json', permissionMode: 'bypassPermissions' } }); // 3. 获取结果 console.log(result.status); // 'success' console.log(result.filesModified); // ['src/views/Login.vue'] console.log(result.toolCalls); // [{tool: 'write_to_file', ...}] ``` ### 监听进度 ```javascript // 订阅进度事件 codebuddy.onProgress((progress) => { console.log(`进度: ${progress.percentage}%`); console.log(`当前任务: ${progress.currentTask}`); console.log(`已用时间: ${progress.elapsedTime}s`); }); ``` --- ## 🔧 配置说明 ### 环境要求 - **CodeBuddy CLI** v2.68.0+ - **Node.js** v16.0.0+ - **OpenClaw** coding-agent skill 框架 ### Skill 配置 ```json { "name": "codebuddy-coding", "version": "1.0.0", "type": "coding", "capabilities": [ "code-generation", "file-operations", "command-execution", "progress-monitoring" ], "dependencies": { "codebuddy-cli": ">=2.68.0" } } ``` --- ## 📚 API 文档 ### `execute(options)` 执行编程任务。 **参数：** ```typescript interface ExecuteOptions { task: string; // 任务描述 context?: { // 任务上下文 projectPath?: string; // 项目路径 techStack?: string; // 技术栈 files?: string[]; // 相关文件 }; options?: { // 执行选项 outputFormat?: 'json' | 'text'; // 输出格式 permissionMode?: 'default' | 'bypassPermissions'; // 权限模式 timeout?: number; // 超时时间（秒） }; } ``` **返回：** ```typescript interface ExecuteResult { status: 'success' | 'failed' | 'timeout'; filesModified: string[]; // 修改的文件列表 toolCalls: ToolCall[]; // 工具调用记录 reasoning: string[]; // 推理过程 duration: number; // 执行时长（秒） error?: string; // 错误信息 } ``` ### `onProgress(callback)` 订阅进度更新事件。 **参数：** ```typescript type ProgressCallback = (progress: { percentage: number; // 完成百分比 currentTask: string; // 当前任务描述 elapsedTime: number; // 已用时间（秒） estimatedTime?: number; // 预计剩余时间（秒） filesModified: string[]; // 已修改文件 toolCalls: number; // 已调用工具次数 }) => void; ``` ### `getStatus()` 获取当前任务状态。 **返回：** ```typescript interface TaskStatus { state: 'idle' | 'running' | 'completed' | 'failed'; taskId?: string; startTime?: Date; progress?: Progress; } ``` --- ## 🎯 使用示例 ### 示例1：创建新组件 ```javascript const codebuddy = require('./skill'); // 创建登录组件 const result = await codebuddy.execute({ task: '创建一个用户登录组件，包含用户名、密码输入框和登录按钮', context: { projectPath: '/path/to/vue-project', techStack: 'Vue 3 Composition API + TypeScript' } }); if (result.status === 'success') { console.log('组件创建成功！'); console.log('创建的文件:', result.filesModified); } ``` ### 示例2：修复 Bug ```javascript const codebuddy = require('./skill'); // 修复登录验证 Bug const result = await codebuddy.execute({ task: '修复用户登录时的验证逻辑，密码应该至少8位且包含数字和字母', context: { projectPath: '/path/to/project', files: ['src/views/Login.vue', 'src/utils/validator.ts'] } }); console.log('修复完成:', result.filesModified); ``` ### 示例3：监听长时间任务进度 ```javascript const codebuddy = require('./skill'); // 订阅进度 codebuddy.onProgress((progress) => { console.log(`[${progress.percentage}%] ${progress.currentTask}`); console.log(` 已修改 ${progress.filesModified.length} 个文件`); console.log(` 已执行 ${progress.toolCalls} 次操作`); console.log(` 用时 ${progress.elapsedTime}s`); }); // 执行长时间任务 const result = await codebuddy.execute({ task: '重构整个用户管理模块，使用更清晰的架构', context: { projectPath: '/path/to/project' }, options: { timeout: 600 // 10分钟超时 } }); ``` --- ## 🔍 进度监控原理 ### JSON 输出解析 CodeBuddy CLI 支持 `--output-format json` 输出结构化数据： ```bash codebuddy -p "任务描述" --output-format json --permission-mode bypassPermissions ``` **输出格式：** ```json { "status": "running", "tool_calls": [ { "tool": "write_to_file", "parameters": { "filePath": "src/Login.vue", "content": "..." }, "result": "success" } ], "files_modified": ["src/Login.vue"], "reasoning": [ "分析任务需求", "设计组件结构", "编写代码" ], "progress": { "percentage": 45, "current_task": "编写登录表单" } } ``` ### 进度解析流程 ```mermaid graph LR A[CodeBuddy CLI] -->|JSON Stream| B[Progress Monitor] B -->|Parse JSON| C[Progress Data] C -->|Emit Event| D[Event Callbacks] D -->|Update| E[Agent UI] ``` --- ## ⚙️ 高级配置 ### 自定义输出解析器 ```javascript const codebuddy = require('./skill'); // 自定义解析器 codebuddy.setOutputParser((jsonLine) => { // 自定义解析逻辑 return { percentage: jsonLine.progress?.percentage || 0, task: jsonLine.progress?.current_task || '处理中' }; }); ``` ### 超时和重试 ```javascript const result = await codebuddy.execute({ task: '复杂重构任务', options: { timeout: 1200, // 20分钟超时 retryCount: 3, // 失败重试3次 retryDelay: 5000 // 重试间隔5秒 } }); ``` --- ## 🐛 调试和日志 ### 启用详细日志 ```javascript const codebuddy = require('./skill'); // 启用调试模式 codebuddy.setDebugMode(true); // 所有 CLI 输出会被记录到控制台 const result = await codebuddy.execute({ task: '创建测试文件' }); ``` ### 查看执行日志 ```javascript // 获取最近的执行日志 const logs = codebuddy.getExecutionLogs(); console.log(logs); // [ // { time: '11:30:01', event: 'CLI_START', command: '...' }, // { time: '11:30:02', event: 'TOOL_CALL', tool: 'write_to_file' }, // { time: '11:30:05', event: 'CLI_END', status: 'success' } // ] ``` --- ## 🚨 错误处理 ### 错误类型 ```typescript enum CodeBuddyErrorType { CLI_NOT_FOUND = 'CLI_NOT_FOUND', // CodeBuddy CLI 未安装 INVALID_TASK = 'INVALID_TASK', // 无效的任务描述 TIMEOUT = 'TIMEOUT', // 执行超时 PERMISSION_DENIED = 'PERMISSION_DENIED', // 权限被拒绝 CLI_ERROR = 'CLI_ERROR' // CLI 执行错误 } ``` ### 错误处理示例 ```javascript try { const result = await codebuddy.execute({ task: '创建文件' }); } catch (error) { if (error.type === 'CLI_NOT_FOUND') { console.error('请先安装 CodeBuddy CLI'); } else if (error.type === 'TIMEOUT') { console.error('任务超时，请增加超时时间'); } else { console.error('执行失败:', error.message); } } ``` --- ## 📦 集成到 Agent ### Developer Agent 集成 ```javascript // developer/agent.js const codebuddy = require('codebuddy-coding'); class DeveloperAgent { async implementFeature(task) { // 使用 CodeBuddy 实现功能 const result = await codebuddy.execute({ task: task.description, context: { projectPath: this.projectPath, files: task.relatedFiles } }); return result; } } ``` ### Architect Agent 集成 ```javascript // architect/agent.js const codebuddy = require('codebuddy-coding'); class ArchitectAgent { async generateProjectScaffold(requirements) { // 使用 CodeBuddy 生成脚手架 const result = await codebuddy.execute({ task: `创建项目脚手架：${requirements}`, options: { permissionMode: 'bypassPermissions' } }); return result; } } ``` --- ## 🧪 测试 ### 运行测试 ```bash # 运行所有测试 npm test # 运行特定测试 npm test -- --grep "CLI Wrapper" ``` ### 测试覆盖 - ✅ CLI Wrapper 单元测试 - ✅ Progress Monitor 单元测试 - ✅ Integration 集成测试 - ✅ E2E 端到端测试 --- ## 📄 许可证 MIT License --- ## 🤝 贡献 欢迎提交 Issue 和 Pull Request！ --- ## 📞 支持 如有问题，请联系： - GitHub Issues: [OpenClaw Repository] - Email: support@openclaw.ai --- **让每个 Agent 都拥有 AI 编程能力！** 🚀

Archived SourceRecently Updated
--13770626440
Coding

anti-sycophancy

Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).

Archived SourceRecently Updated
--0xcjl
Coding

validation-rule-management

管理校验规则、规则组和校验场景的全流程操作。支持通过统一 CLI 工具快速执行 API 调用，自动处理参数解析、配置加载和错误提示。使用当用户需要进行校验规则管理、规则组维护、校验场景配置、启停操作或相关查询时，即使用户只说"帮我创建一条规则"或"查一下场景列表"也应触发。

Archived SourceRecently Updated
--12266601032
Coding

mcdonalds-skill

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.

Archived SourceRecently Updated
--1052666