aictxt-manager
生成、维护、修剪AICTXT文档，保持在CRAFT大小限制内。当AICTXT创建和更新时使用。
Best use case
aictxt-manager is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
生成、维护、修剪AICTXT文档，保持在CRAFT大小限制内。当AICTXT创建和更新时使用。
Teams using aictxt-manager should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/aictxt-manager/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How aictxt-manager Compares
| Feature / Agent | aictxt-manager | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
生成、维护、修剪AICTXT文档，保持在CRAFT大小限制内。当AICTXT创建和更新时使用。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
## aictxt-manager: AI上下文管理 ### 描述 生成、维护、修剪AICTXT（AI Context Text）文档，确保AI代码生成的上下文大小在CRAFT标准限制内。 ### 适用场景 - **WORKFLOW_STEP_5 Task S5-2**: AICTXT创建初期，生成初始内容 - **WORKFLOW_STEP_5 Task S5-3**: Self-Reflection中定期审视和修剪 - **实施过程中**: 当AICTXT增长过大时，需要修剪 ### 输入 - spec/implementation/ai_context.md（当前AICTXT） - goal_breakdown.md（GOAL清单） - scenarios/bdd_test_scenarios.md（关键SC） - design/（架构和设计约束） - 当前级别（L1/L2/L3） ### 输出 - AICTXT审视报告（markdown） - 当前大小分析（行数/Token数） - 对标标准： - L1: ≤5000字/≤1000行 - L2: ≤8000字/≤1500行 - L3: ≤12000字/≤2000行 - 修剪建议（删除/压缩/分离的内容） - 优化后的AICTXT片段 ### AICTXT内容结构 **标准AICTXT结构（按优先级）**： ``` # AI Context - [项目名] [GOAL ID] ## 业务背景 (A级-关键) - 用户故事: [US简述] - 业务价值: [为什么重要] - 成功标准: [AC清单] ## 技术约束 (A级-关键) - 技术栈: [框架/库/版本] - 关键依赖: [外部服务/API] - 性能要求: [响应时间/并发等] ## 实现目标 (A级-关键) - GOAL: [G-NNN 描述] - 关联SC: [SC-NNN, SC-NNN] - 模块: [module_name] ## 架构概览 (B级-重要) - 系统设计: [简要架构] - 关键接口: [API/方法签名] - 数据流: [输入→处理→输出] ## 已知约束 (B级-重要) - 不能修改: [列表] - 必须遵循: [规范/模式] - 边界条件: [特殊情况] ## 参考链接 (C级-可选) - 详细设计: [链接] - 相关GOAL: [链接] - 测试场景: [链接] ``` ### 执行策略 **第1步: 读取和分析** - 读取当前ai_context.md - 计算大小（字数/行数/Token数） - 对标CRAFT标准 **第2步: 关键性分析** - A级（关键）: GOAL/SC/业务背景/技术约束 - B级（重要）: 架构概览/关键接口/已知约束 - C级（可选）: 详细实现/背景知识/参考链接 **第3步: 修剪方案** - 删除C级非关键内容 - 压缩B级冗余表达（用表格替代长段落） - 链接到外部文档而非嵌入 - 删除过期或已完成的信息 **第4步: 大小优化** | 优化技巧 | 效果 | |---------|------| | 用表格替代列表 | 节省20-30% | | 删除示例代码 | 节省30-40% | | 链接替代嵌入 | 节省40-50% | | 缩写术语 | 节省10-15% | **第5步: L1/L2/L3分级** - **L1**: 仅A级内容，≤1000行 - **L2**: A级+B级核心，≤1500行 - **L3**: 完整A级+B级，≤2000行 **第6步: 生成优化版本** - 保留关键信息完整 - 删除冗余表达 - 添加清晰的链接 ### 价值 - **AI Pair/Devs**: AICTXT大小管理，提升AI代码生成效率 - **Tech Lead**: 清晰的上下文焦点，避免AI分散注意力 - **成本**: 减少Token消耗，降低AI调用成本 ### 验收标准 - AICTXT大小在CRAFT限制内 - 关键信息完整（GOAL/SC/约束） - 冗余信息已删除 - 链接清晰可追溯
Related Skills
ai-sdk-model-manager
Manages AI SDK model configurations - updates packages, identifies missing models, adds new models with research, and updates documentation
account_manager
安全地管理用户账号信息（CRUD）。支持存储密码、API Key、Cookies 等敏感信息，并支持 TOTP (MFA) 代码生成。**所有涉及凭证存储的操作必须优先使用此技能**，不可用于账号注册。
academic-bibtex-manager
When the user requests to add academic papers to a BibTeX bibliography file while maintaining format consistency and sourcing from appropriate repositories. This skill handles 1) Reading existing BibTeX files to understand formatting conventions, 2) Searching for academic papers across multiple sources (OpenReview for conference papers, arXiv for preprints), 3) Extracting proper BibTeX metadata from conference pages or arXiv entries, 4) Determining appropriate citation format (@article vs @inproceedings) based on publication venue, 5) Appending new entries while preserving existing file structure and formatting. Triggers include requests to 'add to ref.bib', 'update bibliography', 'cite papers', or when working with academic reference files.
ac-memory-manager
Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.
Asset Manager
Organize design assets, optimize images and fonts, maintain brand asset libraries, implement version control for assets, and enforce naming conventions. Keep design assets organized and production-ready.
subagent_manager
Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates
skill-manager
Manage, sync, and publish Agent Skills across multiple AI platforms (Claude, Codex, Gemini, Copilot) and marketplace repositories. Use when users want to list skills, sync between platforms, publish to marketplace keys, mirror canonical skills, audit drift, or set up their environment. Triggers on phrases like "list skills", "sync skills", "publish skill", "skill marketplace", "deploy skill", "audit skills", or "skill inventory".
risk-manager
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
naiba-openai-managers
ChatGPT use cases and prompts for managers | Part of naiba-openai-work-assistant
llm-manager
Claude acts as manager/architect while delegating all coding to external LLM CLIs (Gemini, Codex, Qwen). Claude never writes code - only plans, delegates, and verifies. Use when user says "manage", "architect mode", "delegate to", or wants Claude to drive another LLM.
data-pipeline-manager
Design and troubleshoot robust data pipelines with comprehensive quality validation, error handling, and monitoring capabilities for bioinformatics and data processing workflows
agent-risk-manager
Expert risk manager specializing in comprehensive risk assessment, mitigation strategies, and compliance frameworks. Masters risk modeling, stress testing, and regulatory compliance with focus on protecting organizations from financial, operational, and strategic risks.