项目上下文自动更新器。当新增功能、重构代码、修改架构时触发,确保 project_context.md 保持最新。触发词:新功能, 重构, 架构变更, 新模块, 新系统, 完成实现。
Scanned 6/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill context-updater --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Context Updater Hongliangc Combo Demon?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-context-updater-hongliangc-combo-demon)More formats (shields.io, HTML) on the badges page.
---
name: context-updater
description: 项目上下文自动更新器。当新增功能、重构代码、修改架构时触发,确保 project_context.md 保持最新。触发词:新功能, 重构, 架构变更, 新模块, 新系统, 完成实现。
---
# 项目上下文更新器
当项目发生重大变更时,自动提醒更新 `.claude/context/project_context.md`。
## 触发判断
### ✅ 需要更新
- 新增 AutoLoad / 核心系统 / 重要组件
- 架构重构(状态机、依赖关系、数据流)
- 修改输入映射 / 物理层配置
- 完成重要功能实现
### ❌ 不需要更新
- bug修复、参数调整、性能优化(不涉及架构)
- UI样式调整、添加注释
## 更新原则
**文件**: `.claude/context/project_context.md`
1. **简洁优先** - 每个模块 ≤ 3 行描述
2. **结构化** - 使用列表/表格,避免段落
3. **架构级别** - 只记录架构信息,不含实现细节
4. **控制总量** - 保持 < 4000 tokens
## 更新示例
**变更**: 新增 SkillManager AutoLoad
**更新内容**:
```markdown
### AutoLoad 系统
- **SkillManager**: 技能管理,处理释放和冷却
```
**变更**: 实现连招系统
**更新内容**:
```markdown
### 连招系统
- **功能**: 检测输入序列,触发特殊技能
- **关键类**: ComboDetector, ComboData (Resource)
- **信号**: combo_triggered(combo_name: String)
```
## 自动检查清单
完成以下任务时,检查是否需要更新 context:
- [ ] 新增 AutoLoad 脚本
- [ ] 创建核心系统
- [ ] 重构状态机框架
- [ ] 修改输入/物理层配置
- [ ] 完成重要功能
## 更新流程
1. 检测变更范围(AutoLoad/核心模块/配置)
2. 读取 project_context.md,识别需要更新的章节
3. 生成简洁内容(≤3行/模块)
4. 验证 token 数量 < 4000,删除过时信息
5. 保存文件
## 提醒机制
**触发条件**:
- 检测到 `Util/AutoLoad/` 新增脚本
- 对话中出现 "完成"、"重构" 关键词
- 修改了状态机、伤害系统等框架代码
**提醒用户**: 列出变更内容,询问是否更新 context
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.