core-context-management-response-format-rules
О программе
Этот навык определяет правила структурированного вывода для управления большими ответами в Claude Code, включая ограничения для таблиц, блоков кода и списков. Он предписывает использование определённого формата статуса для ответов и запрещает такие действия, как повторение ввода или предоставление неограниченных выводов. Разработчикам следует использовать его для обеспечения единообразия и предотвращения перегрузки контекста при генерации объёмного или сложного контента.
Быстрая установка
Claude Code
Рекомендуетсяnpx skills add vamseeachanta/workspace-hub/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/core-context-management-response-format-rulesСкопируйте и вставьте эту команду в Claude Code для установки этого навыка
Документация
Response Format Rules (+3)
Response Format Rules
Output Constraints
- Tables: Maximum 10 rows, summarize remainder
- Code blocks: Maximum 50 lines, split larger into files
- Lists: Maximum 15 items, aggregate beyond
- Large outputs: Write to
.claude/outputs/, return path only
Mandatory Response Ending
STATUS: [complete|in_progress|blocked] | NEXT: [action] | KEY: [metrics]
Prohibited Actions
- No Echo: Never repeat input data back
- No Redundancy: Don't repeat previous findings
- No Over-Explanation: Keep explanations ≤3 sentences
- No Raw Content: Use file paths instead of pasting
- No Unbounded Lists: Always cap with "and N more..."
Context Health Indicators
| %ctx | Status | Action |
|---|---|---|
| 0-40% | 🟢 Healthy | Normal operation |
| 40-60% | 🟡 Elevated | Consider summarizing |
| 60-80% | 🟠 High | Archive older exchanges |
| 80-100% | 🔴 Critical | Trim to essentials |
Recovery Patterns
When context exceeds threshold:
- Create checkpoint with current state
- Write to
.claude/outputs/session-state.json - Clear verbose history
- Continue with checkpoint reference only
GitHub репозиторий
Похожие навыки
algorithmic-art
МетаThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
РазработкаThis skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
ДизайнUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
ДругоеThis Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
