Back to skills
SKILL.md
Response Format Rules
ASecuritySub-skill of core-context-management: Response Format Rules (+3).
- 17 stars
- 0 votes
- 0 copies
- 2 views
- Added September 9, 2026
Security analysis
100/100npx -y skills add vamseeachanta/workspace-hub --skill response-format-rules --agent claude-codeAre you the author of Response Format Rules?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-response-format-rules)---
name: core-context-management-response-format-rules
description: 'Sub-skill of core-context-management: Response Format Rules (+3).'
version: 1.0.0
category: _core
type: reference
scripts_exempt: true
---
# 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
1. **No Echo**: Never repeat input data back
2. **No Redundancy**: Don't repeat previous findings
3. **No Over-Explanation**: Keep explanations β€3 sentences
4. **No Raw Content**: Use file paths instead of pasting
5. **No Unbounded Lists**: Always cap with "and N more..."
## Context Health Indicators
| %ctx | Status | Action |
|------|--------|--------|
| 0-40% | π’ Healthy | Normal operation |
| 40-60% | π‘ Elevated | Consider summarizing |
| 60-80% | π High | Archive older exchanges |
| 80-100% | π΄ Critical | Trim to essentials |
## Recovery Patterns
When context exceeds threshold:
1. Create checkpoint with current state
2. Write to `.claude/outputs/session-state.json`
3. Clear verbose history
4. Continue with checkpoint reference only
---
Attribution
Comments
Loading commentsβ¦
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.