Dynamically add specialist agents to existing Loop 3 team based on recurring feedback themes. - Preserve existing team composition - Add specialists without removing current agents - Match specialist to specific feedback themes - Security Specialist - Performance Engineer - Testing Expert - Architecture Consultant - Domain-Specific Experts ```bash ./recommend-specialist.sh \ --current-loop3 "backend-dev,coder" \ --feedback-themes "security,authentication,jwt" \ --r
Scanned 2/12/2026
Install via CLI
openskills install masharratt/claude-flow-novice# Specialist Injection Skill
## Purpose
Dynamically add specialist agents to existing Loop 3 team based on recurring feedback themes.
## Injection Strategies
- Preserve existing team composition
- Add specialists without removing current agents
- Match specialist to specific feedback themes
## Specialist Types
- Security Specialist
- Performance Engineer
- Testing Expert
- Architecture Consultant
- Domain-Specific Experts
## Usage
```bash
./recommend-specialist.sh \
--current-loop3 "backend-dev,coder" \
--feedback-themes "security,authentication,jwt" \
--recurring-count 3
```
## Decision Criteria
1. Recurring feedback theme
2. Keyword matching
3. Iteration context
4. Existing team composition
## Output Components
- Specialist to add
- Reasoning for injection
- Updated agent list
- Context modification recommendations
## Best Practices
- Non-destructive team modification
- Transparent decision process
- Actionable recommendationsNo 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', ...