From core
Orchestrates structured thinking and multi-agent parallel execution for multi-step projects, complex breakdowns, architectural decisions, and task coordination.
npx claudepluginhub joaquimscosta/arkhe-claude-plugins --plugin coreThis skill uses the workspace's default tool permissions.
Guide users through structured thinking and recommend appropriate tools for complex tasks.
Orchestrates subagents by delegating tasks to role-matched specialists like engineer, reviewer, analyst for multi-agent coding workflows.
Orchestrates multi-phase feature development: research, plan, implement, review with confidence scoring, approvals, and quality gates. For complex features spanning multiple files or needing architecture decisions.
Share bugs, ideas, or general feedback.
Guide users through structured thinking and recommend appropriate tools for complex tasks.
| Situation | Recommendation |
|---|---|
| Multi-step project, full SDLC | /core:develop command |
| Plan only, implement later | /core:develop --plan-only |
| Resume existing plan | /core:develop @path/to/plan.md |
| Single complex problem needing deep analysis | /think command |
| Security-sensitive or high-stakes work | /core:develop --validate |
| Strategic decision with long-term impact | deep-think-partner agent |
| Simple task, clear steps | Inline guidance (no command needed) |
Detect these signals for structured thinking:
Keyword triggers:
Context triggers:
When structured approach is needed:
1. GATE → Is the request clear and actionable?
2. CONTEXT → What files/patterns are relevant?
3. PLAN → What tasks? Parallel vs sequential?
4. EXECUTE → Deploy specialists, maximize parallelism
5. VALIDATE → Confidence scoring (if needed)
6. REPORT → Summary with next steps
/core:develop <request> [flags]Unified SDLC command with 6-phase pipeline and multi-agent orchestration.
Flags:
--plan-only - Stop after Phase 2 (save plan, don't implement)--validate - Enable deep validation with opus agent--phase=N - Execute specific phase only--auto - Autonomous mode (no checkpoints)Best for: Feature implementations, refactoring projects, any multi-step development task.
Resume mode: /core:develop @path/to/plan.md loads existing plan and continues.
/think [problem]Invoke deep-think-partner for collaborative reasoning.
Best for: Single complex problems, decision analysis, reasoning validation, architectural decisions.
For simpler tasks, provide structured thinking directly:
| Task Type | Model | Use Case |
|---|---|---|
| Gating, routing | haiku | Quick decisions, simple queries |
| Implementation | sonnet | Standard coding, documentation |
| Deep analysis | opus | Architecture, complex reasoning |
When providing orchestration guidance:
## Recommended Approach
**Complexity:** [Low | Medium | High]
**Suggested tool:** [command or inline]
### Why
[Brief explanation of why this approach fits]
### Steps
1. [First step]
2. [Second step]
...