npx claudepluginhub melodic-software/claude-code-plugins --plugin tacThis skill is limited to using the following tools:
Guide design of composable agentic primitives for flexible workflow creation.
Orchestrates structured thinking and multi-agent parallel execution for multi-step projects, complex breakdowns, architectural decisions, and task coordination.
Designs Plan/Build/Review/Fix steps for composable AI Developer Workflows (ADWs) with contracts, isolation patterns, success criteria, and error handling.
Creates multi-agent orchestration workflows from natural language using Socratic questioning, pattern detection for sequential/parallel/conditional flows, temp script creation, and syntax generation with visualization.
Share bugs, ideas, or general feedback.
Guide design of composable agentic primitives for flexible workflow creation.
"The secret of tactical agentic coding is that it's not about the software developer lifecycle at all. It's about composable agentic primitives you can use to solve any engineering problem class."
| Primitive | Purpose | Input | Output |
|---|---|---|---|
| Classify | Categorize input | Issue/task | Classification |
| Plan | Create implementation spec | Issue | Plan file |
| Build | Implement the plan | Plan file | Code changes |
| Test | Validate functionality | Code changes | Pass/fail |
| Review | Validate alignment | Spec + code | Issue list |
| Patch | Fix specific issues | Issue description | Targeted fix |
| Document | Generate documentation | Code changes | Doc files |
| Ship | Deploy to production | Validated code | Deployed state |
| Branch | Create isolated context | Classification | Branch name |
| Commit | Save checkpoint | Changes | Commit hash |
What type of work?
Based on problem class, choose primitives:
| Problem Class | Primitives |
|---|---|
| Chore | Classify -> Build -> Test -> Ship |
| Bug | Classify -> Plan -> Build -> Test -> Review -> Ship |
| Feature | Full SDLC |
| Hotfix | Patch -> Test -> Ship |
| Documentation | Document -> Review -> Ship |
Ensure correct sequencing:
Where should failures stop the pipeline?
Plan -> Build -> [Test GATE] -> Review -> [Review GATE] -> Ship
Classify -> Plan -> Build -> Test -> Review -> Document -> Ship
Classify -> Plan -> Build -> Test -> Review -> Document -> Ship
| |
[GATE] [GATE]
Classify -> Patch -> Test -> Ship
Review -> Patch -> Test -> Ship
Consider:
Classify -> Plan -> [Compliance Review] -> Build -> Test ->
[Security Scan] -> Review -> Document -> [Approval] -> Ship
Build -> Test -> Ship (no planning for small changes)
Provide composition design:
## Workflow Composition
**Problem Class:** {type}
**Entry Trigger:** {trigger}
**Exit Criteria:** {criteria}
### Primitives Selected
1. Classify - Categorize the task
2. Plan - Create implementation spec
3. Build - Implement changes
4. Test - Validate functionality
5. Ship - Deploy to production
### Composition Flow
Classify -> Plan -> Build -> Test -> Ship | [GATE: Must pass]
### Validation Gates
- After Test: Abort if tests fail
- After Review: Optional based on confidence
### Customizations
- [Organization-specific additions]
Date: 2025-12-26 Model: claude-opus-4-5-20251101