From tac
Designs composable prompt sections for agentic prompts using tiered structure (S-tier Workflow), level-based requirements, and templates for Metadata, Variables, Workflow. Use for creating, restructuring, or standardizing prompts.
npx claudepluginhub melodic-software/claude-code-plugins --plugin tacThis skill is limited to using the following tools:
Design composable prompt sections that work like LEGO blocks for building prompts at any level.
Generates agentic prompts at levels 1-7 via meta-prompting for slash commands and workflows. Designs variables, steps, and saves to .claude/commands. Invoke: /create-prompt [level] [purpose].
Crafts or updates LLM prompts from first principles by discovering goals, constraints, and context through targeted questions. Use for new prompts, updates, or reviews.
Transforms vague or unreliable prompts into structured, constraint-aware prompts with roles, task decomposition, output formats, and quality checks. Useful for inconsistent outputs, multi-step reasoning, safety guardrails, or prompt optimization.
Share bugs, ideas, or general feedback.
Design composable prompt sections that work like LEGO blocks for building prompts at any level.
Create well-structured prompt sections that are reusable, consistent, and effective for the stakeholder trifecta.
| Tier | Sections | Priority |
|---|---|---|
| S | Workflow | Always include (Level 2+) |
| A | Variables, Examples, Control Flow, Delegation, Template | High value |
| B | Purpose, High-Level, Higher Order, Instructions | Supporting |
| C | Metadata, Codebase Structure, Relevant Files, Report | As needed |
Ask:
Based on level:
| Level | Required | Recommended |
|---|---|---|
| 1 | Title, Prompt | - |
| 2 | Title, Workflow | Variables, Report |
| 3 | Title, Workflow | Variables, Control Flow |
| 4 | Title, Workflow | Variables, Delegation |
| 5 | Title, Workflow | Variables |
| 6 | Title, Workflow, Template | Variables |
| 7 | Title, Workflow, Expertise | Variables |
---
description: Clear, searchable description
argument-hint: [arg1] [arg2]
allowed-tools: Read, Write, Edit
model: sonnet
---
Guidelines:
description: What does it do? When to use?argument-hint: What parameters expected?allowed-tools: Minimal set neededmodel: Match to task complexity# Action-Oriented Title
Guidelines:
## Purpose
[1-2 sentences describing what the prompt accomplishes]
Guidelines:
## Variables
# Dynamic (from user)
USER_PROMPT: $ARGUMENTS
FILE_PATH: $1
COUNT: $2 or 3 if not provided
# Static (fixed)
OUTPUT_DIR: specs/
MODEL: sonnet
Guidelines:
## Workflow
1. Validate inputs
- Check USER_PROMPT is provided
- If not, STOP and ask user
2. Process task
- Sub-step detail
3. Generate output
4. Report results
Guidelines:
## Instructions
- IMPORTANT: Always validate before processing
- Handle edge cases gracefully
- Never modify files outside project
Guidelines:
## Report
## Task Complete
**Files:** [count]
**Status:** [status]
### Changes
- [change 1]
- [change 2]
Guidelines:
## Specified Format
```text
---
allowed-tools: <tools>
description: <description>
---
# <name>
## Variables
<VAR>: $1
## Workflow
<steps>
Guidelines:
## Expertise
### Domain Knowledge
- Pattern 1 learned
- Pattern 2 discovered
### Discovered Patterns
- Implementation insight 1
- Best practice 2
Guidelines:
Checklist:
---
[frontmatter]
---
# [Title]
## Purpose
[purpose]
## Variables
[variables]
## Instructions
[instructions]
## Workflow
[workflow]
## Report
[report format]
When designing sections:
## Section Design
**Prompt:** [name]
**Level:** [1-7]
### Recommended Sections
1. **Title**: [suggested title]
2. **Frontmatter**:
```yaml
description: ...
argument-hint: ...
allowed-tools: ...
model: ...
```
1. **Variables**:
- Dynamic: [list]
- Static: [list]
2. **Workflow**: [step count] steps
- Step 1: [overview]
- Step 2: [overview]
...
3. **Report**: [format type]
| Anti-Pattern | Problem | Solution |
|---|---|---|
| No Workflow section | Agent lacks direction | Always add for Level 2+ |
| Inconsistent variable names | Confusion | SCREAMING_SNAKE_CASE |
| Missing STOP conditions | Runaway execution | Explicit early exits |
| Over-detailed workflow | Reduces agent autonomy | High-level steps |
| No frontmatter | Hard to discover | Add description |
"Build libraries of reusable battle-tested agentic prompts with composable sections that work like LEGO blocks."
Date: 2025-12-26 Model: claude-opus-4-5-20251101