template-engineering
Guide creation of meta-prompt templates that encode engineering workflows into reusable, scalable units. Use when creating slash commands that generate plans, designing workflow templates, or encoding team best practices into agentic prompts.
What this skill does
# Template Engineering
Guide for creating meta-prompt templates - prompts that build prompts.
## When to Use
- Creating new slash commands that generate plans
- Encoding team workflows into reusable templates
- Designing meta-prompts for chores, bugs, features
- Analyzing existing templates for improvement
## Template Anatomy
Every effective template has five sections:
### 1. Purpose Section
Clear description at the top:
```markdown
# [Work Type] Planning
Create a new plan in specs/*.md to resolve the [Work Type] using
the exact specified markdown Plan Format.
```
### 2. Instructions Section
Guidance for the agent:
```markdown
## Instructions
- You are writing a plan, not implementing
- Use your reasoning model: THINK HARD about the plan
- Focus on files in the Relevant Files section
- Include validation commands that verify completion
- Fill in every section of the Plan Format
```
### 3. Relevant Files Section
Guide context loading:
```markdown
## Relevant Files
Focus on the following files:
- README.md (project context)
- src/** (source code)
- tests/** (test patterns)
- docs/** (documentation)
```
### 4. Plan Format Section
Template with placeholders:
```markdown
## Plan Format
# [WorkType]: <name>
## Description
<what needs to be done>
## Relevant Files
<files to modify>
## Step by Step Tasks
<numbered actionable tasks>
## Validation Commands
<commands proving completion>
## Notes
<edge cases and considerations>
```
### 5. Parameter Section
Accept user input:
```markdown
## [WorkType]
$ARGUMENTS
```
## Design Workflow
### Step 1: Identify the Work Type
What class of problems does this template solve?
- Chores: Maintenance, updates, cleanup
- Bugs: Investigation and fixes
- Features: New functionality
- Refactors: Code improvement
### Step 2: Define the Plan Structure
What sections does this work type need?
| Work Type | Essential Sections |
| --- | --- |
| Chore | Description, Files, Tasks, Validation |
| Bug | Problem, Solution, Reproduce, Root Cause, Tasks, Validation |
| Feature | User Story, Implementation Plan, Testing, Acceptance |
| Refactor | Before/After, Migration, Rollback |
### Step 3: Write Instructions
Guide the agent's reasoning:
- What should they focus on?
- What reasoning depth is needed? ("think hard")
- What common mistakes should they avoid?
- What format requirements are strict?
### Step 4: Specify Relevant Files
Limit scope to improve quality:
- Core files for this work type
- Test files to understand patterns
- Config files if relevant
- Avoid overly broad patterns
### Step 5: Test with Examples
Validate your template:
1. Run with simple input
2. Check generated plan completeness
3. Try edge cases
4. Refine based on results
## Quality Checklist
Before deploying a template:
- [ ] Purpose clearly states what template does
- [ ] Instructions include "THINK HARD" for reasoning
- [ ] Relevant Files are specific, not too broad
- [ ] Plan Format has all necessary sections
- [ ] Validation Commands section is mandatory
- [ ] Parameter uses `$ARGUMENTS` correctly
- [ ] Output location specified (specs/*.md)
## Common Patterns
### Reasoning Activation
```markdown
Use your reasoning model: THINK HARD about the plan
and the steps to accomplish this work.
```
### File Output Pattern
```markdown
Create a new plan in specs/*.md using the following naming:
specs/[worktype]-[descriptive-name].md
```
### Validation Mandate
```markdown
The Validation Commands section is REQUIRED. Every plan must
include commands that prove the work is complete.
```
## Anti-Patterns to Avoid
### Too Broad Relevant Files
**Bad**: `**/*` (everything)
**Good**: `src/auth/**, tests/auth/**` (focused)
### Missing Validation Section
**Bad**: No way to verify completion
**Good**: Specific test and lint commands
### Vague Instructions
**Bad**: "Make a good plan"
**Good**: "Focus on error handling edge cases, include rollback steps"
### No Output Location
**Bad**: Plan written somewhere undefined
**Good**: `specs/[worktype]-[name].md` pattern
## Related Memory Files
- @template-engineering.md - Core concepts and examples
- @meta-prompt-patterns.md - Prompt hierarchy
- @plan-format-guide.md - Standard plan structures
## Version History
- **v1.0.0** (2025-12-26): Initial release
---
## Last Updated
**Date:** 2025-12-26
**Model:** claude-opus-4-5-20251101
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.