k-create-skill
Meta knowledge for creating Claude skills. Provides templates, best practices, and patterns for building effective skills with routing tables and reference files. Load this when creating new skills or understanding the skill system. Triggers: create skill, new skill, skill template, skill architecture, SKILL.md.
When & Why to Use This Skill
This Claude skill serves as a comprehensive meta-framework designed for developers and AI architects to standardize the creation, organization, and optimization of Claude-based agentic skills. By providing structured templates, a specialized three-prefix taxonomy (Commands, Skills, Knowledge), and advanced routing patterns, it ensures that new capabilities are built with high modularity and efficient context management.
Use Cases
- Standardizing AI agent development by implementing the c-/s-/k- taxonomy to distinguish between explicit workflows, how-to knowledge, and background context.
- Optimizing token usage and response latency through 'Progressive Loading' strategies, ensuring the agent only loads deep reference material when explicitly relevant.
- Designing complex routing tables that guide Claude to the correct internal documentation or reference files based on specific user request types.
- Establishing a scalable architecture for organizational knowledge bases, allowing for self-contained and easily maintainable skill modules.
| name | k-create-skill |
|---|---|
| description | > |
| Triggers | create skill, new skill, skill template, skill architecture, SKILL.md. |
Creating Claude Skills
Knowledge for creating and maintaining Claude commands and skills.
Mechanic Skill System
This project uses a three-prefix taxonomy:
| Prefix | Type | Purpose |
|---|---|---|
c- |
Commands | Action workflows with explicit steps |
s- |
Skills | How-to knowledge (paired with commands) |
k- |
Knowledge | Context/background (no command needed) |
See ../../AGENTS.md for full system documentation.
Creating a New Action
To add a new action (e.g., "deploy"):
- Create
commands/c-deploy.mdwith explicit steps - Create
skills/s-deploy/SKILL.mdwith detailed guidance - Add bidirectional links between them
Creating New Knowledge
To add new context (e.g., "blizzard-api"):
- Create
skills/k-blizzard-api/SKILL.md - No command needed - the skill IS the context loader
Skill Structure
skills/[skill-name]/
├── SKILL.md # Required: Main skill file
└── references/ # Optional: Supporting documents
├── topic1.md
└── topic2.md
SKILL.md Format
---
name: [prefix]-[name]
description: >
[What this skill does]. [What content it covers].
Use when [scenarios]. Triggers: [keyword1], [keyword2], [keyword3].
---
# [Title]
[One-line description]
## Related Commands (for s-* skills only)
- [c-X](../../commands/c-X.md) - [description]
## Capabilities / Key Concepts
1. **[Item 1]** — [Brief description]
2. **[Item 2]** — [Brief description]
## Routing Logic (optional)
| Request type | Load reference |
|--------------|----------------|
| [Topic] | [references/file.md](references/file.md) |
Core Principles
1. Progressive Loading
Skills load in stages:
- Stage 1: Name + description (always loaded)
- Stage 2: SKILL.md body (when skill is relevant)
- Stage 3: References (only when explicitly needed)
Design for minimal initial context, deep references.
2. Clear Triggers
Description should include trigger words that help Claude know when to use this skill.
3. Self-Contained References
Each reference file should be independently useful without requiring other files.
4. Actionable Content
Focus on rules, patterns, and examples—not background explanation.
Routing Logic
| Request type | Load reference |
|---|---|
| Skill file format | references/format.md |
| Routing tables | references/routing.md |
| Description writing | references/descriptions.md |
| Reference file design | references/reference-files.md |
| Skill architecture | references/architecture.md |