Skill Creator
Standards for creating new High-Density Agent Skills with optimal token economy.
Skill by fierzone
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fierzone-skill-creator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/skill-creator
What's inside
- Skill name
Skill Creator- Description
- Standards for creating new High-Density Agent Skills with optimal token economy.
- License
- Apache-2.0
- Instructions
- 219 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Skill Creator" does not match folder "skill-creator"
Files (4)
- SKILL.md
- TEMPLATE.md · references/
- lifecycle.md · references/
- resource-organization.md · references/
SKILL.md (first lines)
# Agent Skill Creator Standard
## **Priority: P0 (CRITICAL)**
Strict guidelines for authoring High-Density Agent Skills. Maximize information density while minimizing token consumption through progressive disclosure and strategic content organization.
## Core Principles
### **Token Economy First** ⚡
Every word costs tokens. Design skills for maximum information/token ratio:
- **Progressive Loading**: Load only essential content initially
- **Lazy References**: Move detailed examples to `references/` folder
- **Imperative Compression**: Use verbs, abbreviations, bullet points
- **Context Window Awareness**: Design for 4k-32k token limits across agents
### **Three-Level Loading System**
```ts
Level 1: Metadata (Triggers) → AGENTS.md index (Proactive Activation)
Level 2: SKILL.md Body (70 lines) → Core guidelines (When triggered)
Level 3: References/Scripts/Assets → Deep knowledge (On-demand only)
```
## Directory Structure
```text
skills/
└── {category}/ # e.g., "flutter" (lowercase)
└── {skill-name}/ # e.g., "bloc-state-management" (kebab-case)
├── SKILL.md # Core Logic (High Density, <500 lines)
├── scripts/ # Executable code (Deterministic tasks)
│ └── automation.py
├── references/ # Heavy Examples (Lazy loaded)
│ ├── patterns.md
│ └── examples.md
└── assets/ # Output templates (Never loaded)
└── template.json
```
## Writing Rules (Token-Optimized)
1. **Imperative Compression**: Start with verbs. No "Please/You should".
- _Waste_: "You should use BLoC for state management." (8 words)
- _Efficient_: "Use BLoC for state management." (5 words)
2. **Token Economy**: Maximize info/token ratio.
- Skip articles ("the", "a") if readable
- Use standard abbreviations (cfg, param, impl)
- Bullet points > paragraphs (3x density)
3. **Progressive Disclosure**: Essential info first, details on-demand.
- Core workflow in SKILL.md
- Complex examples in references/
- Templates/assets never loaded
4. **Context-Aware Design**: Different agents have different limits.
- Cursor: ~100k tokens
- Claude: ~200k tokens
- Windsurf: ~32k tokens
## Content Sections (Token-Budgeted)
Required sections in `SKILL.md`:
1. **Frontmatter (Mandatory)**: Metadata for proactive activation.
```yaml
---
name: Skill Name
description: 1-sentence purpose
metadata:
labels: [tag1, tag2]
triggers:
# Patterns that suggest context for this skill
files: ['**/*.ext', 'characteristic-file.json']
# Keywords that indicate work in this area
keywords: [term1, term2]
---
```
2. **Priority**: P0 (Critical), P1 (Standard), or P2 (Optional)
3. **Structure**: ASCII tree of expected file layout
4. **Guidelines**: Bullet points of "Do this" (imperative)
5. **Anti-Patterns**: Bullet points of "Don't do this"
6. **Reference Links**: Links to `references/` files (lazy loading)
## Size Limits (Strict)
| Element | Limit | Action if Exceeded |
| -------------------------- | -------- | ------------------------ |
| SKILL.md total | 70 lines | Extract to references/ |
| Inline code block | 10 lines | Move to references/ |
| Anti-pattern item | 15 words | Compress to imperative |
| Description after Priority | 0 lines | Remove (use frontmatter) |
| Tables | 8 rows | Extract to references/ |
| Explanatory sections | 10 lines | Extract to references/ |
## Resource Organization (Token-Saving)
### **scripts/** - Executable Code
**When to use**: Deterministic, repeated tasks
**Benefits**: Never loaded into context, executed directly
**Examples**: Code generators, formatters, validators
### **references/** - Documentation
**When to use**: Detailed examples, API docs, complex patterns
**Benefits**: Loaded only when needed, keeps SKILL.md lean
**Examples**: Implementation patterns, error handling guides
### **assets/** - Output Templates
**When to use**: Boilerplate files, images, configs
**Benefits**: Never loaded, copied to output as-needed
**Examples**: Project templates, config files, iconsFrom fierzone/agent-skills-standard, Apache-2.0.
More from fierzone/agent-skills-standard
- 0.448score
tdd
fierzone
Enforces Test-Driven Development (Red-Green-Refactor) for rigorous code quality.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
Mobile Animation
fierzone
Motion design principles for mobile apps.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Debugging Expert
fierzone
Systematic troubleshooting using the Scientific Method (Observe, Hypothesize, Experiment, Fix).
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
AI Feedback Reporter
fierzone
CRITICAL - Before ANY file write, audit loaded skills for violations.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Git & Collaboration Standards
fierzone
Universal standards for version control, branching, and team collaboration.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
TypeScript Language Patterns
fierzone
Modern TypeScript standards for type safety, performance, and maintainability.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Code Review Expert
fierzone
Standards for performing high-quality, readable code reviews.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Quality Assurance Standards
fierzone
Standards for maintaining code hygiene, automated checks, and testing integrity.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Security Standards
fierzone
Universal security protocols for building safe and resilient software.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
JavaScript Best Practices
fierzone
Idiomatic JavaScript patterns and conventions for maintainable code.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
JavaScript Language Patterns
fierzone
Modern JavaScript (ES2022+) patterns for clean, maintainable code.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
JavaScript Tooling
fierzone
Development tools, linting, and testing for JavaScript projects.
SkillDFreshness: D★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 4, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fierzone
- 0.448score
tdd
fierzone
Enforces Test-Driven Development (Red-Green-Refactor) for rigorous code quality.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
Mobile Animation
fierzone
Motion design principles for mobile apps.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Debugging Expert
fierzone
Systematic troubleshooting using the Scientific Method (Observe, Hypothesize, Experiment, Fix).
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
AI Feedback Reporter
fierzone
CRITICAL - Before ANY file write, audit loaded skills for violations.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Git & Collaboration Standards
fierzone
Universal standards for version control, branching, and team collaboration.
SkillDFreshness: D★ 3Claude Code +9 - 0.440score
Code Review Expert
fierzone
Standards for performing high-quality, readable code reviews.
SkillDFreshness: D★ 3Claude Code +9
Cite this page
Skill Creator. Agent Mart. https://agentmart.dev/skills/fierzone-skill-creator (last updated 2026-10-24)