How do I install the Orthogonal Skill Creator skill?

Run npx skillmds add majiayu000/orthogonal-skill-creator in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Orthogonal Skill Creator safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Orthogonal Skill Creator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Orthogonal Skill Creator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Orthogonal Skill Creator?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Orthogonal Skill Creator by majiayu000

Name: Orthogonal Skill Creator
Rating: 4.2 (5 reviews)
Author: majiayu000

Orthogonal Skill Creator

Create, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build skills with scripts, references, and assets. Triggers on requests to create skills, write SKILL.md files, or structure skill directories.

majiayu000 56c3fc0 2 files · 4.5 KB Updated Sep 9, 2026 567 repo stars

File contents

Skill Creator

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Create modular, self-contained skill packages that extend agent capabilities.

Core Principle: Concise is Key

The context window is shared. Only add what the agent doesn't already know. Challenge every paragraph: "Does this justify its token cost?" Prefer concise examples over verbose explanations.

Skill Structure

skill-name/
├── SKILL.md              # Required: frontmatter + instructions
├── scripts/              # Optional: executable code (deterministic tasks)
├── references/           # Optional: docs loaded on-demand
└── assets/               # Optional: files used in output (templates, images)

SKILL.md Format

---
name: skill-name
description: What it does + when to use it. This is the trigger mechanism.
---

# Skill Name

[Instructions for using the skill]

Frontmatter Rules

name: lowercase, hyphens, under 64 chars (e.g., pdf-editor, gh-review-pr)
description: Include BOTH what it does AND when to trigger. The body isn't loaded until after triggering, so all "when to use" info must be here.

Degrees of Freedom

Match specificity to task fragility:

Freedom	Use When	Format
High	Multiple valid approaches	Text instructions
Medium	Preferred pattern exists	Pseudocode, parameterized scripts
Low	Fragile/error-prone ops	Specific scripts, few params

Creation Process

Understand - Gather concrete usage examples
Plan - Identify reusable scripts, references, assets
Initialize - Run orth skills init <name>
Implement - Write SKILL.md, add resources
Submit - Run orth skills submit <path>
Iterate - Test on real tasks, refine

Quick Start

# Create new skill
orth skills init my-skill

# Or with path
orth skills init my-skill --path ~/.openclaw/skills

# Submit to Orthogonal
orth skills submit ./my-skill

# Update existing skill
orth skills update <slug> ./my-skill

What NOT to Include

README.md, CHANGELOG.md, INSTALLATION_GUIDE.md
Setup/testing procedures
User-facing documentation
Anything not needed for the agent to do the job

Progressive Disclosure

Keep SKILL.md under 500 lines. Split into reference files when approaching this limit.

Pattern: High-level guide with references

## Quick start
[Core workflow here]

## Advanced
- **Complex feature**: See references/feature.md
- **API details**: See references/api.md

Pattern: Domain organization

bigquery-skill/
├── SKILL.md (overview + navigation)
└── references/
    ├── finance.md
    ├── sales.md
    └── product.md

Agent loads only the relevant reference file.

---name: orthogonal-skill-creatordescription: Create, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build skills with scripts, references, and assets. Triggers on requests to create skills, write SKILL.md files, or structure skill directories.--- # Skill Creator ## Setup Read your credentials from ~/.gooseworks/credentials.json: ```bash export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))") ``` If ~/.gooseworks/credentials.json does not exist, tell the user to run: `npx gooseworks login` All endpoints use Bearer auth: `-H "Authorization: Bearer $GOOSEWORKS_API_KEY"` Create modular, self-contained skill packages that extend agent capabilities. ## Core Principle: Concise is Key The context window is shared. Only add what the agent doesn't already know. Challenge every paragraph: "Does this justify its token cost?" Prefer concise examples over verbose explanations. ## Skill Structure ``` skill-name/ ├── SKILL.md # Required: frontmatter + instructions ├── scripts/ # Optional: executable code (deterministic tasks) ├── references/ # Optional: docs loaded on-demand └── assets/ # Optional: files used in output (templates, images) ``` ## SKILL.md Format ```markdown --- name: skill-name description: What it does + when to use it. This is the trigger mechanism. --- # Skill Name [Instructions for using the skill] ``` ### Frontmatter Rules - `name`: lowercase, hyphens, under 64 chars (e.g., `pdf-editor`, `gh-review-pr`) - `description`: Include BOTH what it does AND when to trigger. The body isn't loaded until after triggering, so all "when to use" info must be here. ## Degrees of Freedom Match specificity to task fragility: | Freedom | Use When | Format | |---------|----------|--------| | High | Multiple valid approaches | Text instructions | | Medium | Preferred pattern exists | Pseudocode, parameterized scripts | | Low | Fragile/error-prone ops | Specific scripts, few params | ## Creation Process 1. **Understand** - Gather concrete usage examples 2. **Plan** - Identify reusable scripts, references, assets 3. **Initialize** - Run `orth skills init <name>` 4. **Implement** - Write SKILL.md, add resources 5. **Submit** - Run `orth skills submit <path>` 6. **Iterate** - Test on real tasks, refine ### Quick Start ```bash # Create new skill orth skills init my-skill # Or with path orth skills init my-skill --path ~/.openclaw/skills # Submit to Orthogonal orth skills submit ./my-skill # Update existing skill orth skills update <slug> ./my-skill ``` ## What NOT to Include - README.md, CHANGELOG.md, INSTALLATION_GUIDE.md - Setup/testing procedures - User-facing documentation - Anything not needed for the agent to do the job ## Progressive Disclosure Keep SKILL.md under 500 lines. Split into reference files when approaching this limit. **Pattern: High-level guide with references** ```markdown ## Quick start [Core workflow here] ## Advanced - **Complex feature**: See references/feature.md - **API details**: See references/api.md ``` **Pattern: Domain organization** ``` bigquery-skill/ ├── SKILL.md (overview + navigation) └── references/ ├── finance.md ├── sales.md └── product.md ``` Agent loads only the relevant reference file.

Frequently asked questions