SkillFoxx

skill-creator

A skill that helps an agent author other skills to the agentskills.io spec: structure, metadata, progressive disclosure and validation

  • 2,295 ★ on the repository
  • Last commit
Skill

Minimal access

Why this level

  • The skill consists of instructions, a template and a small metadata validation script
All reasons and checks

mgechev/skills-best-practicesAuthor:Minko Gechev

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/skill-creator

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skill consists of instructions, a template and a small metadata validation script

This is third-party code. Review the repository files before installing.

What it does

The skill guides an agent through building a new skill to the agentskills.io spec. It sets up the folder structure with a SKILL.md and scripts, references and assets directories, helps write a name and description with positive and negative triggers, and validates metadata with the validate-metadata.py script. Its instructions require keeping SKILL.md lean, moving bulky context into references with just-in-time loading, and writing steps in the third-person imperative. It ships a SKILL.md template, a review checklist and a validation script. The repository also includes a README guide with techniques and prompts for validating skills through a separate LLM.

Who it is for. For developers and technical writers who build and maintain their own agent skills.

Good fit when

  • You need to create a new skill with the right structure and metadata
  • You need to check a skill's name and description for trigger fitness
  • You need to tidy a bulky SKILL.md through progressive disclosure

Not a fit when

  • You need ordinary documentation or library code, not an agent skill
  • The skill is already done and needs no rework

Example request

Help me build a skill for migrating a project to a new bundler following the agentskills.io spec

Limitations

The skill provides methodology and metadata validation but does not write your skill's domain logic for you. The validation script needs Python 3. The repository has no license file, so reuse terms should be clarified with the author. Most of the repository is a human-facing guide; only skill-creator itself is meant for the skills directory.

How to disable. Remove the skill-creator folder from the agent's skills directory, for example ~/.claude/skills/.

FAQ

Is this a guide or an installable skill?

Both. The README is a techniques guide, and the skill folder holds the installable skill-creator with a template, a checklist and a metadata validation script.

How is metadata validated?

The skill runs scripts/validate-metadata.py, which checks the name and description against the spec rules and reports errors in its output.

Discussion

No questions or reviews yet.

Skills

A skill that designs, tests, evaluates and packages other agent skills, starting from architecture

SkillExtended access212

A skill for creating skills that proves them by behavior: before-and-after runs, regression evals and ecosystem audit

SkillExtended access918

A meta-skill that turns a workflow into an agent skill: prior-art search, trigger evaluation and publication to GitHub

SkillBroad access391

A meta-skill that takes a vague idea to a finished agent skill: it designs, writes the files, checks them and refines by evidence

SkillExtended access250

A skill that creates and reviews other skills, weighing usefulness, trigger boundaries, setup and stability before release.

SkillMinimal access102

skill-creator-plus audits skills against 46 Anthropic rules, then builds and refines them for the newer Claude models.

SkillExtended access82

README in short

The repository collects techniques for building agent skills: folder structure, optimizing the name and description for triggers, progressive disclosure of context, imperative step-by-step instructions, moving repetitive operations into scripts and composing skills. A dedicated section covers validating skills through a separate LLM: trigger, logic and edge-case validation and architecture refinement. Alongside the guide the repository holds an installable skill-creator with a SKILL.md template, a checklist and a metadata validation script. The author points to a separate project, skillgrade, for scoring skills.

README badge

Original SKILL.md

---
name: skill-creator
description: Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.
---

# Skill Authoring Procedure

Follow these steps to generate a skill that adheres to the agentskills.io specification and progressive disclosure principles.

## Step 1: Initialize and Validate Metadata
1.  Define a unique `name`: 1-64 characters, lowercase, numbers, and single hyphens only. **This must exactly match the parent directory name** (e.g., name `angular-testing` must live in `angular-testing/SKILL.md`).
2.  Draft a `description`: Max 1,024 characters, written in the third person. Include positive triggers ("Use when...") and negative triggers ("Don't use for...").
3.  **Execute Validation Script:** Run the validation script to ensure compliance before proceeding:
    `python3 scripts/validate-metadata.py --name "[name]" --description "[description]"`
4.  If the script returns an error, self-correct the metadata based on the `stderr` output and re-run until successful.

Report a problem