Automated summary
Generates a new aiagent skill under .aiagent/skills/<name>/SKILL.md, complete with the required YAML frontmatter and agent-executable instruction content.
Strengths
- Provides the exact frontmatter template (name, description, license, compatibility, allowed-tools, metadata) so the file passes format checks
- States the naming rules up front: lowercase letters, digits and hyphens only, no leading/trailing or doubled hyphens, 64 characters max
- Handles snake_case to hyphen-case conversion and includes a validation pass through skill.Validate() for name format and description length
- Requires the body to be a self-contained instruction set that names the tools to use and the output to produce
Limitations
- Tied to the aiagent runtime and its .aiagent/skills/ layout, so it does not transfer directly to other skill formats
- Validation stops at skill.Validate(); the generated skill is never actually executed as a test
- The generated content is a first draft that still needs human review
Use it when you want to add a new reusable skill to the aiagent repository quickly without getting the file format wrong.
Avoid it for authoring skills for a different ecosystem (Claude Code, Cursor, etc.) or for editing an existing skill, which this procedure does not cover.
Security analysis
SafeThis is a documentation/scaffolding skill that describes how to create a new SKILL.md file under .aiagent/skills/. It performs no network calls, no secret access, no destructive commands, and no obfuscated payloads. The only side effect is creating a directory and a markdown file inside the project, which is benign and expected for a skill-authoring helper. The example frontmatter references bash/file-read but the skill itself declares no allowed-tools and does not instruct any privileged execution.
No concerns found
How this analysis is madeExamples
Create a new aiagent skill named pr-review-checklist that walks an agent through reading a pull request diff, flagging risky changes, and posting structured review comments.Add a skill called changelog_writer that turns the commits merged since the last git tag into a formatted CHANGELOG entry.Create an aiagent skill named deploy-health-check that runs the test suite, checks pending migrations, and reports whether the release is safe to ship.description: Create a new skill for the aiagent project under .aiagent/skills/. A skill is a reusable prompt/instruction set that agents can invoke.
Create a new aiagent skill.
Skill name and purpose: $ARGUMENTS
Skill File Format
Skills are discovered from .aiagent/skills/<name>/SKILL.md. The format requires YAML frontmatter:
---
name: <skill-name>
description: <description up to 1024 chars>
license: MIT
compatibility: aiagent>=1.0
allowed-tools:
- bash
- file-read
metadata:
author: drujensen
---
# Skill content here (the actual instructions/prompt for the agent)
Name Rules
- Lowercase letters, numbers, hyphens only
- Cannot start or end with a hyphen
- No consecutive hyphens
- Max 64 characters
Steps
- Determine the skill name (snake-case to hyphen-case)
- Create directory:
.aiagent/skills/<name>/ - Create
.aiagent/skills/<name>/SKILL.mdwith proper frontmatter - Write clear, actionable skill content that an AI agent can follow
- Verify the skill would pass
skill.Validate()(name format, description length)
The skill content should be a self-contained set of instructions that an agent can execute. Be specific about what tools to use and what output to produce.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/create-aiagent-skill-mrwake87/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/create-aiagent-skill-mrwake87' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-aiagent-skill-mrwake87/download' --output '.skill-downloads/create-aiagent-skill-mrwake87/SKILL.md.part' && mv '.skill-downloads/create-aiagent-skill-mrwake87/SKILL.md.part' '.skill-downloads/create-aiagent-skill-mrwake87/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/create-aiagent-skill-mrwake87/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.