Automated summary
Scaffolds a new skill (slash command) under .claude/commands from the framework templates and registers it in the manifest.
Strengths
- Auto-generates the command file with frontmatter (description, argument-hint) and a ready-to-fill step structure
- Validates the skill name (lowercase, hyphens) and checks for duplicates before creating anything
- Supports domain namespaces (issue, pr, ops, release, tool, etc.) and registers the entry in .claude/.manifest.json with hash and size
- Prints clear next steps: implement the logic, then sync via /tool:skill-sync
Limitations
- Only emits a skeleton — every step's logic is still yours to write
- Assumes a specific framework layout and conventions (.claude/.manifest.json, SKILL_FORMAT.md, /tool:skill-sync) and is not portable as-is
- Mentions the SHA-256 hash and file size for the manifest but does not spell out how to compute them
Use it when you need to add a new slash command quickly while staying compliant with the conventions of a repo built on this framework.
Avoid it outside Claude Code, or in a repo without a .claude/.manifest.json, where hand-writing the skill file is simpler.
Security analysis
SafeThe skill is a pure scaffolding workflow: it prompts for metadata, emits a markdown command file, and appends a manifest entry. It declares no tools, runs no shell commands, performs no network access, and handles no secrets. The only side effect is creating/updating files inside the repo's .claude directory, which is the stated purpose and carries minimal risk.
- •Instructional only: writes new markdown files under .claude/commands/ and edits .claude/.manifest.json (including replacing an existing manifest hash) with no confirmation step, though nothing destructive or exfiltrating is involved.
Examples
/local:create-skill deploy/local:create-skill my-tool --domain tool/local:create-skill deploy --domain releasedescription: Scaffold a new skill using framework templates argument-hint: "<skill-name> [--domain DOMAIN]" global: true
Create Skill
Scaffold a new skill for your consumer repository using framework templates and best practices.
Usage
/local:create-skill <skill-name> # Interactive mode
/local:create-skill deploy --domain release # Create with domain prefix
/local:create-skill my-tool --domain tool # Create tool:my-tool
Steps
1. Validate Skill Name
- Check naming conventions (lowercase, hyphens only)
- Verify domain namespace if provided
- Ensure skill doesn't already exist
2. Gather Skill Details
Prompt for:
- Description: One-line summary (required)
- Domain: Namespace (issue, pr, milestone, audit, ops, repo, local, release, sprint, tool)
- Argument hint: Usage pattern (e.g., "ISSUE_NUMBER [--flag]")
- Permission tier: 1 (read-only), 2 (write), or 3 (destructive)
3. Create Skill File
Generate .claude/commands/{domain}-{name}.md with:
---
description: {description}
argument-hint: "{argument-hint}"
---
# {Title}
{description}
## Usage
/{domain}-{name} {argument-hint}
## Steps
### 1. [Step Name]
Describe what this step does.
## Notes
- Document any important considerations
- List related skills
- Note permission tier if applicable
4. Register in Manifest
Add entry to .claude/.manifest.json:
{
"core/commands/{domain}-{name}.md": {
"target": "commands/{domain}-{name}.md",
"category": "commands",
"hash": "<computed-sha256>",
"size": <file-size>
}
}
5. Display Next Steps
Show:
- File created at:
.claude/commands/{domain}-{name}.md - Invoke with:
/{domain}-{name} - Edit the file to implement logic
- Run
/tool:skill-syncto sync with framework if needed
Notes
- New skills are automatically detected by Claude
- Follow SKILL_FORMAT.md conventions
- Use existing skills as reference templates
- Consider token optimization from the start
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-skill-mrwake3d/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-skill-mrwake3d' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-skill-mrwake3d/download' --output '.skill-downloads/create-skill-mrwake3d/SKILL.md.part' && mv '.skill-downloads/create-skill-mrwake3d/SKILL.md.part' '.skill-downloads/create-skill-mrwake3d/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-skill-mrwake3d/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.