Automated summary
Scaffolds a new skill (SKILL.md, README, plugin, and marketplace entry) inside the agent-skills repository, then validates the result.
Strengths
- Enforces kebab-case naming and aborts if a skill with that name already exists
- Produces SKILL.md, README.md, the plugin directory, marketplace.json, and the root README table row in a single run
- Asks two targeted questions (category, description) via AskUserQuestion to fill in the frontmatter
- Finishes by running scripts/validate.py and printing the remaining manual next steps
Limitations
- Tightly coupled to the 2ykwang/agent-skills repo: it relies on scripts/generate_plugins.py, scripts/validate.py, and the existing skills/ layout
- Output content is intentionally TODO placeholders; actually writing the skill instructions is not automated
- The offered category list (development, design-frontend, productivity, integrations, media) is repo-specific and does not match common taxonomies
Use it when adding a new skill to the agent-skills repository and you want a consistent skeleton, a generated plugin, and synced README entries.
Avoid it outside that specific repository, or when the task is writing and refining a skill's actual content rather than generating boilerplate.
Security analysis
CautionThe skill is a scaffolding utility: it validates a name, creates a directory with two files, asks the user for metadata, runs two in-repo Python scripts, and appends a row to the README. Nothing is destructive, obfuscated, or exfiltrating; the kebab-case regex blocks path-traversal tricks. It is 'caution' only because it exercises file-write and code-execution capabilities that are undeclared in allowed-tools and depends on the safety of scripts it invokes.
- •No allowed-tools declared, yet the workflow instructs file creation/editing and execution of repo scripts (`python3 scripts/generate_plugins.py`, `python3 scripts/validate.py`)
- •Step 6/8 run local Python scripts whose behavior is not described here; the agent must trust them without inspecting them
- •Step 7 edits the repository root README table by loosely described text matching ('between the two --- separators'), which could corrupt the file if the structure differs
- •Input is constrained to kebab-case (^[a-z0-9]+(-[a-z0-9]+)*$), which usefully prevents path traversal in `skills/$ARGUMENTS/`
Examples
/add-skill pdf-table-extractor/add-skill PDF_Table_Extractor/add-skill code-reviewdescription: Scaffold a new skill with validation, plugin generation, and README update. argument-hint: "<skill-name>"
Add Skill
Scaffold a new skill named $ARGUMENTS.
Workflow
1. Validate Input
- Check
$ARGUMENTSis kebab-case (^[a-z0-9]+(-[a-z0-9]+)*$). Stop with error if not. - Check
skills/$ARGUMENTS/does not already exist. Stop with error if it does.
2. Create Directory Structure
skills/<name>/
├── SKILL.md
└── README.md
3. Write SKILL.md
---
name: <name>
version: 0.0.1
category: TODO
description: "TODO — one sentence describing what this skill does and when to trigger it."
argument-hint: "<argument>"
---
## Instructions
TODO
4. Ask User
Use AskUserQuestion:
- Category — one of:
development,design-frontend,productivity,integrations,media - Description — one sentence for the skill description
Update SKILL.md frontmatter with the user's answers.
5. Write README.md
Create skills/<name>/README.md with this structure:
# <name>
<description from step 4>
## When to use
- TODO
## Usage
/skill-name <example>
## Installation
### Claude Code
```bash
claude plugin marketplace add 2ykwang/agent-skills
claude plugin install <name>@2ykwang-agent-skills
npx skills
npx skills add 2ykwang/agent-skills --skill <name>
### 6. Generate Plugins
Run `python3 scripts/generate_plugins.py`. This generates:
- `plugins/<name>/` directory with plugin.json, README.md, and copied skills
- Updated `.claude-plugin/marketplace.json`
### 7. Update README.md Skills Table
Find the table between the two `---` separators. Append 3-row block before the closing `---`:
```markdown
| [<name>](skills/<name>) | <description> |
| | `npx skills add 2ykwang/agent-skills --skill <name>` |
| | `claude plugin install <name>@2ykwang-agent-skills` |
8. Validate and Report
Run python3 scripts/validate.py. Show output.
Print summary:
Created skills/<name>/
Next steps:
1. Edit skills/<name>/SKILL.md — replace TODOs
2. Edit skills/<name>/README.md — add "When to use" and "Usage" examples
3. just generate && just validate
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/add-skill-ms47vqoi/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/add-skill-ms47vqoi' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/add-skill-ms47vqoi/download' --output '.skill-downloads/add-skill-ms47vqoi/SKILL.md.part' && mv '.skill-downloads/add-skill-ms47vqoi/SKILL.md.part' '.skill-downloads/add-skill-ms47vqoi/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/add-skill-ms47vqoi/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.