Manage Reusable Parameterized Skills

VerifiedSafe

Allows users to list, show, validate, and render reusable parameterized prompts (skills) defined in SKILL.md files. Helps organize common coding tasks like code reviews or bug detection by providing a structured way to run targeted prompts with arguments.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#skill-management#cli#prompt-templates#code-review

Recommended for

Automated summary

Manages reusable, parameterized prompts (skills) for AI coding agents via a CLI tool.

Strengths

  • Supports listing, showing details, validating, and rendering skills
  • Skills use YAML frontmatter for structured metadata
  • Integrates with scheduled tasks for automated skill execution
  • Allows global and project-specific skill storage

Limitations

  • Limited to skills conforming to the specific SKILL.md format
  • No built-in skill marketplace or sharing mechanism beyond file system
  • Requires manual file management for skill discovery
When to use it

When you need to standardize and reuse complex prompts across multiple AI agent tasks or projects.

When not to use it

If you only need one-off prompts or prefer to write prompts directly without a formal system.

Security analysis

Safe
Quality score92/100

The SKILL.md is purely documentation describing a skill management CLI. It contains no executable code or dangerous instructions; it only explains command usage and format.

No concerns found

How this analysis is made

Examples

List all skills
List all available skills using the skill manager.
Show skill details
Show the details of the 'review' skill.
Render a skill with arguments
Render the 'review' skill with arguments 'Check authentication code'.

skill

Manage skills - reusable, parameterized prompts.

Usage

codegeass skill [OPTIONS] COMMAND [ARGS]...

Commands

::: mkdocs-click :module: codegeass.cli.commands.skill :command: skill :prog_name: codegeass skill :depth: 1

Examples

List Skills

# List all available skills
codegeass skill list

# List with details
codegeass skill list --verbose

Show Skill Details

codegeass skill show review

Validate a Skill

# Validate SKILL.md format
codegeass skill validate .claude/skills/review/SKILL.md

# Validate all skills
codegeass skill validate --all

Render a Skill

Preview the rendered prompt with arguments:

codegeass skill render review "Check authentication code"

Skill Format

Skills use YAML frontmatter in SKILL.md files:

---
name: review
description: Review code for issues
context: fork
agent: Explore
allowed-tools: Read, Grep, Glob
---

# Code Review

$ARGUMENTS

Focus on:
- Code quality
- Potential bugs
- Security issues

Frontmatter Fields

| Field | Required | Description | |-------|----------|-------------| | name | Yes | Skill identifier | | description | Yes | What the skill does | | context | No | Execution context | | agent | No | Agent type | | allowed-tools | No | Permitted tools |

Skill Locations

Skills are searched in:

  1. .claude/skills/ in the current project
  2. ~/.claude/skills/ for global skills

Using Skills with Tasks

# Create a task that uses a skill
codegeass task create \
  --name review-task \
  --schedule "0 9 * * *" \
  --mode skill \
  --skill review \
  --skill-args "Review the API module"

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 files

This 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.md

From the root of a test project, save the file as .skill-downloads/manage-reusable-parameterized-skills-mma3jrk4/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/manage-reusable-parameterized-skills-mma3jrk4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/manage-reusable-parameterized-skills-mma3jrk4/download' --output '.skill-downloads/manage-reusable-parameterized-skills-mma3jrk4/SKILL.md.part' && mv '.skill-downloads/manage-reusable-parameterized-skills-mma3jrk4/SKILL.md.part' '.skill-downloads/manage-reusable-parameterized-skills-mma3jrk4/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/manage-reusable-parameterized-skills-mma3jrk4/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.

Related skills