All skills
brianlovin avatar

/skill-creator

@24ef25a official

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use this Skill: https://skilld.dev/gh/brianlovin/claude-config/skill-creator

This session only. Nothing lands on disk.

referencesoutput-patterns.md

≈454 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Output Patterns

Use these patterns when skills need to produce consistent, high-quality output.

Template Pattern

Provide templates for output format. Match the level of strictness to your needs.

For strict requirements (like API responses or data formats):

## Report structure

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary
[One-paragraph overview of key findings]

## Key findings
- Finding 1 with supporting data
- Finding 2 with supporting data
- Finding 3 with supporting data

## Recommendations
1. Specific actionable recommendation
2. Specific actionable recommendation

For flexible guidance (when adaptation is useful):

## Report structure

Here is a sensible default format, but use your best judgment:

# [Analysis Title]

## Executive summary
[Overview]

## Key findings
[Adapt sections based on what you discover]

## Recommendations
[Tailor to the specific context]

Adjust sections as needed for the specific analysis type.

Examples Pattern

For skills where output quality depends on seeing examples, provide input/output pairs:

## Commit message format

Generate commit messages following these examples:

**Example 1:**
Input: Added user authentication with JWT tokens
Output:

feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware


**Example 2:**
Input: Fixed bug where dates displayed incorrectly in reports
Output:

fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation


Follow this style: type(scope): brief description, then detailed explanation.

Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.

Source: SKILL.md on GitHub

1 warning16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a development toolkit for creating, initializing, and packaging new agent skills. It contains documentation on best practices and utility scripts that perform local file operations. The skill does not communicate with external servers or access sensitive credentials.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    5/7 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 24ef25a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 8 months ago
  • Documentation
  • skill-creation
  • guidelines
  • workflows
  • knowledge-management
  • context-window
  • ai-agents
  • modular-design

README badge

README badge for brianlovin/claude-config/skill-creator

This skill teaches how to create effective skills—modular instruction packages that extend Claude's capabilities with specialized workflows, tool integrations, and domain knowledge. It covers skill anatomy (SKILL.md frontmatter and body, bundled scripts/references/assets), design principles like progressive disclosure and appropriate degrees of freedom, and a five-step creation process grounded in concrete examples and reusable content planning.

Generated from the current SKILL.md.

What is a skill, and how does it differ from a plugin or package?
A skill is a modular instruction file (SKILL.md) with optional bundled scripts, references, and assets that extends Claude's capabilities with specialized knowledge and workflows. It is not a package, plugin, or extension—it's loaded on-demand by an AI coding agent to provide domain expertise, tool integrations, or procedural guidance.
What should I include in a skill, and what should I leave out?
Include only SKILL.md (required), bundled scripts for deterministic tasks, reference files for documentation, and assets for templates or boilerplate. Do not include README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, or other auxiliary documentation—the skill should contain only information needed for the agent to do the job.
How long should my SKILL.md be, and when should I split content into separate files?
Keep SKILL.md under 500 lines and under 5k words to minimize context bloat. When approaching this limit or supporting multiple variants/frameworks, move detailed content into separate reference files and link to them from SKILL.md, using progressive disclosure to load files only when needed.
When should I include a script versus instructions in SKILL.md?
Include a script when the same code is rewritten repeatedly, deterministic reliability is critical, or a specific sequence must be followed. Use text-based instructions when multiple approaches are valid or decisions depend on context.

Generated from the current SKILL.md. These answers refresh after source changes.