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.
Sign in to like and favorite skills
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/ ├── SKILL.md (required) │ ├── YAML frontmatter metadata (required) │ │ ├── name: (required) │ │ └── description: (required) │ └── Markdown instructions (required) └── Bundled Resources (optional) ├── scripts/ - Executable code (Python/Bash/etc.) ├── references/ - Documentation intended to be loaded into context as needed └── assets/ - Files used in output (templates, icons, fonts, etc.)
Metadata Quality: The
namedescriptionscripts/Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
scripts/rotate_pdf.pyreferences/Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
references/finance.mdreferences/mnda.mdreferences/policies.mdreferences/api_docs.mdassets/Files not intended to be loaded into context, but rather used within the output Claude produces.
assets/logo.pngassets/slides.pptxassets/frontend-template/assets/font.ttfSkills use a three-level loading system to manage context efficiently:
*Unlimited because scripts can be executed without reading into context window.
Before running any skill scripts, verify that the required tools are available:
Check if Python 3 is installed:
python3 --version
If not available, install it:
brew install python3sudo apt-get install python3winget install Python.Python.3Check if packmind-cli is installed:
packmind-cli --version
If not available, install it:
npm install -g packmind-cli
To create a skill, follow the "Skill Creation Process" in order, skipping steps only if there is a clear reason why they are not applicable.
Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
For example, when building an image-editor skill, relevant questions include:
To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
Conclude this step when there is a clear sense of the functionality the skill should support.
To turn concrete examples into an effective skill, analyze each example by:
Example: When building a
pdf-editorscripts/rotate_pdf.pyExample: When designing a
frontend-webapp-builderassets/hello-world/Example: When building a
big-queryreferences/schema.mdTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
Before running the script, verify that python3 and packmind-cli are available (see Prerequisites section). If not installed, install them first.
When creating a new skill from scratch, always run the
init_skill.pyUsage:
python3 scripts/init_skill.py <skill-name> --path <output-directory>
The script:
scripts/references/assets/After initialization, customize or remove the generated SKILL.md and example files as needed.
When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Focus on including information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
To begin implementation, start with the reusable resources identified above:
scripts/references/assets/brand-guidelinesassets/references/Also, delete any example files and directories not needed for the skill. The initialization script creates example files in
scripts/references/assets/Writing Style: Write the entire skill using imperative/infinitive form (verb-first instructions), not second person. Use objective, instructional language (e.g., "To accomplish X, do Y" rather than "You should do X" or "If you need to do X"). This maintains consistency and clarity for AI consumption.
To complete SKILL.md, answer the following questions:
Before distributing, validate the skill to ensure it meets all requirements.
Before running the script, verify that python3 is available (see Prerequisites section). If not installed, install it first.
python3 scripts/quick_validate.py <path/to/skill-folder>
The validation script checks:
If validation fails, fix the reported errors and run the validation again.
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
Iteration workflow:
After successful validation, always run the distribution command to register the skill with Packmind. Do not skip this step.
Before running the command, verify that packmind-cli is available (see Prerequisites section). If not installed, install it first.
Run the following command with the actual skill path:
packmind-cli skills add <path/to/skill-folder> --origin-skill=create-skill
This registers the skill with Packmind, making it available for deployment to target repositories and AI coding agents.
After successful distribution, check if the skill fits an existing package:
packmind-cli install --list<package-slug><package-slug>packmind-cli packages add --to <package-slug> --skill <skill-slug> --origin-skill=create-skillpackmind-cli installpackmind-cli install