New Skill Project

VerifiedSafe

Initializes a new skill project in the Anthropic Agent Skills format. Quickly creates the project structure for a new skill.

Sby Skills Guide Bot
DevelopmentIntermediate
7/24/2026
Claude Code
#scaffolding#project-initialization#anthropic-agent-skills#kata#ahrena

Recommended for

Automated summary

Initializes a new skill project in the Anthropic Agent Skills format using the Ahrena layout.

Strengths

  • Validates slug and description against the official specification.
  • Generates the full project structure (SKILL.md, widgets, scripts, tools) automatically.
  • Allows opting out of unnecessary components via options (with_widgets, with_tools, with_scripts).
  • Respects paths from .ahrena/.directives for custom skill root locations.

Limitations

  • Requires the Ahrena layout and Anthropic Agent Skills format.
  • Fails if the destination directory already exists (no overwrite).
  • Does not modify the .ahrena/.directives file.
When to use it

When you need to scaffold a new skill project that conforms to the Anthropic Agent Skills specification with the Ahrena structure.

When not to use it

For projects not following the Anthropic Agent Skills format, or when the target slug is already in use.

Security analysis

Safe
Quality score85/100

This skill merely describes a command to initialize a new project scaffolding. It contains no executable code, dangerous shell commands, network calls, or data exfiltration. It delegates to a predefined function (kata-init-skill) and only validates user parameters.

No concerns found

How this analysis is made

Examples

Basic skill creation
/cry-new-skill scheduled-payments-skill description="Schedules bank transfers when the user requests payment for a future date" license=Apache-2.0
Minimal skill without widgets or tools
/cry-new-skill my-skill description="A simple skill for logging" with_widgets=false with_tools=false with_scripts=python
Skill with custom language and human title
/cry-new-skill data-analyzer description="Analyzes datasets using Python tools" language=en human_title="Data Analyzer" license=MIT

New Skill Project. Initialization of a new skill project in the repository, in Anthropic Agent Skills format, with the Ahrena layout

Cry: New Skill Project

Prefix: cry- | Type: Recurring Command | Scope: Initialization of a new skill project in the repository, in Anthropic Agent Skills format, with the Ahrena layout

Usage

/cry-new-skill <slug> [options]

Parameters

| Parameter | Required | Description | Example | |-----------|:--------:|-------------|---------| | slug | Yes | Project name in kebab-case (1-64 chars, a-z/0-9/hyphen, no leading/trailing hyphen, no --) | scheduled-payments-skill | | description= | Yes | Single sentence for the frontmatter (1-1024 chars), with what it does + when to use | description="Schedules bank transfers when the user requests payment for a future date" | | language= | No | BCP 47; default = language.default in .directives | language=en | | license= | No | Identifier (Apache-2.0, MIT) or reference | license=Apache-2.0 | | human_title= | No | Human-readable title for the # H1 of SKILL.md | human_title="Scheduled Payments" | | with_widgets= | No | true (default) or false | with_widgets=false | | with_tools= | No | true (default) or false | with_tools=false | | with_scripts= | No | python (default), js, or false | with_scripts=js |

What the Command Does

  1. Validates slug and description against the Anthropic Agent Skills spec (regex and limits)
  2. Resolves paths.skills_root from .ahrena/.directives (default skills)
  3. Confirms the destination {paths.skills_root}/{slug}/ does not exist
  4. Invokes kata-init-skill with the received parameters
  5. Reports the created path, applied opt-outs, and next steps

Prompt Template

Context:
- slug: {{slug}}
- description: {{description}}
- language: {{language}} (optional)
- license: {{license}} (optional)
- human_title: {{human_title}} (optional)
- with_widgets: {{with_widgets}} (default true)
- with_tools: {{with_tools}} (default true)
- with_scripts: {{with_scripts}} (default python)

Task:
Invoke kata-init-skill with the parameters above. The kata:
1. Validates slug and description per codex-skill-anthropic-agent-skills
2. Copies framework/templates/skill-project-sample/ to
   {paths.skills_root}/{slug}/, replacing placeholders
3. Applies opt-outs (with_widgets, with_tools, with_scripts)
4. Ensures .gitignore contains .build/
5. Reports the result

Abort if: invalid slug, destination already exists, or template missing.

Output format:
Confirmation of the created project, list of subdirectories, next steps
for authoring. On error, specific message and suggested correction.

Invocation Example

/cry-new-skill scheduled-payments-skill \
  description="Schedules and approves bank transfers using widgets connected to Python tools. Use when the user wants to create or approve a scheduled transfer." \
  license=Apache-2.0

Expected output:

✅ Project created: skills/scheduled-payments-skill/
   SKILL.md, skill.config.json, .skill-manifest.json
   widgets/ (React + TS)
   scripts/ (Python)
   tools/ (MCP placeholder)
   references/REFERENCE.md

.gitignore: .build/ added.

Next steps:
- Edit SKILL.md (body)
- Add components in widgets/src/
- Add handlers in tools/handlers/
- Suggested next cry: `/cry-skill --mode implement --slug <slug>` to orchestrate authoring + validation + packaging via warrior-claudionor

Restrictions

  • The Cry does not modify .ahrena/.directives (per lex-directives)
  • The Cry does not create the project if the destination already exists; the user decides whether to remove or pick another slug
  • User messages in the language.default language; technical identifiers (slug, frontmatter, placeholder) preserved

Difference from Kata

| Aspect | Cry | Kata | |--------|-----|------| | Nature | 1:1 shortcut that gathers parameters and dispatches | Full scaffold procedure (8 steps) | | Validation | Parameter shape | Anthropic spec compliance + filesystem | | Effect | Invokes the Kata | Writes files, updates .gitignore |

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/new-skill-project-mrwake7i/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/new-skill-project-mrwake7i' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/new-skill-project-mrwake7i/download' --output '.skill-downloads/new-skill-project-mrwake7i/SKILL.md.part' && mv '.skill-downloads/new-skill-project-mrwake7i/SKILL.md.part' '.skill-downloads/new-skill-project-mrwake7i/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/new-skill-project-mrwake7i/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