AgentStack
SKILL verified MIT Self-run

Skill Creator

skill-d-o-hub-rust-self-learning-memory-skill-creator · by d-o-hub

Create new Claude Code skills with proper structure, YAML frontmatter, and best practices. Use when creating reusable knowledge modules, adding specialized guidance, or building domain-specific expertise.

No reviews yet
0 installs
15 views
0.0% view→install

Install

$ agentstack add skill-d-o-hub-rust-self-learning-memory-skill-creator

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Skill Creator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill Creator

Create new Claude Code skills following the official format and best practices.

Quick Reference

  • [Structure Guide](structure.md) - Directory format and file organization
  • [Naming Rules](naming.md) - Skill naming requirements
  • [Description Guide](description.md) - Writing effective descriptions
  • [Templates](templates.md) - Process, knowledge, and tool skill templates
  • [Examples](examples.md) - Complete skill creation walkthroughs
  • [Validation](validation.md) - Commands to validate new skills

When to Use

  • Creating a new reusable knowledge module
  • Adding specialized guidance for specific tasks
  • Building domain-specific expertise into Claude Code
  • Need to ensure proper skill format and structure

Required SKILL.md Format

Every skill requires a SKILL.md file with two parts:

  1. YAML frontmatter (metadata between --- markers on line 1)
  2. Markdown instructions (guidance for Claude)
---
name: skill-name
description: Brief description of what this skill does and when to use it
---

# Skill Title

## Instructions
Step-by-step guidance for Claude...

YAML Frontmatter Fields

| Field | Required | Description | |-------|----------|-------------| | name | Yes | Lowercase letters, numbers, hyphens only (max 64 chars). Must match directory name. | | description | Yes | What the skill does and when to use it (max 1024 chars). Claude uses this to match requests. | | allowed-tools | No | Tools Claude can use without permission | | model | No | Specific model to use | | context | No | Set to fork for isolated sub-agent context |

File Structure

skill-name/
├── SKILL.md              # Required - overview and navigation
├── reference.md          # Detailed docs - loaded when needed
├── examples.md           # Usage examples - loaded when needed
└── scripts/
    └── helper.sh         # Utility script - executed, not loaded

Best Practices

  • Keep SKILL.md under 250 lines - Use progressive disclosure
  • Write specific descriptions - Include trigger terms users would naturally use
  • Link supporting files - From SKILL.md using markdown links
  • Validate structure - Check YAML syntax and file organization
  • No .py or .sh files in root - Place scripts in scripts/ or within the skill directory. Never create one-off scripts in the repository root.

See [naming.md](naming.md) for naming conventions and [templates.md](templates.md) for ready-to-use templates.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.