← All docs

DOCS

  1. Getting Started
  2. Configuration
  3. Tools
  4. Sessions
  5. Compaction & Branch Summarization
  6. Subagents
  7. Extensions
  8. Themes
  9. Memory System
  10. Skills
  11. Code intelligence (LSP)
  12. Termux Support
  13. Environment variables
  14. Custom Providers
  15. JSON Event Stream Mode
  16. Keybindings
  17. Prompt Templates
  18. RPC Mode
  19. Session File Format
  20. Shell Aliases
  21. Terminal Setup
  22. tmux Setup
DOCS
  1. Getting Started
  2. Configuration
  3. Tools
  4. Sessions
  5. Compaction & Branch Summarization
  6. Subagents
  7. Extensions
  8. Themes
  9. Memory System
  10. Skills
  11. Code intelligence (LSP)
  12. Termux Support
  13. Environment variables
  14. Custom Providers
  15. JSON Event Stream Mode
  16. Keybindings
  17. Prompt Templates
  18. RPC Mode
  19. Session File Format
  20. Shell Aliases
  21. Terminal Setup
  22. tmux Setup
ON THIS PAGE
  1. Installing Skills
  2. Using Skills
  3. Skill Structure
  4. SKILL.md Format
  5. Policy
  6. Listing Skills
  7. Token Budget

Skills

Skills are installable packages that extend Neo Code with specialized instructions, workflows, and tools.

#Installing Skills

/skills install <source>          Install globally (user scope)
/skills install <source> --local  Install for current project only

Sources can be:

  • GitHub URLs
  • Local directories
  • npm-style package references

#Using Skills

Skills are loaded automatically when a task matches their description. They can also be invoked explicitly:

/skill:<name>              Invoke a skill as a slash command

The /skill:name commands are available when enableSkillCommands is true in settings (default: true).

Skills can also opt out of automatic invocation via frontmatter:

---
name: skill-name
description: Use when [conditions]
disable-model-invocation: true
---

#Skill Structure

skill-name/
  SKILL.md              Required — frontmatter + instructions
  agents/
    openai.yaml         Optional — UI metadata (display name, icon, prompt)
  scripts/              Optional — executable tools
  references/           Optional — documentation loaded on demand
  assets/               Optional — templates, images

#SKILL.md Format

---
name: skill-name
description: Use when [triggering conditions]
---

# Skill Name

Instructions for the agent...

#Policy

In agents/openai.yaml:

policy:
  allow_implicit_invocation: false  # Only invoke explicitly

#Listing Skills

/skills list    Show all loaded skills with source and path

#Token Budget

Skill metadata in the system prompt is limited to 2% of the context window. Skills are prioritized: project > user > path. Excess skills are omitted with a notice.

ON THIS PAGE

  1. Installing Skills
  2. Using Skills
  3. Skill Structure
  4. SKILL.md Format
  5. Policy
  6. Listing Skills
  7. Token Budget
Previous← Memory SystemNextCode intelligence (LSP) →

Neo Code

Neosantara-first AI coding agent for your terminal.

Product

  • Docs
  • Pricing
  • GitHub

Neosantara

  • Dashboard
  • API

Legal

  • Terms
  • Privacy

2026 Neosantara. All rights reserved.