1# Agent Skills Repository
 2
 3Amolith's collection of Agent Skills—markdown-based documentation that extends AI agent capabilities through a standardized format.
 4
 5## Repository Structure
 6
 7Each directory under `skills/` is a skill. A skill's directory name **must match** its `name` frontmatter field.
 8
 9```
10skills/skill-name/
11├── SKILL.md          # Required: YAML frontmatter + markdown instructions
12├── references/       # Optional: additional documentation loaded on-demand
13├── scripts/          # Optional: executable code
14└── assets/           # Optional: templates, resources
15```
16
17## Creating/Editing Skills
18
19The `skills/authoring-skills/` directory has the necessary info for, well, authoring skills.
20
21## Listing Skills in README.md
22
23When adding a new skill, include an entry in the "Available Skills" section of README.md. Entries should be:
24
25- **Third-person present tense**: "Writes", "Creates", "Queries" — describes what the skill does
26- **Concise**: Tight paragraph that conveys the capability
27- **Human-oriented**: A human can read it and understand what the skill will make the agent do
28
29Example pattern:
30- "Creates commits following Conventional Commits format via git-format."
31
32Sort entries alphabetically by skill name.
33
34## Naming Convention
35
36Two categories of skills exist:
37
38- **Generic capability skills** (`formatting-commits`): Use specific tools to accomplish general tasks. Tool name omitted from skill name.
39- **Service workflow skills** (`creating-tasks-through-lunatask`): Workflows for specific proprietary services. Service name included via `-through-{service}` suffix.
40
41## Design Principles
42
431. Progressive disclosure: Frontmatter loads at startup; SKILL.md body loads on activation; references/ load on-demand
442. Conciseness over completeness: Every token competes for context window space
453. Appropriate freedom: Match instruction specificity to task fragility (see `skills/authoring-skills/references/patterns.md`)