# manoj-11-dahal/try-skills architecture

> Architecture diagram of the GitHub repository manoj-11-dahal/try-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/manoj-11-dahal/try-skills
- Repository: https://github.com/manoj-11-dahal/try-skills

## Overview

Agentic Skills is a library of more than 16,500 task-focused Markdown workflows, not an agent runtime. A user browses the index, opens a matching skill, and provides it to an agent host; the host maps the workflow to authorized tools and produces a concrete artifact, checks its feedback signal, then reports or stops/escalates. Skills span multiple domains and commonly specify scope, evidence gathering, bounded iteration, and approval gates. The graph reflects README-documented behavior; sampled scripts concern repository content generation and organization, not runtime execution.

Main entry points: [`skills/ai-agent-systems/agent-architecture-orchestration`](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration) (Skill Package), [`INDEX.md`](https://github.com/manoj-11-dahal/try-skills/blob/main/INDEX.md) (Skill Index), [`skills`](https://github.com/manoj-11-dahal/try-skills/tree/main/skills) (Skill Collection), [`skills/ai-agent-systems`](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems) (Domain Skills)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_catalog["Discovery and Catalog"]
  node_index["Skill Index<br/>[INDEX.md]"]
  node_collection["Skill Collection"]
  node_domain_skills["Domain Skills"]
end

subgraph group_workflows["Skill Workflows"]
  node_skill_package["Skill Package"]
  node_scope["Scope and Authority"]
  node_evidence["Baseline Evidence"]
  node_tool_action["Focused Tool Action"]
  node_artifact["Concrete Artifact"]
  node_feedback["Feedback Signal"]
  node_iteration["Bounded Iteration"]
  node_approval["Stop and Approval Gates"]
end

subgraph group_execution["Host Execution"]
  node_host["Agent Host"]
  node_authorized_tools["Authorized Tools"]
  node_result["Reported Result"]
end

node_user(("User"))

node_user -->|"browses"| node_index
node_user -->|"selects"| node_skill_package
node_index -->|"indexes"| node_collection
node_collection -->|"organizes"| node_domain_skills
node_skill_package -->|"defines"| node_scope
node_scope -->|"guides"| node_evidence
node_evidence -->|"informs"| node_tool_action
node_tool_action -->|"updates"| node_artifact
node_artifact -->|"checked against"| node_feedback
node_feedback -->|"guides"| node_iteration
node_iteration -->|"retries"| node_tool_action
node_feedback -->|"may trigger"| node_approval
node_skill_package -->|"provided to"| node_host
node_host -->|"maps workflow"| node_authorized_tools
node_host -->|"reports"| node_result
node_approval -->|"records handoff"| node_result

click node_index "https://github.com/manoj-11-dahal/try-skills/blob/main/INDEX.md"
click node_collection "https://github.com/manoj-11-dahal/try-skills/tree/main/skills"
click node_domain_skills "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems"
click node_skill_package "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_scope "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_evidence "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_tool_action "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_artifact "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_feedback "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_iteration "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"
click node_approval "https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_index,node_collection,node_domain_skills,node_user toneBlue
class node_skill_package,node_scope,node_evidence,node_tool_action,node_artifact,node_feedback,node_iteration,node_approval toneAmber
class node_host,node_authorized_tools,node_result toneMint
```

## Components

### Discovery and Catalog

- [Skill Index](https://github.com/manoj-11-dahal/try-skills/blob/main/INDEX.md): `INDEX.md`
- [Skill Collection](https://github.com/manoj-11-dahal/try-skills/tree/main/skills): `skills`
- [Domain Skills](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems): `skills/ai-agent-systems`

### Skill Workflows

- [Skill Package](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Scope and Authority](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Baseline Evidence](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Focused Tool Action](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Concrete Artifact](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Feedback Signal](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Bounded Iteration](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`
- [Stop and Approval Gates](https://github.com/manoj-11-dahal/try-skills/tree/main/skills/ai-agent-systems/agent-architecture-orchestration): `skills/ai-agent-systems/agent-architecture-orchestration`

### Host Execution

- **Agent Host**
- **Authorized Tools**
- **Reported Result**

### Other components

- **User**

## Connections

- User → Skill Index: browses (evidence: `README.md`)
- User → Skill Package: selects (evidence: `README.md`)
- Skill Index → Skill Collection: indexes (evidence: `README.md`)
- Skill Collection → Domain Skills: organizes (evidence: `README.md`)
- Skill Package → Scope and Authority: defines (evidence: `README.md`)
- Scope and Authority → Baseline Evidence: guides (evidence: `README.md`)
- Baseline Evidence → Focused Tool Action: informs (evidence: `README.md`)
- Focused Tool Action → Concrete Artifact: updates (evidence: `README.md`)
- Concrete Artifact → Feedback Signal: checked against (evidence: `README.md`)
- Feedback Signal → Bounded Iteration: guides (evidence: `README.md`)
- Bounded Iteration → Focused Tool Action: retries (evidence: `README.md`)
- Feedback Signal → Stop and Approval Gates: may trigger (evidence: `README.md`)
- Skill Package → Agent Host: provided to (evidence: `README.md`)
- Agent Host → Authorized Tools: maps workflow (evidence: `README.md`)
- Agent Host → Reported Result: reports (evidence: `README.md`)
- Stop and Approval Gates → Reported Result: records handoff (evidence: `README.md`)
