Skip to content
Agentmart
Submit a tool

router

Intelligent intent detection and workflow routing for NSO.

Skill by lshtram

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lshtram-router

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Intelligent intent detection and workflow routing for NSO.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/router

What's inside

Skill name
router
Description
Intelligent intent detection and workflow routing for NSO.
License
MIT
Instructions
65 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Instructions read files in your home folder (~/.ssh, ~/.aws…)

Files (5)

  • SKILL.md
  • contracts.md · references/
  • keywords.md · references/
  • router_logic.py · scripts/
  • test_router_logic.py · scripts/

SKILL.md (first lines)

# Role
Orchestrator

# Trigger
- User invokes `/router` command or requests a development task.
- Any request that sounds like: build, fix, debug, review, plan, design, architect.

# Inputs
- User's natural language request.
- Existing memory files (if loaded by the agent).

# Outputs
- Detected workflow (BUILD/DEBUG/REVIEW/PLAN).
- Task hierarchy (list of scoped tasks).
- Router Contract template (YAML).
- Routing decision log.

# Steps
## 1. Parse User Request
Extract the user's intent from the request text.

## 2. Detect Intent (Keyword Matching)
Match keywords against BUILD, DEBUG, REVIEW, PLAN patterns.

## 3. Select Workflow
Based on intent detection, select the appropriate workflow.
Default to BUILD if no explicit keywords found.
Priority: DEBUG > REVIEW > PLAN > BUILD.

## 4. LOAD Memory (Optional)
If memory files are available, read them for context.
Use memory to inform routing decisions (e.g., check for in-progress work).

## 5. Create Task Hierarchy
Generate a human-readable task breakdown for the selected workflow.
Scope each task to 2-5 minutes.

## 6. Output Router Contract
Generate a YAML contract template for the workflow agent.

## 7. Log Routing Decision
Record the routing decision for traceability.

# Usage
```bash
# Via command line
python3 ~/.config/opencode/nso/scripts/router_logic.py "build a new feature"

# Via OpenCode
/router "debug the login issue"
```

# Examples
- `/router "implement a REST API for user authentication"` → BUILD workflow
- `/router "fix the memory leak in production"` → DEBUG workflow
- `/router "review the security implementation"` → REVIEW workflow
- `/router "plan the microservices architecture"` → PLAN workflow

# Files
- `scripts/router_logic.py`: Core routing logic
- `references/keywords.md`: Trigger keyword definitions
- `references/contracts.md`: Router Contract format and validation
- `scripts/test_router_logic.py`: Unit tests

From lshtram/nso, MIT.

More from lshtram/nso

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Feb 12, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from lshtram

Cite this page

router skill. Agent Mart. https://agentmart.dev/skills/lshtram-router (last updated 2026-10-24)