# Solid Intent Router

> Route SolidJS user intent to the correct macro and domain subskill with deterministic keyword precedence and fallback rules. Use when selecting which Solid skill should execute first.

- **Type:** Skill
- **Install:** `agentstack add skill-lvcoi-solidjskills-solid-intent-router`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [lvcoi](https://agentstack.voostack.com/s/lvcoi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [lvcoi](https://github.com/lvcoi)
- **Source:** https://github.com/lvcoi/solidJSkills/tree/main/skills/solid-intent-router

## Install

```sh
agentstack add skill-lvcoi-solidjskills-solid-intent-router
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# solid-intent-router

## Trigger

Use this skill when a request could match multiple SolidJS skills and deterministic routing is required.

## Required Inputs

- Raw user prompt.
- Optional file/diff context if present.
- Optional runtime hint (core/router/start/meta).

## Workflow

1. Evaluate explicit package signals first (`solid-router`, `solid-start`, `solid-meta`).
2. Apply deterministic precedence from `tools/gemini-mcp-extension/skill-routing-map.md`.
3. Select one primary macro skill and one secondary domain subskill.
4. If confidence is low, choose the closest macro skill and annotate missing input.

## Failure Modes

- Conflicting package signals: route to `solid-design-patterns` + best-fit domain subskill.
- No recognizable signal: default to `solid-component-builder` + `solid-reactivity-core-expert`.
- Missing prompt text: fail and request prompt.

## Output Contract

Return output matching `IntentRoutingOutput` schema with `primary_skill`, `secondary_skill`, confidence, rationale, and `citations` (`doc_id`, `claim`).

## Validation

- `node tools/scripts/validate-skills.mjs --skill solid-intent-router`
- `node tools/scripts/run-smoke-evals.mjs`

## Key Corpus References

Use these `doc_id` values with the `read_corpus_doc` MCP tool:

- `solid-core.reference.basic-reactivity.create-signal` — core signal API (default fallback)
- `solid-router.solid-router.index` — router package overview
- `solid-start.solid-start.index` — SolidStart package overview
- `solid-meta.solid-meta.index` — solid-meta package overview

## References

- `../../tools/gemini-mcp-extension/skill-routing-map.md`
- `../../references/solidjs-normalized/manifest.jsonl`
- `../../references/solidjs-normalized/taxonomy.json`

## Source & license

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

- **Author:** [lvcoi](https://github.com/lvcoi)
- **Source:** [lvcoi/solidJSkills](https://github.com/lvcoi/solidJSkills)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-lvcoi-solidjskills-solid-intent-router
- Seller: https://agentstack.voostack.com/s/lvcoi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.