How do I install the Skill Router skill?

Run npx skillmds@latest add hussi9/skill-router in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skill Router safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill Router?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill Router free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skill Router?

hussi9 (@hussi9) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill Router by hussi9 — Agent Skill

Name: Skill Router
Author: hussi9

Skill Router

Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.

hussi9 3f06f37 11 files · 65.5 KB Updated Sep 17, 2026

File contents

Skill Router (v4)

Routing runs from hooks. A UserPromptSubmit hook classifies every prompt and injects a route card before your first action. Your job is to follow the card, not to compute one.

The route card

[skill-router] This is a BROKEN task — 2-step chain.
[skill-router] Chain: mac-doctor → superpowers:systematic-debugging
▶ mac-doctor  (inherit, in-session)
▶ superpowers:systematic-debugging  (inherit, in-session)
[skill-router] Gates before done: simulator screenshot
[skill-router] Memory: airbook_crash_root_cause  (read from ~/.claude/projects/-Users-airbook/memory/)
[skill-router] IRON RULE: call Skill(skill="mac-doctor") before any Edit/Write/Task.

First ▶ is the domain skill — one of yours, or a plugin's. Load it first.
Second ▶ is the process skill (debugging, planning, TDD). Load it next.
Gates are completion conditions from the project. Check every one before "done".
Memory names the memory file for this project. Read it before deciding.

Two tiers

Line on the card	Meaning
`IRON RULE: …`	hard — Edit/Write/Task are denied until the skill is loaded. BROKEN path, and project routes with gates.
`Soft route: …`	soft — nothing is blocked. If you finish without loading it, the Stop hook asks once; answer by loading it or by one line `[skill-router] skipped <skill>: <reason>`.

Wrong route either way: python3 ~/.claude/skills/skill-router/scripts/router_override.py "<reason>". The user can also write [no-router] in their message.

How the card is decided

Project route in SKILL.personal.md (@economicalai, capgo, …) — deterministic.
Enriched index of every invokable skill (~/.claude/skill_index.json): name, "use when" triggers, keywords, project aliases. Lexical rank, ~50 ms.
Small model (Gemini Flash-Lite, ~1 s, cached) settles low-confidence ties.
Process table (references/routing-tables.md) supplies the second leg.

Questions, discussion and harness noise get no card. Silence is an answer.

Sub-agents

Every Agent(...) dispatch gets the parent's route appended to its prompt (skill, gates, memory), and SubagentStart briefs the agent with the skills paired to its type. Enforcement never reaches inside a sub-agent.

When there is no card

Non-trivial task, no [skill-router] line? Run the fallback yourself: python3 ~/.claude/skills/skill-router/scripts/router.py <<< "the prompt". If that is silent too, routing may be dead: python3 ~/.claude/skills/skill-router/scripts/doctor.py.

Maintenance

Command	When
`scripts/doctor.py`	routing feels dead, or after a Claude Code upgrade
`scripts/build_index.py --enrich`	you installed or edited a skill
`scripts/index_match.py --all "<prompt>"`	a route looked wrong — see the ranking
`scripts/learn.py --show`	what has been learned
`scripts/check.sh`	after editing any routing logic

Project routes, projects, gates: SKILL.personal.md. Full tables and protocols: references/routing-tables.md.

---name: skill-routerdescription: Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.---# Skill Router (v4)Routing runs from hooks. A `UserPromptSubmit` hook classifies every promptand injects a **route card** before your first action. Your job is to*follow the card*, not to compute one.## The route card```[skill-router] This is a BROKEN task — 2-step chain.[skill-router] Chain: mac-doctor → superpowers:systematic-debugging▶ mac-doctor (inherit, in-session)▶ superpowers:systematic-debugging (inherit, in-session)[skill-router] Gates before done: simulator screenshot[skill-router] Memory: airbook_crash_root_cause (read from ~/.claude/projects/-Users-airbook/memory/)[skill-router] IRON RULE: call Skill(skill="mac-doctor") before any Edit/Write/Task.```- **First `▶` is the domain skill** — one of yours, or a plugin's. Load it first.- **Second `▶` is the process skill** (debugging, planning, TDD). Load it next.- **Gates** are completion conditions from the project. Check every one before "done".- **Memory** names the memory file for this project. Read it before deciding.## Two tiers| Line on the card | Meaning ||---|---|| `IRON RULE: …` | **hard** — Edit/Write/Task are denied until the skill is loaded. BROKEN path, and project routes with gates. || `Soft route: …` | **soft** — nothing is blocked. If you finish without loading it, the Stop hook asks once; answer by loading it or by one line `[skill-router] skipped <skill>: <reason>`. |Wrong route either way: `python3 ~/.claude/skills/skill-router/scripts/router_override.py "<reason>"`.The user can also write `[no-router]` in their message.## How the card is decided1. **Project route** in `SKILL.personal.md` (`@economicalai`, `capgo`, …) — deterministic.2. **Enriched index** of every invokable skill (`~/.claude/skill_index.json`): name, "use when" triggers, keywords, project aliases. Lexical rank, ~50 ms.3. **Small model** (Gemini Flash-Lite, ~1 s, cached) settles low-confidence ties.4. **Process table** (`references/routing-tables.md`) supplies the second leg.Questions, discussion and harness noise get no card. Silence is an answer.## Sub-agentsEvery `Agent(...)` dispatch gets the parent's route appended to its prompt(skill, gates, memory), and `SubagentStart` briefs the agent with the skillspaired to its type. Enforcement never reaches inside a sub-agent.## When there is no cardNon-trivial task, no `[skill-router]` line? Run the fallback yourself:`python3 ~/.claude/skills/skill-router/scripts/router.py <<< "the prompt"`.If that is silent too, routing may be dead: `python3 ~/.claude/skills/skill-router/scripts/doctor.py`.## Maintenance| Command | When ||---|---|| `scripts/doctor.py` | routing feels dead, or after a Claude Code upgrade || `scripts/build_index.py --enrich` | you installed or edited a skill || `scripts/index_match.py --all "<prompt>"` | a route looked wrong — see the ranking || `scripts/learn.py --show` | what has been learned || `scripts/check.sh` | after editing any routing logic |Project routes, projects, gates: `SKILL.personal.md`. Full tables and protocols: `references/routing-tables.md`.

Frequently asked questions