Skill Router — AI skill for Claude Code
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires.
How to install Skill Router
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open hussi9/skill-router and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Skill Router does
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.
Alternatives in AI
- AI Engineering Hub — In-depth tutorials on LLMs, RAGs and real-world AI agent applications 37.2k ★
- Klaatcode — Open-source AI coding agent for the terminal 357 ★
- Cupcake — A native policy enforcement layer for AI coding agents 255 ★
README
skill-router
[](https://github.com/hussi9/skill-router/stargazers) [](LICENSE) [](https://github.com/hussi9/skill-router/actions)
**Your skill first, the process skill second, gates and memory on the card — before any tool fires.**
A hook-driven router for Claude Code. It indexes every skill you have installed by *when it applies*, ranks them against each prompt in ~80 ms, asks a small model only when the ranking is unsure, and injects a route card before Claude's first action. Enforcement is tiered: hard where a wrong skill is expensive, soft everywhere else. The route follows every sub-agent you dispatch.
> my macbook restarted again last night, can you check why
[skill-router] This is a BROKEN task — 2-step chain.
[skill-router] Chain: mac-doctor → superpowers:systematic-debugging
[skill-router] Invoke step 1/2 now:
▶ mac-doctor (inherit, in-session)
▶ superpowers:systematic-debugging (inherit, in-session)
[skill-router] Memory: airbook_crash_root_cause (read from ~/.claude/projects/.../memory/)
[skill-router] IRON RULE: call Skill(skill="mac-doctor") before any Edit/Write/Task.
Every line is `[skill-router]`-prefixed, so `grep '\[skill-router\]'` on a transcript shows exactly what was routed.
Why (v4, September 2026)
An audit of this machine after five months of use:
| Finding | Number |
|---|---|
| Skills installed / ever invoked / invoked last month | 291 / 80 / 32 |
| Tokens the skill listing cost every session start | ~22,600 |
| Skills the v3 routing table could name | ~20 (all process skills) |
| Real prompts the v3 router answered with silence | 4 of 10 |
writing-plans announced / followed |
6 / 1 |
| Months routing was dead without anyone noticing | 2 |
The routing table could never enumerate the domain skills — t
Related Skills
Systems Thinking
A cognitive base that shifts AI agent reasoning from linear cause-effect chains to feedback-driven structural
Frontend Design Pro
Machine-enforced frontend UI/UX skill pack for AI agents. Registry + lazy loading: a 2,149-token router loads
Inspect Chats
Inspects Chat AI conversation logs for a workspace — routing-outcome breakdowns (Routed/NotRouted/Abandoned),
Media Routing Mesh
Routed Media OS 2026: 96 AI Skills, 13 Modes & 7 Agents for FFmpeg, OBS, DeckLink & Dolby Vision
UnabatedPM Coaching
The first coaching-depth PM skills for AI. 27 skills with scoring rubrics, behavioral markers, real coaching e
Smart Dispatch Report
Show smart-dispatch routing stats — model distribution, estimated savings, and budget-mode downgrades.
Related Agents
Router Opus
Worker subagent dispatched by the auto-model-router for deep work — architectural refactors, multi-file cross-
Clarify Thinking
Probe lens 1 of 6. Clarifies key terms, traces where conclusions came from, and exposes reasoning chains that
AI Reviewer
Senior AI prompt-engineering reviewer (2026) auditing a single Claude Code agent or skill file. Reviews frontm