Skip to main content
skill CX Codex

skill-router · rohitg00 — Claude Code skill: overview and install

The skill-router skill maps pro-workflow skills and commands to jobs, with guidance on when to use each and whether a person or the agent starts it. Use it when you’re unsure what fits.

MIT ★ 2,966 updated 2026-09-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
Open on GitHub

What skill-router does

skill-router is a task-based directory for pro-workflow skills and slash commands. Its groups cover planning, parallel work, context, quality checks, research, and project setup. Each entry explains when to reach for it and whether a person invokes it or the agent selects it automatically.

Describe the job, match it to a group, then use the entry’s guidance to choose between close options. For instance, plan-interrogate resolves decisions before coding, while improve-architecture proposes structural changes as a plan rather than rewriting code. The directory also lists commands without a matching skill. Keeping it accurate takes a maintenance step: update the index in the same change when a skill is added, renamed, removed, or its role changes.

What it helps with

  • find a pro-workflow skill for a specific job
  • see which skills the agent can trigger automatically
  • choose between similar skills using their guidance
  • identify slash commands without a matching skill

Example prompts for the agent

  • Which pro-workflow skill should I use to review these changes?
  • Show me which context-related skills the agent can trigger automatically.
  • Group the pro-workflow skills and commands by the jobs they handle.

How to install skill-router

1Plugin marketplace

/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow

This installs the whole pro-workflow plugin with all its skills

2Skills CLI (Vercel)

npx skills add rohitg00/pro-workflow --skill skill-router -a claude-code

3Manually: put the files in place

~/.claude/skills/skill-router/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-router/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-router

How do I install skill-router in Claude Code?

Add the marketplace with /plugin marketplace add rohitg00/pro-workflow, then install the plugin with /plugin install pro-workflow@pro-workflow.

What does skill-router do?

It organizes pro-workflow skills and commands by job, explains when each fits, and marks whether a person or the agent starts it.

How does skill-router distinguish manual and automatic activation?

The [human] and [auto] labels show whether a person invokes a skill or the agent selects it based on a prompt. Skills marked [human] are intended for deliberate user invocation.

Source text

SKILL.md · MIT
---
name: skill-router
description: The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
user-invocable: true
---

# skill-router

You cannot hold 41 skills and 23 commands in your head. This is the index so you do not have to. Each entry says what it is for and how it fires: `[human]` you invoke it deliberately, `[auto]` the agent reaches for it from your prompt.

Keep this honest. When a skill is added, renamed, removed, or changes how it fits a flow, update this file in the same change. A router that points at a skill that no longer exists, or omits a new one, is worse than none.

## How to use it

State the job in one line. Match it to a group below. If two skills look close, the `when to reach` clause is the tiebreaker. Most skills have a matching slash command of the same name, so this index covers commands too.

## Self-correction and memory

- `learn-rule` `[human]` - capture a correction as a durable rule loaded on every future session.
- `replay-learnings` `[auto]` - surface past learnings relevant to the task before you start.
- `insights` `[human]` - correction trends, heatmaps, productivity view.
- `skill-optimizer` `[human]` - train a skill's SKILL.md against accumulated corrections.

## Planning and decisions

- `plan-interrogate` `[human]` - resolve every open decision before code; emits a decision ledger, a shared-language `CONTEXT.md`, and decision records.
- `domain-modeling` `[human]` - build the project's shared vocabulary and bounded contexts up front.
- `improve-architecture` `[human]` - audit an area and propose the smallest structural moves; plan, not rewrite.
- `thoroughness-scoring` `[auto]` - score each decision point 1-10 so effort tracks stakes.
- `orchestrate` `[human]` - wire commands, agents, and skills together for a multi-phase feature.

## Multi-agent and parallel work

- `agent-teams` `[human]` - lead plus teammates sharing one task list.
- `batch-orchestration` `[human]` - split a large change into independent units, one agent each.
- `parallel-worktrees` `[human]` - git worktrees for zero-dead-time parallel sessions.
- `sprint-status` `[human]` - status across active parallel sessions.

## Context and tokens

- `context-engineering` `[human]` - Write, Select, Compress, Isolate; the memory taxonomy.
- `context-optimizer` `[human]` - trim token usage when a session drags.
- `compact-guard` `[human]` - preserve critical state before compaction.
- `token-efficiency` `[auto]` - anti-sycophancy, tool-call budgets, one-pass output.
- `mcp-audit` `[human]` - audit MCP servers for token overhead, redundancy, security.

## Quality and review

- `tdd` `[human]` - red-green-refactor loop with good-test guidance.
- `deslop` `[auto]` - strip AI slop and over-engineering from the branch diff; also lints SKILL.md files.
- `smart-commit` `[human]` - quality gates, staged review, conventional commit.
- `llm-gate` `[auto]` - LLM-verified checks on commits, patterns, patches.
- `llm-council` `[human]` - multi-LLM deliberation on a hard call.
- `safe-mode` `[human]` - hook-enforced guard against destructive operations.

## Design and writing

- `design-engineering` `[auto]` - interface craft: motion decision framework, easing, timing, springs, component feel, visual foundations.
- `writing-guidelines` `[auto]` - clear-writing standards for docs, UI copy, error messages, commit and PR text.

## Knowledge and research

- `wiki-builder` `[human]` - start and grow a persistent FTS5-indexed wiki.
- `wiki-query` `[auto]` - BM25 retrieval over a wiki with citations.
- `wiki-research-loop` `[human]` - budget-capped auto-grow of a wiki.
- `wiki-viewer` `[human]` - self-contained HTML view of a wiki.
- `survey-generator` `[human]` - structured literature survey on a topic.

## Orientation, cost, lifecycle, setup

- `module-map` `[auto]` - one-screen map of an unfamiliar area.
- `bug-capture` `[auto]` - turn a reported defect into a domain-language issue.
- `cost-tracker` `[human]` - session cost and budget alerts.
- `permission-tuner` `[human]` - generate allow/deny rules from denial patterns.
- `wrap-up` `[human]` - end-of-session ritual: audit, persist learnings, handoff.
- `session-handoff` `[human]` - structured handoff doc for the next session.
- `file-watcher` `[human]` - hooks that react to config/env/dep changes.
- `auto-setup` `[human]` - configure gates, hooks, settings for a new project.
- `pro-workflow` `[auto]` - the system overview; orchestration patterns and reference.
- `skill-router` `[human]` - this index of every skill and command.

## Command-only (no matching skill)

These slash commands ship without a skill of the same name: `/commit`, `/develop`, `/doctor`, `/handoff`, `/learn`, `/list`, `/parallel`, `/replay`, `/search`, `/skill-optimize`, `/wiki`.

## Naming the invocation mode

Every skill declares one intent. `[human]` skills are deliberate, side-effectful, or session rituals and carry `user-invocable: true`. `[auto]` skills earn their place in context by a description precise enough to fire on the right prompt and stay quiet otherwise. See [`rules/skill-conventions.mdc`](../../rules/skill-conventions.mdc) for the full convention and the write-operation rules for state-changing skills.

© Rohit Ghumare · MIT · rohitg00/pro-workflow

Similar skills

SKILL.md skills catalog →

skill-router by other authors comes first.

skill-router zhaono1 skill-router reads your request and points to the narrowest matching skill from the catalog. Handy when you don't know which tool fits the job. CX Codex +1 896installs skill-router dotslashsimran The skill-router Claude Code skill selects a matching skill or builds a sequence for a task. It kicks in when a request is vague or could call for several skills. CX Codex +1 ★ 541repo stars expo-router expo Skill for file-based routing, stacks, modals and tabs in Expo Router. Use it when building navigation in a React Native mobile app. CX Codex +1 34,500installs nextjs-app-router-patterns Seth Hobson This skill covers Next.js App Router patterns for rendering, routing, and data fetching. Use it when starting an App Router project or moving from Pages Router. CX Codex +1 32,529installs vue-router-best-practices github.com/vuejs-ai vue-router-best-practices is a Claude Code skill that teaches Vue Router 4 navigation guards, route params, and component lifecycle synchronization. It helps prevent redirect loops and memory leaks. CX Codex +1 16,700installs clerk-react-router-patterns clerk clerk-react-router-patterns guides Clerk integration with React Router v7/v8, including loaders, protected routes, SSR auth, and organization switching. Useful when wiring auth into a router. CX Codex +1 16,300installs router gamedev-skills The router Claude Code skill selects game-development skills based on the project engine and the requested work. It runs at the start of a game-building or debugging request. CX Codex +1 12,900installs tanstack-router-best-practices DeckardGer tanstack-router-best-practices — a rule set for TanStack Router in React: type safety, data loading, search params, navigation. Useful once routing in a project grows past a few pages. CX Codex +1 7,200installs

From the same set83

The whole set →
thoroughness-scoring thoroughness-scoring rates implementation choices from 1 to 10 and prompts the agent to pick thorough solutions with tests and typing over brittle shortcuts. CX Codex +1 ★ 2,966repo stars skill-optimizer The skill-optimizer skill proposes edits to a SKILL.md based on stored corrections, then checks candidates against held-out examples before accepting changes. CX Codex +1 ★ 2,966repo stars agent-teams agent-teams is a Claude Code skill that coordinates multiple sessions through shared tasks, messaging, and file locks. Teammates work in parallel on separate parts of the codebase. CX Codex +1 ★ 2,966repo stars sprint-status sprint-status tracks parallel Claude Code sessions and prevents confusion by enforcing session headers and standardized status lines. CX Codex +1 ★ 2,966repo stars permission-analyst permission-analyst analyzes permission prompts and auto mode denials, recommends permissions rules and autoMode entries. Use it when prompts slow you down or auto mode keeps falling back to confirmations. CX Codex ★ 2,966repo stars safe-mode safe-mode intercepts destructive terminal commands and confines agent edits to a specific directory using Claude Code hooks. CX Codex +1 ★ 2,966repo stars wiki-research-loop wiki-research-loop is a Claude Code skill that researches a topic and adds pages to a wiki. It runs on requests such as research <topic> or instructions to grow a wiki automatically. CX Codex +1 ★ 2,966repo stars survey-generator survey-generator generates structured literature surveys on AI/ML topics. Output is a wiki page in markdown with bibliography, not a one-off HTML file. CX Codex +1 ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open