Agent skill

Skill Router

by sickn33 in sickn33/agentic-awesome-skills

A skill your agent uses when the user is unsure which skill to use or where to start.

MITAuto-check passed

Install Skill Router

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill skill-router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills skill-router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-router .claude/skills/skill-router && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-router
GitHub stars
47k
Used in
2 other repos
Token cost
~2.1k tokens
SKILL.md length
907 words
Files
1
Skills in repo
1,493
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user is unsure which skill to use or where to start.

  • Works in 4 steps: Acknowledge and open the interview → Ask the Funnel Questions (one at a time,… → Recommend skills → …
  • The user is unsure which skill to use
  • SKILL.md covers When to Use, Goal, Instructions and Example Interaction, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Router is an agent skill from sickn33/agentic-awesome-skills. Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

When your agent uses it

  • The user is unsure which skill to use

Example prompts

  • “/skill-router”

Requirements

  • Node.js
  • Docker

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Acknowledge and open the interview
  2. Ask the Funnel Questions (one at a time, in order)
  3. Recommend skills
  4. Offer a ready-made prompt

What it can do on your machine

Read from SKILL.md and the folder at commit 680176d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Router loads about 2.1k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 907 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit 680176d, republished under its MIT licence (© sickn33). 907 words, ~2,142 tokens.

Download SKILL.mdSave it as .claude/skills/skill-router/SKILL.md (or your agent's skills folder).
name
skill-router
description
Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.
risk
safe
source
self
date_added
2026-09-04

Skill Router

When to Use

Use this skill when:

  • The user says "I don't know where to start" or "which skill should I use"
  • The user has a vague goal without a clear method
  • The user asks "what should I use for..." or "I'm not sure how to approach this"
  • The user is new to the skill library and needs guidance

Goal

Help users who are unsure of what they want to do or which skill to use. Interview them with a short structured conversation, then recommend the most relevant skill(s) from the installed library — with a clear explanation of why each skill fits and exactly how to invoke it.


Instructions

Step 1 — Acknowledge and open the interview

Respond warmly and tell the user you'll ask a few quick questions to find the right skill for them. Do NOT suggest any skills yet.

Example opener:

"No problem — let me ask you a few quick questions so I can point you to exactly the right skill."


Step 2 — Ask the Funnel Questions (one at a time, in order)

Ask only what you need. If an earlier answer makes a later question irrelevant, skip it.

Q1 — What is the broad area of the task? Present these as numbered options:

  1. Building / coding something (app, feature, component, script)
  2. Fixing or debugging something that's broken
  3. Security, pentesting, or vulnerability assessment
  4. AI agents, LLMs, or automation pipelines
  5. Marketing, SEO, content, or growth
  6. DevOps, infrastructure, deployment, or git
  7. Design, UI/UX, or creative output
  8. Planning, strategy, or documentation
  9. Something else (ask them to describe it)

Q2 — How specific is the task?

  1. I have a clear spec / I know exactly what I want built
  2. I have a rough idea but need help shaping it
  3. I'm totally starting from scratch with no clear direction

Q3 — What tech stack or domain is involved? (only ask if relevant) Examples: React / Next.js, Node.js, Python, AWS, Stripe, AI/LLM, no-code, etc. If they say "not sure" or "any", that's fine — move on.

Q4 — Do you want to work autonomously (agent does everything) or collaboratively (you stay in the loop)?

  1. Fully autonomous — just go
  2. Collaborative — I want to review/approve steps
  3. Not sure yet

Step 3 — Recommend skills

Based on their answers, recommend 1 primary skill and up to 2 secondary skills. Structure your recommendation exactly like this:

✅ Primary Skill: @skill-name Why: [1–2 sentences explaining why this is the best fit for what they described] Invoke it like this:

@skill-name [paste their goal here]

🔁 Also consider:

  • @skill-name-2 — [one sentence on when to layer this in]
  • @skill-name-3 — [one sentence on when to layer this in]

Step 4 — Offer a ready-made prompt

After the recommendation, offer to write them a ready-to-use prompt they can paste directly into Antigravity. Ask:

"Want me to write the full prompt for you so you can just paste it in?"

If yes, compose a complete, specific prompt using the recommended skill and everything you learned about their goal from the interview.


Example Interaction

User: @skill-router I want to build something but I'm not sure where to start

Agent: No problem — let me ask a few quick questions.
       What is the broad area?
       (1) Building  (2) Debugging  (3) Security  (4) AI/LLM
       (5) Marketing  (6) DevOps  (7) Design  (8) Planning

User: 1 - building something

Agent: How specific is the task?
       (1) Clear spec  (2) Rough idea  (3) Starting from scratch

User: 2 - rough idea

Agent: What tech stack? (React, Node, Python, etc. — or "not sure")

User: Next.js

Agent: ✅ Primary Skill: @brainstorming
       Why: You have a rough idea that needs shaping before building.
       Brainstorming asks structured questions and produces a clear spec.

       @brainstorming help me design a [your app idea] using Next.js

       🔁 Also consider:
       - @plan-writing — once brainstorming produces a spec, break it into tasks
       - @senior-fullstack — when you are ready to start building

       Want me to write the full prompt for you?

Skill Routing Reference

Building a full product or app from scratch
  • Primary: @app-builder
  • If they want to plan first: @brainstorming → @plan-writing → @app-builder
  • If they want it fully autonomous: @loki-mode
Building a specific frontend feature / UI
  • Primary: @senior-fullstack or @frontend-design
  • Stack-specific: @react-patterns, @nextjs-best-practices, @tailwind-patterns
  • If they want a full design system: @ui-ux-pro-max + @core-components
Show full SKILL.md (356 more words)Show less
Building a backend API or service
  • Primary: @backend-dev-guidelines
  • Stack-specific: @nodejs-best-practices, @python-patterns, @nestjs-expert
  • API design: @api-patterns
  • Database: @database-design + @prisma-expert
Debugging something broken
  • Primary: @systematic-debugging
  • If tests are failing: @test-fixing
  • If it's a code quality issue: @clean-code
Writing tests / TDD
  • Primary: @tdd
  • For Playwright/browser tests: @playwright-skill
  • For Jest patterns: @testing-patterns
Integrating a third-party service
  • Payments: @stripe-integration
  • Auth: @clerk-auth or @nextjs-supabase-auth
  • Database: @neon-postgres or @firebase
  • Messaging: @twilio-communications
  • Bots: @slack-bot-builder, @discord-bot-architect, @telegram-bot-builder
  • File storage: @file-uploads
  • Analytics: @analytics-tracking
AI / LLM / agents
  • Architecture: @ai-agents-architect
  • RAG pipelines: @rag-engineer
  • Prompts: @prompt-engineer
  • Multi-agent: @langgraph or @crewai
  • Observability: @langfuse
  • Voice: @voice-agents
Security / pentesting
  • Start here: @ethical-hacking-methodology + @pentest-checklist
  • Web app testing: @burp-suite-testing, @sql-injection-testing, @xss-html-injection
  • Network/infra: @aws-penetration-testing, @linux-privilege-escalation
  • Reference: @top-web-vulnerabilities
DevOps / infrastructure / deployment
  • Docker: @docker-expert
  • Cloud: @aws-serverless, @gcp-cloud-run, @vercel-deployment
  • Git workflow: @git-pushing, @using-git-worktrees, @github-workflow-automation
  • Scripting: @linux-shell-scripting
Marketing / growth / SEO
  • Copy: @copywriting
  • Landing pages: @page-cro
  • SEO: @seo-fundamentals + @seo-audit
  • Email: @email-sequence
  • Ads: @paid-ads
  • Launch: @launch-strategy
Planning / architecture / strategy
  • Quick plan: @concise-planning
  • Full plan: @plan-writing → @executing-plans
  • Architecture: @software-architecture or @senior-architect
  • Product strategy: @product-manager-toolkit
Creative / design / visuals
  • UI: @frontend-design
  • Data viz: @claude-d3js-skill
  • Generative art: @algorithmic-art
  • Presentations: @pptx-official
Fully autonomous / parallel execution
  • Full startup mode: @loki-mode
  • Independent parallel tasks: @dispatching-parallel-agents
  • Plan then execute: @subagent-driven-development
Document creation
  • Word doc: @docx-official
  • PDF: @pdf-official
  • Spreadsheet: @xlsx-official
  • Presentation: @pptx-official

Constraints

  • Never recommend more than 1 primary skill and 2 secondary skills at a time.
  • Always include the exact @invoke syntax so users can copy-paste it.
  • If the user's goal spans multiple categories, pick the most upstream skill (e.g. @brainstorming before @senior-fullstack).
  • Do not overwhelm the user with the full skill list. Recommend only what is relevant to their specific answers.
  • If the user is totally lost, default to @brainstorming for open-ended goals, or @app-builder for anything involving building something.
  • After recommending, always offer to write a ready-made prompt for them.

Limitations

  • Only recommends skills from the installed library. If a skill is not installed, the recommendation may not work.
  • Routing is based on natural language matching. Highly ambiguous goals may require follow-up clarification.
  • Does not execute the recommended skill — it only recommends it. The user must invoke the skill themselves.
  • The routing reference covers the most common skills but does not include every skill in the library.

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skill-router of sickn33/agentic-awesome-skills.

Open the folder on GitHubat commit 680176d

Used in 2 other repositories

We found 11 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Skill Router next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Router this skillsickn33/agentic-awesome-skills47k2 repos~2.1kAutomated safety check: PassMIT
Router Onweave-os/router5.6k—~169Automated safety check: PassApache-2.0
Router Offweave-os/router5.6k—~183Automated safety check: PassApache-2.0
Acp Routeropenclaw/openclaw392k—~2.4kAutomated safety check: PassMIT
React Router Developmentremix-run/react-router57k1 repos~1.5kAutomated safety check: PassMIT
Server TRPC Router Guidelobehub/lobehub83k—~904Automated safety check: PassCustom licence

Similar skills

  • Router On

    weave-os/router

    Route Codex through the Weave Router again (turn it back on).

    5.6k GitHub stars~169 tokensUpdated today
    Auto-check passed
  • Router Off

    weave-os/router

    Route Codex to its default provider again (turn the Weave Router off).

    5.6k GitHub stars~183 tokensUpdated today
    Auto-check passed
  • Acp Router

    openclaw/openclaw

    Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either…

    392k GitHub stars~2.4k tokensUpdated today
    Writing & ContentAuto-check passed
  • React Router Development

    remix-run/react-router

    Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.

    57k GitHub starsUsed in 1 repo~1.5k tokens
    Frontend & DesignAuto-check passed
  • Conventions for LobeHub's server tRPC routers: file locations, middleware that injects models into ctx, procedure patterns, aggregated detail endpoints and return shapes.

    83k GitHub stars~904 tokensUpdated today
    Backend & APIsAuto-check passed
  • Router Act

    vercel/next.js

    Official

    How to write end-to-end tests using createRouterAct and LinkAccordion.

    143k GitHub stars~3.1k tokensUpdated today
    Testing & QAAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,493 skills in this repo
  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed
  • Whatsapp Cloud API

    sickn33/agentic-awesome-skills

    Integracao com WhatsApp Business Cloud API (Meta). An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.5k tokens
    Auto-check passed
  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Questions about Skill Router

What does Skill Router do?

A skill your agent uses when the user is unsure which skill to use or where to start. Skill Router is an agent skill from sickn33/agentic-awesome-skills. Use when the user is unsure which skill to use or where to start.

When should I use Skill Router?

Skill Router fits situations like: the user is unsure which skill to use.

How do I install Skill Router in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill skill-router -a claude-code`. Or copy the skill folder (skills/skill-router in sickn33/agentic-awesome-skills) into .claude/skills/skill-router in your project. Claude Code loads it when a task matches its description.

How do I install Skill Router in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill skill-router -a codex`. Or copy the skill folder (skills/skill-router in sickn33/agentic-awesome-skills) into .agents/skills/skill-router in your project. Codex loads it when a task matches its description.

Can I use Skill Router in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill skill-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-router, .gemini/skills/skill-router, .github/skills/skill-router and .opencode/skills/skill-router in your project.

What does Skill Router need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Router is instructions for the agent only. Our summary lists: Node.js; Docker.

Does Skill Router access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Router safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Router use?

Skill Router is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Router use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Router?

Skills that share tags, products or a category with Skill Router: Router On (weave-os/router, 5.6k stars), Router Off (weave-os/router, 5.6k stars), Acp Router (openclaw/openclaw, 392k stars) and React Router Development (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Router?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,379 GitHub stars. The repository holds 1,493 skills in this directory. The repository was last updated on October 9, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.