Awesome-omni-skills skill-router

Skill Router workflow skill. Use this skill when the user needs 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 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

install

source · Clone the upstream repo

git clone https://github.com/diegosouzapw/awesome-omni-skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/skill-router" ~/.claude/skills/diegosouzapw-awesome-omni-skills-skill-router && rm -rf "$T"

manifest: skills/skill-router/SKILL.md

Skill Router

Overview

This public intake copy packages

plugins/antigravity-awesome-skills-claude/skills/skill-router

from

https://github.com/sickn33/antigravity-awesome-skills

into the native Omni Skills editorial shape without hiding its origin.

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses

metadata.json

plus

ORIGIN.md

as the provenance anchor for review.

Skill Router

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Goal, Constraints, Limitations.

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

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
Use when the request clearly matches the imported source intent: 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.
Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.

Operating Table

Situation	Start here	Why it matters
First-time use	`metadata.json`	Confirms repository, branch, commit, and imported path before touching the copied workflow
Provenance review	`ORIGIN.md`	Gives reviewers a plain-language audit trail for the imported source
Workflow execution	`SKILL.md`	Starts with the smallest copied file that materially changes execution
Supporting context	`SKILL.md`	Adds the next most relevant copied source file without loading the entire package
Handoff decision	`## Related Skills`	Helps the operator switch to a stronger native skill when the task drifts

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

Building / coding something (app, feature, component, script)
Fixing or debugging something that's broken
Security, pentesting, or vulnerability assessment
AI agents, LLMs, or automation pipelines
Marketing, SEO, content, or growth
DevOps, infrastructure, deployment, or git
Design, UI/UX, or creative output

Imported Workflow Notes

Imported: 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:

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

Q2 — How specific is the task?

I have a clear spec / I know exactly what I want built
I have a rough idea but need help shaping it
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)?

Fully autonomous — just go
Collaborative — I want to review/approve steps
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.

Imported: 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.

Examples

Example 1: Ask for the upstream workflow directly

Use @skill-router to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @skill-router against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @skill-router for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @skill-router using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Imported Usage Notes

Imported: 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?

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
Treat generated examples as scaffolding; adapt them to the concrete task before execution.
Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in

plugins/antigravity-awesome-skills-claude/skills/skill-router

, fails to mention provenance, or does not use any copied source files at all. Solution: Re-open

metadata.json

ORIGIN.md

, and the most relevant copied upstream files. Load only the files that materially change the answer, then restate the provenance before continuing.

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated

SKILL.md

, but they cannot quickly tell which references, examples, or scripts matter for the current task. Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Related Skills

```
@server-management
```
- Use when the work is better handled by that native specialization after this imported skill establishes context.
```
@service-mesh-expert
```
- Use when the work is better handled by that native specialization after this imported skill establishes context.
```
@service-mesh-observability
```
- Use when the work is better handled by that native specialization after this imported skill establishes context.
```
@sexual-health-analyzer
```
- Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

Resource family	What it gives the reviewer	Example path
`references`	copied reference notes, guides, or background material from upstream	`references/n/a`
`examples`	worked examples or reusable prompts copied from upstream	`examples/n/a`
`scripts`	upstream helper scripts that change execution or validation	`scripts/n/a`
`agents`	routing or delegation notes that are genuinely part of the imported package	`agents/n/a`
`assets`	supporting assets or schemas copied from the source package	`assets/n/a`

Imported Reference Notes

Imported: 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
```

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
```

Imported: 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.

Imported: 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.