Routes questions to an analysis workflow to compare model perspectives and trade-offs.
Install
mkdir -p .claude/skills/ask-jmstar85 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17828" && unzip -o skill.zip -d .claude/skills/ask-jmstar85 && rm skill.zipInstalls to .claude/skills/ask-jmstar85
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Route multi-perspective questions through OMG's existing CCG-style analysis workflow. Activate when: ask, multi-model ask, ask models, compare model opinions.Key capabilities
- →Restate the user's question and the decision it supports.
- →Decide if a single answer or multi-perspective analysis is needed.
- →Route multi-perspective questions to `/ccg`.
- →Synthesize results into one recommendation.
- →Provide assumptions and confidence for recommendations.
How it works
This skill acts as a router for multi-model questions, determining if a single answer suffices or if a multi-perspective analysis via `/ccg` is beneficial. It then synthesizes the results into a recommendation.
Inputs & outputs
When to use ask
- →Comparing model opinions
- →Analyzing complex trade-offs
- →Synthesizing multi-model recommendations
About this skill
Ask
OMG adapted scope: This skill is a
/ccgrouting helper only. It does not invoke provider CLIs or wrap raw OMC ask commands.
Workflow
- Restate the user's question and the decision it supports.
- Decide whether a single answer is enough or a multi-perspective
/ccganalysis is useful. - Route to
/ccgwhen comparing model viewpoints, trade-offs, or uncertainty would materially improve the answer. - Synthesize results into one recommendation with assumptions and confidence.
Rules
- Do not fabricate responses from external providers.
- Do not run raw provider CLI commands unless the user explicitly asks and the environment supports them.
- Prefer concise synthesis over dumping multiple opinions.
When not to use it
- →When the question does not require multiple viewpoints.
- →When the environment does not support provider CLI commands.
- →When the user explicitly asks for raw provider CLI commands.
Limitations
- →Does not fabricate responses from external providers.
- →Does not run raw provider CLI commands unless explicitly asked and supported.
- →Prefers concise synthesis over dumping multiple opinions.
How it compares
This skill explicitly routes questions for multi-perspective analysis and synthesizes diverse model opinions into a single recommendation, unlike simply providing a direct answer from one source.
Compared to similar skills
ask side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ask (this skill) | 0 | 2mo | No flags | Beginner |
| council | 0 | 27d | No flags | Intermediate |
| deep-research | 35 | 8mo | Review | Advanced |
| scientific-brainstorming | 37 | 7mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jmstar85
View all by jmstar85 →You might also like
council
ZaxbyHub
>
deep-research
davidorex
Multi-agent parallel investigation for complex VCV Rack problems
scientific-brainstorming
davila7
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
nlm-skill
jacob-bd
Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.
gpt-researcher
assafelovic
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API, customizing research workflows, adding new retrievers, integrating MCP data sources, or troubleshooting research pipelines.
skill-from-github
GBSOSS
Create skills by learning from high-quality GitHub projects