snowflake-ai-research/arcticswarm/deep-reasoning
Claude Code and agent skill by snowflake-ai-research/arcticswarm
- community
Checking that the SKILL.md file is still in the repository.
Deep chain-of-thought analysis workflow using the reasoning tool. Covers when to use reasoning, how to provide context, verifying findings, and producing well-supported conclusions.
Install
npx vskill@latest install snowflake-ai-research/arcticswarm/deep-reasoningSKILL.md
The same SKILL.md was published earlier as majiayu000/claude-skill-registry-data/deep-reasoning.
Deep Reasoning Skill
Mission
Use the reasoning tool for deep chain-of-thought analysis to solve complex problems, verify findings, and produce well-reasoned conclusions.
When to Use the Reasoning Tool
Always use the reasoning tool for:
- Complex multi-step logical analysis.
- Verifying correctness of findings or data.
- Resolving contradictions between different data sources.
- Hard math, logic puzzles, or constraint satisfaction.
- Synthesising multiple pieces of evidence into a final answer.
- Checking for hidden assumptions or overlooked edge cases.
How to Use It
When calling reasoning, provide:
- The full, unchanged text of the original question.
- All relevant findings and evidence collected so far.
- Specific concerns or aspects to investigate.
- An explicit request to check for mistakes and hidden assumptions.
Workflow
- Gather context — review all available findings and data before
reasoning. Your reasoning is only as good as the information you feed into it.
- Reason deeply — use the
reasoningtool to:
- Analyse the problem step by step.
- Identify hidden assumptions, logical gaps, or potential errors.
- Cross-check findings from multiple sources.
- Synthesise information into a coherent conclusion.
- Verify numerical calculations and logical chains.
- Report conclusions — include your reasoning chain, evidence
supporting your conclusion, confidence level, and any issues found.
Output Format
Always include:
- Conclusion: Your reasoned conclusion.
- Reasoning summary: Brief summary of the reasoning chain.
- Confidence: How confident you are (high / medium / low).
- Issues: Any problems or concerns identified.
Rules
- Always use the
reasoningtool for substantive analysis — do not
try to reason through complex problems in plain text.
- Provide actionable conclusions — not just "this might be wrong" but
"this is wrong because X, and the correct answer is Y."
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingarcticswarm/skills/deep-reasoning/SKILL.md
Popularity
- Repository stars
- 13
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/snowflake-ai-research/arcticswarm/deep-reasoning)