From reasoning-services
Select the right reasoning tool or chain multiple tools together. Use when deciding between structured reflection, decision matrix, context switcher, or sequential thinking.
npx claudepluginhub reasoning-services/marketplaceThis skill uses the workspace's default tool permissions.
These tools run reasoning in isolated sessions — separate from your main conversation context. This prevents self-reinforcing patterns and context pollution.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
These tools run reasoning in isolated sessions — separate from your main conversation context. This prevents self-reinforcing patterns and context pollution.
Structured Reflection — Use when thinking feels muddy, you're stuck on a problem, or you need to work through complex logic. Articulating to an external session forces clarity.
Decision Matrix — Use when multiple viable options exist with meaningful trade-offs and you need systematic comparison against weighted criteria. Produces structured scoring.
Context Switcher — Use when a decision affects multiple stakeholders or teams, when designing APIs or interfaces, or when you need to surface blind spots from different roles. Runs parallel perspectives.
Sequential Thinking — Use when a problem needs step-by-step linear reasoning with explicit confidence tracking, dependency mapping, and contradiction detection.
For complex decisions, chain tools in sequence:
The synthesis happens in the user's head, not in a self-reinforcing loop. Each tool returns structured output — decisions, scores, concerns, alternatives — back to the main conversation without polluting it with thousands of tokens of internal reasoning.