Deep Logical Reasoning Expert
Paste the following prompt into your AI chat to install this skill:
Install @user_1e593ee7/77 using https://skillhub.cn/install/skillhub.md.
About this skill
Problem to Solve
In complex solution reviews, incident triage, and multi-constraint decisions, jumping straight to a conclusion can miss assumptions and edge cases. This skill makes reasoning explicit: it first separates goals, constraints, and key variables, then builds a step-by-step chain of reasoning.
How It Works
- Problem decomposition: identify the core objective, boundary conditions, and critical variables to create a checkable analysis.
- Logic chain construction: present inference step by step, with each step grounded in evidence or stated assumptions.
- Hypothesis validation: test the chain from different angles, flag contradictions, and request missing facts when needed.
- Structured output: return a
reasoning processfollowed by afinal conclusion, which makes the result easier to audit.
Fit and Limits
It works well for logical deduction, solution validation, and problem breakdown, but it is not a substitute for authoritative data sources. If key facts are missing, it should ask follow-up questions; if the task depends on real-time external information, separate retrieval is required.
Use Cases
- Compare options by constraints, risks, and dependencies.
- Split symptoms, logs, and hypotheses; verify root cause.
- Extract delivery and acceptance constraints into a checklist.
- Separate goals, users, and boundaries before prioritizing.
Best For
- Software engineers in architecture reviews who need to compare constraints, risks, and dependencies step by step.
- Support engineers handling incidents who need to separate facts, hypotheses, and root cause.
- Solution consultants drafting proposals who need to validate scope, acceptance terms, and dependencies.
- Product managers running requirement reviews who need to split goals, scenarios, and boundaries.
Related Skills
Automatically searches job postings based on the user profile, AI-scores fit, saves desktop reports, and sends email updates with scheduled tracking.
Activates bionic reasoning for causal judgment, numerical prediction, and hypothesis validation, using hypothesis-driven checks, Bayesian updates, falsifiability tests, bias defense, and physical constraints.
Triggered by /plan, it asks the agent to output a plan, risks, impact scope, and validation approach before execution.
Track and clean agent session files, packages, and Skills via trash-first safety.