$npx -y skills add HoangTheQuyen/think-better --skill problem-solving-proSystematic problem-solving toolkit: root cause analysis, hypothesis testing, debugging strategies, critical thinking frameworks. Use when user says "solve", "analyze", "diagnose", "debug", "figure out", "what's wrong", "root cause", "why is this happening", "I'm stuck", "break do
| 1 | # Goal |
| 2 | |
| 3 | Help users solve complex problems systematically using proven frameworks — turning vague issues into structured analyses with actionable recommendations. |
| 4 | |
| 5 | # problem-solving-pro |
| 6 | |
| 7 | Comprehensive structured problem-solving framework for tackling any complex challenge. Contains a 7-step methodology, 15 decomposition frameworks, 8 prioritization techniques, 12 analysis tools, 12 cognitive biases with debiasing strategies, 10 communication patterns, 12 mental models, and 10 team dynamics patterns. Searchable database with reasoning-based recommendations that adapts to your specific problem type. |
| 8 | |
| 9 | ## Prerequisites |
| 10 | |
| 11 | **IMPORTANT: Detect the correct Python command first.** Some systems use `python3`, others use `python`. Run: |
| 12 | |
| 13 | ```bash |
| 14 | python3 --version 2>/dev/null || python --version |
| 15 | ``` |
| 16 | |
| 17 | Use whichever command succeeds (`python3` or `python`) for ALL script calls below. If the system only has `python` (common on Windows), substitute `python` everywhere you see `python3` in this document. |
| 18 | |
| 19 | If Python is not installed at all, install it based on user's OS: |
| 20 | |
| 21 | **macOS:** |
| 22 | ```bash |
| 23 | brew install python3 |
| 24 | ``` |
| 25 | |
| 26 | **Ubuntu/Debian:** |
| 27 | ```bash |
| 28 | sudo apt update && sudo apt install python3 |
| 29 | ``` |
| 30 | |
| 31 | **Windows:** |
| 32 | ```powershell |
| 33 | winget install Python.Python.3.12 |
| 34 | ``` |
| 35 | |
| 36 | > **Note:** On Windows, Python 3 is typically available as `python` (not `python3`). |
| 37 | |
| 38 | --- |
| 39 | |
| 40 | ## How to Use This Workflow |
| 41 | |
| 42 | When user requests problem-solving help (analyze, solve, diagnose, decide, structure, decompose, plan, strategy, recommendation), follow this workflow: |
| 43 | |
| 44 | ### Step 1: Understand the Problem |
| 45 | |
| 46 | Extract key information from user's problem description: |
| 47 | - **Problem type**: Business performance, market entry, organizational change, product, cost reduction, innovation, crisis, data/analytics, partnership/M&A, policy |
| 48 | - **Complexity**: Well-structured, ill-structured, wicked |
| 49 | - **Keywords**: revenue, growth, decline, entry, change, innovation, cost, crisis, etc. |
| 50 | - **Context**: Industry, scale, time pressure, stakeholder dynamics |
| 51 | |
| 52 | ### Step 2: Generate Problem-Solving Plan (REQUIRED) |
| 53 | |
| 54 | **Always start with `--plan`** to get comprehensive recommendations with reasoning: |
| 55 | |
| 56 | ```bash |
| 57 | python3 scripts/search.py "<problem_description>" --plan [-p "Project Name"] |
| 58 | ``` |
| 59 | |
| 60 | This command: |
| 61 | 1. Classifies the problem type automatically |
| 62 | 2. Searches across all 9 knowledge domains in parallel |
| 63 | 3. Applies reasoning rules to select best frameworks and tools |
| 64 | 4. Returns a complete solving plan: methodology, decomposition, analysis, communication, mental models, bias warnings |
| 65 | 5. Includes anti-patterns to avoid and a problem-solving checklist |
| 66 | |
| 67 | **Example:** |
| 68 | ```bash |
| 69 | python3 scripts/search.py "revenue declining 20% despite market growth" --plan -p "Revenue Recovery" |
| 70 | ``` |
| 71 | |
| 72 | ### Step 2b: Persist Problem-Solving Plan |
| 73 | |
| 74 | To save the plan for reference: |
| 75 | |
| 76 | ```bash |
| 77 | python3 scripts/search.py "<problem>" --plan --persist -p "Project Name" |
| 78 | ``` |
| 79 | |
| 80 | This creates: |
| 81 | - `solving-plans/project-name/PLAN.md` — Complete problem-solving plan |
| 82 | |
| 83 | ### Step 3: Deep-Dive Domain Searches |
| 84 | |
| 85 | Use when the plan's recommendation needs more detail, OR when user asks about a specific topic (e.g., "how do I do a root cause analysis?"): |
| 86 | |
| 87 | ```bash |
| 88 | python3 scripts/search.py "<keyword>" --domain <domain> [-n <max_results>] |
| 89 | ``` |
| 90 | |
| 91 | **When to use domain searches:** |
| 92 | |
| 93 | | Need | Domain | Example | |
| 94 | |------|--------|---------| |
| 95 | | Understand the methodology steps | `steps` | `--domain steps "define problem"` | |
| 96 | | Classify the problem | `problem-types` | `--domain problem-types "wicked systemic"` | |
| 97 | | Choose decomposition framework | `decomposition` | `--domain decomposition "MECE logic tree"` | |
| 98 | | Pick prioritization technique | `prioritization` | `--domain prioritization "impact feasibility"` | |
| 99 | | Select analysis tools | `analysis` | `--domain analysis "root cause benchmark"` | |
| 100 | | Identify cognitive biases | `biases` | `--domain biases "confirmation anchoring"` | |
| 101 | | Structure communication | `communication` | `--domain communication "pyramid executive"` | |
| 102 | | Apply mental models | `heuristics` | `--domain heuristics "first principles inversion"` | |
| 103 | | Improve team dynamics | `team` | `--domain team "red team brainstorm"` | |
| 104 | |
| 105 | ### Step 4: Apply the Framework |
| 106 | |
| 107 | Guide the user through the recommended process: |
| 108 | |
| 109 | 1. **Define**: Help craft a precise problem statement |
| 110 | 2. **Decompose**: Build the recommended logic tree (MECE) |
| 111 | 3. **Prioritize**: Apply 80/20 to focus on what matters |
| 112 | 4. **Plan**: Design specific analyses for priority issues |
| 113 | 5. **Analyze**: Guide data gather |