problem-solver
Systematic analytical frameworks for diagnosing root causes, evaluating options, and solving complex technical or operational problems.
Best use case
problem-solver is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Systematic analytical frameworks for diagnosing root causes, evaluating options, and solving complex technical or operational problems.
Teams using problem-solver should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
How problem-solver Compares
| Feature / Agent | problem-solver | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Systematic analytical frameworks for diagnosing root causes, evaluating options, and solving complex technical or operational problems.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Problem-Solving Skill Structured frameworks for diagnosis and solution evaluation. Read the reference file for whichever framework you select. ## Framework Selection | Problem Signal | Framework | Reference | |---|---|---| | Unknown root cause, simple chain | Five Whys | `references/five-whys.md` | | Conflicting requirements / trade-offs | TRIZ | `references/triz.md` | | Slow throughput / capacity issue | Theory of Constraints | `references/theory-of-constraints.md` | | Recurring / interconnected issues | Systems Thinking | `references/systems-thinking.md` | | Multi-factor quality issue | Ishikawa / Fishbone | `references/ishikawa.md` | | Critical incident, high stakes | Root Cause Analysis | `references/root-cause-analysis.md` | | Comparing multiple solutions | Solution Evaluation Matrix | `references/solution-matrix.md` | **Escalation path**: Start simple (Five Whys) → escalate to Ishikawa or full RCA if multiple factors emerge → finish with Solution Matrix when comparing options. ## Workflow 1. **Describe symptoms** — What, when, where, impact, what's NOT affected? 2. **Define boundaries** — Scope, recent changes, constraints, stakeholders 3. **Diagnose** — Pick framework from table above, read its reference, apply it 4. **Generate solutions** — 3-5 distinct options addressing root causes 5. **Evaluate** — Use Solution Matrix (read `references/solution-matrix.md`) to score options 6. **Plan implementation** — Actions, owners, timeline, risks, success metrics 7. **Monitor** — Track metrics, iterate if unresolved ## Diagnostic Questions 1. Symptom or root cause? 2. What changed before the problem appeared? 3. Can I reproduce it reliably? 4. Are there multiple root causes? 5. What feedback loops are at play? 6. Where is the bottleneck? 7. What's the technical contradiction? ## Anti-Patterns - Jumping to solutions before diagnosis - Treating symptoms instead of root causes - Choosing solutions by ease alone - Ignoring feedback loops - Not monitoring after implementation
Related Skills
Molt-Solver 🧩
自动解决 Moltbook 验证码难题的专家。
Error Resolver
Systematic error diagnosis and resolution using first-principle analysis. Use when encountering any error message, stack trace, or unexpected behavior. Supports replay functionality to record and reuse solutions.
scientific-problem-selection
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
github-issue-resolver
Autonomous GitHub Issue Resolver Agent with guardrails. Use when the user wants to discover, analyze, and fix open issues in GitHub repositories. Triggers on requests like "fix GitHub issues", "resolve issues in repo", "work on GitHub bugs", or when the user provides a GitHub repository URL and asks for issue resolution. Supports the full workflow from issue discovery to PR submission with safety guardrails preventing scope creep, unauthorized access, and dangerous operations.
priority-conflict-resolver
面对多个目标、有限资源与冲突时，输出排序、牺牲说明、边界与不做清单。；use for priority, tradeoff, planning workflows；do not use for 替代人事绩效决策, 伪造资源承诺.
solver
How the Faebryk parameter solver works (Sets/Literals, Parameters, Expressions), the core invariants enforced during mutation, and practical workflows for debugging and extending the solver. Use when implementing or modifying constraint solving, parameter bounds, or debugging expression simplification.
problem-statement
Write a user-centered problem statement with who is blocked, what they are trying to do, why it matters, and how it feels. Use when framing discovery, prioritization, or a PRD.
problem-framing-canvas
Guide teams through MITRE's Problem Framing Canvas. Use when you need a clearer problem statement before jumping to solutions.
graphql-resolver-creator
Graphql Resolver Creator - Auto-activating skill for Backend Development. Triggers on: graphql resolver creator, graphql resolver creator Part of the Backend Development skill category.
scientific-problem-selection
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
nonlinear-solvers
Select and configure nonlinear solvers for f(x)=0 or min F(x). Use for Newton methods, quasi-Newton (BFGS, L-BFGS), Broyden, Anderson acceleration, diagnosing convergence issues, choosing line search vs trust region, and analyzing Jacobian quality.
linear-solvers
Select and configure linear solvers for systems Ax=b in dense and sparse problems. Use when choosing direct vs iterative methods, diagnosing convergence issues, estimating conditioning, selecting preconditioners, or debugging stagnation in GMRES/CG/BiCGSTAB.