Menu
Skills in this repository
SkillsMP has collected 655 skills from benjam3n/reasoningtool. Open a skill to review its source and details.
benjam3n/reasoningtoolShowing 40 of 655 collected skills.
Systematic diagnosis of WHY something is happening (or not happening). Forces generation of multiple candidate explanations before evaluation, separates symptoms from causes, and distinguishes proximate from root cause. Works across domains: code, systems,…
Decompose system functions into subfunctions, define functional interfaces, allocate functions to physical components, and trace functions to requirements. Produces a functional decomposition tree and allocation matrix.
Ensure system design accounts for human capabilities, limitations, and needs across all user populations. Addresses human factors, training, staffing, and accessibility.
Define and document all interfaces between system components, subsystems, and external systems. Produces a structured Interface Control Document (ICD) with protocols, data formats, timing, and error handling.
Estimate total cost of ownership across the full system lifecycle. Covers development, production, operations, support, and disposal phases with sensitivity analysis and alternative comparison.
Map any question to the nearest node in the 438-question graph, show connected questions by route type, and suggest reasoning skills that match.
Analyze and specify system reliability, availability, and maintainability characteristics. Models failure behavior, predicts system performance, and identifies improvement opportunities.
Systematically discover, categorize, and specify all requirements for a project or system. Surfaces hidden requirements, resolves conflicts, and produces a structured specification.
Identify, assess, mitigate, and monitor risks throughout the system lifecycle. Produces a risk register, risk matrix, and risk mitigation plan with triggers and contingencies.
Plan and manage the overall SE process for a project. The meta-skill that orchestrates all other SE skills — selects lifecycle model, tailors processes, defines reviews, and creates the SE Management Plan (SEMP).
Analyze and design systems composed of independently operated constituent systems. Identifies emergent behaviors, interdependencies, governance models, and integration strategies.
Systematic procedure for selecting appropriate statistical tests and correctly interpreting results
Systematically identify all stakeholders, map their interests, influence, and requirements, detect conflicts between stakeholder needs, and define engagement strategies. Produces a stakeholder registry and influence map.
Design system architecture from requirements by decomposing into subsystems, defining interfaces, evaluating candidate architectures against quality attributes, and documenting architectural views (functional, physical, behavioral).
Break a complex system into manageable subsystems and components using structured decomposition. Defines component responsibilities, interactions, and validates completeness of the breakdown.
Plan and execute the integration of subsystems into a working whole. Produces an integration plan with strategy selection, dependency analysis, integration sequence, test cases, and issue tracking.
Design comprehensive test strategy and plans for system verification and validation. Defines test levels, types, cases, environments, and criteria to ensure thorough coverage.
Define and track key technical metrics that indicate whether the system is on track to meet requirements. Sets planned profiles, tolerance bands, measurement methods, and escalation thresholds.
Create and maintain bidirectional traceability from stakeholder needs through requirements to design, implementation, and test. Identifies orphan requirements, gold-plating, and coverage gaps.
Plan and execute verification (built right?) and validation (built the right thing?) activities. Produces a V&V plan with requirements traceability matrix, test cases, and acceptance criteria.
Surface and rigorously test a field's hidden assumptions. Compound skill that chains extraction, inversion, research, ARAW testing, cross-domain perspective, and synthesis into a complete audit.
The After Action Review (AAR) is a structured debrief to learn from experience.
Procedure for using AI to analyze biomedical research, evaluate studies, assess drug interactions, and interpret clinical data.
Design a valid experiment with a clear hypothesis, proper controls, sufficient sample size, and pre-defined decision criteria.
Create a checklist that catches what normal checklists miss. Each item includes adversarial branches -- what if this assumption is wrong? Chains assumption extraction, failure anticipation, assumption inversion, and steps generation.
Sub-orchestrator for commands and action requests. Routes to direct execution, step generation, task sequencing, or reclassifies when the command needs analysis first.
Nothing is a fact until it survives an assassination attempt. Builder constructs claims, Breaker tries to destroy them.
A premortem imagines failure has already occurred, then works backward to identify what went wrong.
Analyze and construct arguments by checking logical validity, premise truth, hidden assumptions, and evidence strength.
Invert assumptions to discover blind spots and alternative possibilities. What if the opposite were true?
Analyzes suitability for AI agents. Assesses which tasks are automatable, evaluates reliability requirements, designs human oversight, and plans for failure modes.
Convert a change stream into high-level big-change bullets, filtering out low-level modifications and grouping related changes into coherent shifts.
Choose the right level of abstraction for understanding, deciding, executing, communicating, or creating. Zoom in, zoom out, or reframe.
Explains concept X in terms of familiar concept Y by mapping structural correspondence, then testing where the analogy breaks.
Structured deep analysis after exploration. Selects what to analyze, applies frameworks, finds patterns, tests hypotheses, and synthesizes findings.
Orderings based on classic algorithm design paradigms: greedy, dynamic programming, divide-and-conquer, and branch-and-bound.
First pass at competitive programming — explicit problem decomposition, constraint identification, and straightforward implementation.
Second pass at competitive programming — find implicit patterns, hidden structure, and optimizations the explicit pass missed.
Third pass — meta-reasoning about solution correctness, confidence, and robustness. Catches what testing alone misses.
Orderings for software development — outside-in vs inside-out, API-first vs domain-first, top-down vs bottom-up.