Empirical validation step for GOSM plans - adds external reality testing beyond coherence checks
Skills in this repository
benjam3n/reasoningtool - Page 10
SkillsMP has collected 655 skills from benjam3n/reasoningtool. Open a skill to review its source and details.
benjam3n/reasoningtoolShowing 40 of 655 collected skills.
Standard engineering calculation procedures for robotics and mechanical system design — forces, torques, materials, actuator sizing.
Determine whether something has been examined, built, planned, or analyzed enough — or whether more work is needed, and specifically what's missing.
Systematically develop emotional awareness, regulation, and social skill — treating EQ as a learnable competency, not a personality trait.
Evolution has optimized biological systems for billions of years. Apply evolutionary strategies to find solutions.
Expand 'etc', 'and so on', and other list tails into explicit items by inferring the continuation rule, enumerating omitted items, and stopping at a defined completeness criterion.
Systematically evaluate the ethical and moral dimensions of any decision, plan, action, or system.
Universal dimensions for evaluating any claim, problem, or solution.
Design how something connects to external systems, tools, or services. Identifies touchpoints, maps data flows, defines interfaces, assesses dependencies, plans for failures, and produces an integration checklist.
Systematically explores an unfamiliar space by mapping boundaries, identifying dimensions, sampling broadly, and flagging surprises and promising regions.
Design a structured exercise program tailored to current fitness level, goals, and real-world constraints.
Turns decisions into action. Breaks down tasks, sequences them, sets milestones, identifies the first action, and biases toward starting over perfecting the plan.
Break any problem into the easiest possible steps — no jargon, no prerequisites, no assumed knowledge. Designed for when the user is overwhelmed, new to the domain, or needs the simplest possible path forward.
Orderings that balance competing priorities, prevent starvation, and allocate resources proportionally across stakeholders.
When a project fails, systematically analyze the root cause and attribute failure correctly.
Generate filtered feedback for self-improvement loops. Only accepts well-grounded, high-leverage items to prevent error accumulation.
Test whether a factual claim is true. Assess evidence quality, check for common errors, and deliver a verdict with confidence level.
Comprehensive analysis of a field's key tensions, hidden assumptions, and blind spots. Chains assumption extraction, deep ARAW testing, cross-domain perspective, evaluation dimensions, and insight synthesis into a complete field report.
Most goal journey work focuses on SUCCESS paths. This maps the patterns of sustainable failure.
Analyze the user's just-finished action sequence, extract the repeatable pattern, clean it, name it, and convert it into a reusable procedure with trigger conditions.
Formalize a skill draft into production quality by enforcing schema completeness, overlap detection, dependency mapping, and rollout readiness.
Find the right GOSM skill for what you want to do. Describe your need in plain language and get matched to the best skill(s).
Figure Out How To - Method discovery when you know WHAT but not HOW. Systematically map the method space, test candidates, and find approaches that survive scrutiny.
Systematically understand any complex system by matching investigation depth to your goal and access level, with safeguards against premature certainty.
Determine which skills to run next (more than one), in order, with rationale, handoff prompts, and stop conditions.
Figure Out What Went Wrong - Backward causal diagnosis of failures. Trace from symptom to root cause, test each candidate cause, and derive what would prevent recurrence.
Find the right question to ask by diagnosing your actual situation and generating the most actionable question.
Reason about what's interesting, playful, or worth exploring for its own sake. Follow curiosity threads, note unexpected connections, and assess what exploration reveals.
Systematically explore what the future looks like for any trend, technology, decision, or domain across multiple timeframes.
Check whether an answer is likely wrong before acting on it. Classifies answer type and runs targeted verification.
Assess value for autonomous AI agents. Identifies tasks suitable for autonomous execution, assesses reliability requirements, evaluates error recovery needs, checks human-in-loop requirements, and projects automation potential.
An honest audit of the GOSM system's approach, claims, and limitations — applying the system's own standards to itself.
Convert gates from yes/no vibe checks into explicit, checkable claim-interfaces.
Systematically find what's missing in any system, plan, or collection. Defines intended coverage, enumerates what exists, identifies categories, checks each for coverage, flags gaps, and prioritizes by impact.
Systematic execution of GOSM gates with enforcement.
Analyze at the general level — extract principles, patterns, and transferable insights rather than situation-specific answers. Find the general rule that explains the specific case.
Reason about what's missing and why it matters by identifying intended completeness, enumerating present elements, and prioritizing gaps by impact.
Given a goal, rank relevant skills from highest to lowest expected ROI, including negative-ROI skills with reasons.
A goal journey is NOT a narrative arc. It's a CHAIN OF GOALS. Integration hub for GOSM goal processing.
Systematically identify, define, and maximize the probability of good outcomes for any situation, plan, or decision.