Menu
SkillsMP has collected 25 skills from MRiabov/Problemologist-AI. Open a skill to review its source and details.
Showing 25 of 25 collected skills.
Benchmark planning and handoff authoring for Problemologist. Use when creating or revising benchmark planner artifacts (`benchmark_plan.md`, `todo.md`, `benchmark_definition.yaml`, `benchmark_assembly_definition.yaml`, `benchmark_plan_evidence_script.py`,…
Benchmark execution-review skill for validating implemented benchmarks after validation and simulation. Use when reviewing `benchmark_script.py`, `benchmark_definition.yaml`, `benchmark_assembly_definition.yaml`, `validation_results.json`,…
Benchmark implementation role for turning approved benchmark plans into benchmark_script.py and helper modules, validating and simulating benchmark revisions, preserving planner inventory exactness, handling benchmark-side motion or COTS-backed fixture…
Review benchmark planner handoffs before coding starts, with explicit attention to whether `payload_trajectory_definition.yaml` is physically satisfiable from the full plan. Use when validating `benchmark_plan.md`, `todo.md`, `benchmark_definition.yaml`,…
Problemologist engineering implementation role. Use when turning approved engineering handoffs into solution_script.py, solving engineering evals with bounded retries, selecting mechanism patterns, validating and simulating revisions, inspecting render…
Mechanical mechanism design, friction-aware passive transfer, and simulation guidance for Problemologist. Use this when solving or reviewing passive-transfer mechanisms, realistic constraints/DOFs, manufacturing-config material coefficients, stress or fluid…
Manual trigger only. Use this skill only when the user explicitly asks for `$commit-split-workflow` (or clearly requests this exact workflow) to split changes into meaningful commits with the repository's commit-message conventions. Never ask the user how to…
Engineering planning role for turning benchmark handoff context into implementation-ready plan artifacts. Use when drafting or revising `engineering_plan.md`, `todo.md`, `benchmark_definition.yaml`, `assembly_definition.yaml`,…
Canonical import and execution contract for authored benchmark and engineer scripts. Use when writing `benchmark_script.py` or `solution_script.py` that call validation, simulation, or submission helpers.
Engineer-side execution-review skill for validating the latest solution revision after validation and simulation. Use when reviewing `solution_script.py`, helper modules, `validation_results.json`, `simulation_result.json`, `scene.json`, render or video…
Engineer-side review workflow for validating plan and execution handoffs, review manifests, render and simulation evidence, exact inventory grounding, formula-backed motion and payload trajectory derivations, motion-contract plausibility, plan refusals, and…
Create or repair Problemologist eval seeds by adding role-based dataset rows plus stage-correct seeded workspace artifacts with exact deterministic fields, then verify them with minimal-scope runs through dataset/evals/run_evals.py. Use this when asked to add…
Shared render-evidence workflow for Problemologist agents. Use when previewing scenes with `render_cad(...)` for live scene inspection or `render_technical_drawing()` for drafting packages, inspecting render or video media through the runtime's…
Author and review build123d technical drawings with `TechnicalDrawing`, projected orthographic views, dimensioning, line layering, and SVG/DXF export. Use when creating or editing drawing scripts, orthographic sheets, annotations, or…
Electromechanical planning and runtime guidance for the current Problemologist electronics stack. Use only when a plan or implementation explicitly includes an `electronics` section, benchmark `electronics_requirements`, circuit validation, electronics…
Enforce fail-closed behavior by removing permissive fallbacks and fixing root causes at source, especially for planner/handover/eval validity gates.
Step-by-step workflow to identify fallback-driven regressions and replace them with strict source-level validation and fail-closed transitions.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Run, debug, and implement integration tests for RunAudit at the public boundary of the feature under test. Use when updating system integration tests or the YAML-as-checklist experiment suite.
Write or edit specification documents in `specs/` using the repository style contract in `specs/plan-style-traits.md`. Use whenever creating new spec files, revising existing specs, rewriting plan sections, or tightening wording/structure/acceptance criteria…
Local authoring syntax for motorized moving parts and future electromechanics sections. Use when editing `assembly_definition.yaml`, `final_assembly`, `moving_parts`, `AssemblyPartConfig.control`, or related motion syntax in planner and solution handoffs.
Use this skill when you need do CAD modeling using build123d. Includes builder modes, semantic selectors, and MJCF-compatible boolean strategies, and everything you need to know about build123d syntax.
Catalog-backed COTS part modeling and validation guidance for Problemologist. Use when a task involves motors, off-the-shelf parts, benchmark fixtures, or translating declared COTS components into build123d geometry and handoff artifacts.
Technical specifications, material properties, and cost models for CNC Milling and Injection Molding. Use this when the task specifies a 'max_unit_cost' or 'target_quantity', or when planning for specific manufacturing processes.
Export Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw conversation history to Hugging Face. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring DataClaw, reviewing PII/secrets in exports, or managing their…