Generate coding-test problem sets and run structured evaluations.
npx skills add https://github.com/joseph0926/study-all --skill test-joseph0926
Please help me install this Agent Skill. Skill: test Source: https://github.com/joseph0926/study-all/tree/main/.codex/skills/test Command: npx skills add https://github.com/joseph0926/study-all --skill test-joseph0926
This skill streamlines the end-to-end process of designing, publishing, and evaluating coding-test problems for skill-based learning. It helps educators and learners move from manual, error-prone test creation to a repeatable, auditable workflow that produces consistent assessment materials.
Provide a new coding-skill topic and generate a test problem set, then run a 4-axis evaluation against sample solutions.
High-intent search queries and answers about installing and using this skill.
You can automate coding-test design by providing a target skill topic to generate diverse, scenario-based problem sets aligned with specific learning levels. This replaces manual test creation with a repeatable workflow that produces consistent assessment materials.
Standardized rubric evaluation works by applying a consistent 4-axis grading framework across framing, design, implementation, and self-awareness. This structured evaluation mechanism records results over time to ensure objective, auditable assessment of coding solutions.
The best way to track progression across multiple coding skills is by maintaining per-skill profiles, problem histories, and session logs. This traceable history monitors improvement and allows you to adjust difficulty levels based on recorded results.
Yes, you can generate scenario-based coding questions tailored to specific skill levels. The automated problem generation feature creates diverse question sets aligned to target skills, satisfying requirements for structured problem files.
No, this coding-test workflow does not require external dependencies to run evaluation sessions. It operates independently to simulate evaluation sessions, apply standardized rubrics, and maintain a traceable history of results.
You should use an automated workflow instead of manual coding-test creation to eliminate error-prone processes. It streamlines the end-to-end design, publishing, and evaluation phases, moving from manual test creation to a repeatable, auditable workflow.
luuspoo-createDiagnose metacognitive risks in AI-enabled learning contexts.
badgujarkunal93-blipCalculate geometric area and volume for 2D shapes and 3D solids.
Ankh-StudioValidate AI agent rubrics and run adversarial testing with Python scripts.
techeer-svGenerate position-matched coding problems and score submissions with a 4D rubric.
