research-idea-validator
Research Idea Validator
Turn a rough research idea into a decision: pursue, revise, park, or kill. This skill is for early project steering before implementation and heavy experiments.
Use this skill when:
- the user has a research idea and wants to know whether it is worth doing
- a project direction needs a go/no-go decision
- novelty, feasibility, evaluation, or reviewer risk is unclear
- the user is choosing between multiple ideas
- the user wants to prepare an advisor pitch or project proposal
- early results suggest the project may need repositioning
Do not treat this as generic brainstorming. The goal is to decide whether an idea can become a researchable project and publishable paper.
Pair this skill with:
research-project-memorywhen the decision should persist into a project-level claim, risk, action, or decision boardliterature-review-sprintwhen closest work or novelty risk is unclear
More from a-green-hand-jack/ml-research-skills
project-init
Initialize an ML research project control root. Use for paper/code/slides repos, shared memory, GitHub Project alignment, agent guidance, worktree policy, and lifecycle handoffs.
39init-python-project
Initialize or enhance a Python/ML project. Use for new repos or forks needing production structure, uv environment setup, and research evidence docs.
37new-workspace
Create Git branches or worktrees for research code and paper versions. Use for experiments, baselines, rebuttal fixes, arXiv/camera-ready branches, and worktree memory.
36project-sync
Sync verified code-side experiment results into paper memory. Use when logs, reports, run docs, or user-confirmed metrics should become paper-facing evidence.
36init-latex-project
Initialize a LaTeX academic paper project. Use for new conference or journal papers needing templates, macros, venue preambles, and writing guidance.
36add-git-tag
Create annotated Git milestone tags. Use when completing a phase, releasing a version, or marking a research checkpoint.
36