Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.
安装
npx skills add K-Dense-AI/science-superpowersgh skill install K-Dense-AI/science-superpowersgit clone --depth 1 https://github.com/K-Dense-AI/science-superpowers合集内的技能
- Designing The AnalysisK-DenseUse when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model
- Dispatching Parallel InvestigationsK-DenseUse when facing 2+ independent investigations that can proceed without shared state - parallel literature survey, multi-dataset replication, or pre-specified robustness checks
- Establishing Feasibility FirstK-DenseUse when your human partner has explicitly opted into exploratory or feasibility mode - a compute-heavy simulation, an unproven pipeline, an unbenchmarked solver, an untested cluster job - or when whether the work can run at all is still unknown, when a plan's largest configuration has never been executed, when a memory or wall-clock ceiling is estimated rather than measured, or when someone…
- Executing AnalysisK-DenseUse when you have a pre-registered analysis plan to execute inline in this session with review checkpoints, on a platform without subagents
- Framing Research QuestionsK-DenseYou MUST use this before any data analysis or investigation - before exploring a dataset, loading or profiling data, running a model, computing a statistic, or testing an idea, and before any outcome data is touched
- Investigating Anomalous ResultsK-DenseUse when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
- Preregistering AnalysisK-DenseUse before running any confirmatory analysis or looking at outcome data, when testing a hypothesis, computing a p-value, or about to claim an effect - locks predictions and decision rules before results are seen
- Receiving Critical ReviewK-DenseUse when receiving critical feedback on an analysis or manuscript, before implementing suggestions, especially if feedback seems unclear or methodologically questionable - requires verification, not performative agreement or blind changes
- Reporting And Archiving FindingsK-DenseUse when an analysis is complete and verified, and you need to decide how to report it and archive the work for reproducibility
- Requesting Red Team ReviewK-DenseUse after completing an analysis or before reporting a finding, to have a skeptical reviewer attack the conclusion before you believe it
- Setting Up Reproducible AnalysisK-DenseUse when starting analysis work that needs isolation, or before executing a pre-registered plan - ensures an isolated, reproducible workspace with pinned environment, fixed seeds, and immutable raw data
- Subagent Driven AnalysisK-DenseUse when executing a pre-registered analysis plan with mostly independent steps in the current session
- Surveying Prior WorkK-DenseUse after framing a question and before designing an analysis, or when choosing a method, judging whether a result is novel, or needing a prior effect size for a power calculation
- Using Science SuperpowersK-DenseUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
- Verifying Results Before ClaimingK-DenseUse when about to claim a result, effect, significance, or that an analysis reproduces, before reporting or writing it up - requires running the analysis fresh and reading the actual output first; evidence before claims always
- Writing Science SkillsK-DenseUse when creating new skills, editing existing skills, or verifying skills work before deployment