science-superpowersK-Dense-AI/science-superpowers
Pulls research analysis back from "run the data first, find a conclusion later" to a disciplined flow of "define the que…
No ratings yet
Rate this skill
Stars350
Forks36
Watchers350
Open Issues2
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/K-Dense-AI/science-superpowers.git
OverviewOverview
Key Features
Pulls research analysis back from "run the data first, find a conclusion later" to a disciplined flow of "define the question, pre-register the plan, then execute the analysis", so every step is traceable and reproducible. Key capabilities include: 1. Research question framing: forces vague research ideas into testable research questions before any analysis begins, preventing goal drift; 2. Prior-work survey: systematically reviews existing literature and related work around the research question to ground question positioning and method choice; 3. Analysis design: fixes variables, methods and decision criteria before analysis starts, front-loading the analysis plan; 4. Analysis pre-registration: freezes the analysis plan into a pre-registration record and separates confirmatory from exploratory analysis to prevent post-hoc hypothesis changes; 5. Subagent-driven analysis: executes analysis steps through subagents following the pre-registered plan, keeping execution aligned with the plan; 6. Red-team review: requests an independent red-team review before conclusions are produced to surface logical gaps and overreach; 7. Reproducibility and evidence over claims: checks the reproducibility of the analysis process and requires conclusions to rest on evidence rather than assertions.
Use Cases
Research project scoping and question framing, literature and prior-work survey, analysis design and pre-registration, subagent-driven data analysis execution, red-team review and conclusion auditing, reproducibility checks and evidence tracing.
Target Roles
AI / Algorithm Engineer, Data Analyst / Data Engineer, Product Manager (PM), Test / QA Engineer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 2207 |
|---|---|
| Data source | GitHub |
| Repository | K-Dense-AI/science-superpowers |
| Category | Education, Training & Practice / Technical Learning & Knowledge Architecture |
| Primary language | Shell |
| License | Other |
| Default branch | main |
| GitHub repository ID | 1252814323 |
| Node ID | R_kgDOSqxt8w |
| Rank | #1686 (position within the source ranking) |
| Site-wide popularity rank | #1892 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now350
- Previous point · 09-25 340
- vs previous point +10
- 2 data points 16 days
- Now36
- Previous point · 09-25 35
- vs previous point +1
- 2 data points 16 days
TimelineTimeline
Repository created2026-05-28 22:37:525 months ago
Data last updated2026-10-26 12:20:5523 days ago
Last commit2026-09-13 14:59:312 months ago
CommitLatest commit
Version [latest] committed by timothykassis. Update Category: Feature Addition & Enhancement. Commit details: Add docs. This update introduces new capabilities and module extensions.