Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It enforces a strict evidence-first pipeline that prevents premature modeling, with a data quality gate that can halt or require user confirmation, and adaptive analytical routes that only produce supported outputs.
Who it is for
- Data analysts and scientists
- Decision intelligence practitioners
- Risk and compliance officers
- AI governance and audit teams
Use cases
- High-stakes business or policy decisions requiring transparent evidence
- Model validation and deployment readiness assessment
- Reproducible research with source-preserved data and code
- Data quality auditing and preparation before analysis
Strengths
- Evidence-first workflow reduces overfitting and unwarranted recommendations
- Data readiness gate with explicit blocked/confirmation/ready outcomes
- Adaptive analytical routes (descriptive/diagnostic/predictive/prescriptive) selected based on case
- Reproducible outputs with hashed sources, contracts, and machine-readable results
Considerations
- Requires understanding of analytical methods and evidence contracts to interpret outputs
- May be overly complex for simple or well-understood questions
- Installation dependencies (Node.js 18+, Python 3.10+) and CLI tools may limit accessibility
README quick start
High-Stakes Analytics & Decision Lab
A platform-neutral, evidence-constrained Skill for moving from an ambiguous question to a defensible analysis—and only then, when justified, to action.
What the Skill does
This Skill turns an ambiguous, consequential question into a reproducible evidence product and, only when justified, a bounded decision product. It can start from a question alone or from uploaded row-level data. Instead of assuming the data are clean, the model is useful, or a recommendation must be produced, it makes each transition conditional on visible evidence.
| Highlight | Instead of… | The Skill… |
|---|---|---|
| Evidence first | Starting with a favorite method | Declares the question, estimand, population, grain, horizon, lineage, and claim boundary |
| Data readiness | Silently cleaning until a model runs | Preserves the source, profiles quality and privacy, and pauses on material choices |
| Adaptive analysis | Filling one fixed report template | Selects only the descriptive, diagnostic, predictive, or prescriptive work supported |
| Honest endpoints | Treating a recommendation as mandatory | Accepts an evidence request, negative validation, do_not_deploy, or bounded action |
| Shared uncertainty | Disturbing alternatives independently | Retains common time, market, participant, operational, campaign, or spatial shocks |
| Reproducible evidence | Separating prose from analysis | Links claims and accessible figures to JSON, CSV, hashes, and rerunnable code |
The contribution is not a newly invented statistical estimator. It is an adaptive orchestration system for evidence gating, method selection, claim control, dependent-risk handling, and case-specific analytical communication.
Quick install
npx skills add limingrui679-design/high-stakes-analytics-decision-lab -g
See runtime-specific, manual, and no-install options.
Overview · Complete workflow · Data gate · Four routes · Outputs · Real projects · Use
One complete evidence-to-decision workflow
flowchart TD
Q["1 · Frame the questiondecision · population · estimand · horizon"] --> S["2 · Establish the evidence contractsource · license · grain · lineage"]
S --> G{"3 · Data-readiness gate"}
G -->|"blocked"| X["Stoprequest corrected evidence"]
G -->|"confirmation required"| U["Appr
Description
A platform-neutral analytical Skill that profiles messy data, selects case-adaptive methods, and produces source-backed visual reports for high-stakes decisions.
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.