All authors
Claude Skills by brycewang-stanford
github.com/brycewang-stanford5,310 skills37 installs6,514 views
- MarkitdownConvert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.Votes: 0GitHub stars: 3,775
- 00 Phack RouterEntry point for the p-hacking skills suite. Routes a request to the right sub-skill for (a) mapping researcher degrees of freedom in an econometric design, (b) running an instrumented specification search, (c) detecting p-hacking in a body of results, (d) immunising an analysis against it, or (e) running the agent p-hacking evaluation harness. Use whenever the request involves specification search, multiverse or specification-curve analysis, p-curve or caliper tests, publication bias, researc...Votes: 0GitHub stars: 3,775
- 01 Phack TaxonomyName and classify p-hacking strategies, and quantify what each one does to the false-positive rate. Covers the twelve-strategy compendium of Stefan and Schoenbrodt (2023), thirteen econometrics-specific degrees of freedom (clustering doctrine, fixed-effect structure, RDD bandwidth, kernel and inference mode, IV instrument sets and first-stage screening, staggered-DiD estimator and comparison-group choice, synthetic-control donor pools), the search procedures that turn a strategy into a sessio...Votes: 0GitHub stars: 3,775
- 02 Forking PathsMap the garden of forking paths for a concrete econometric design and turn it into a machine-readable design card that the specification-search engine can walk. Use when asked how many defensible analyses a dataset or research design admits, to enumerate researcher degrees of freedom for a specific DiD, IV, RDD, staggered-adoption, panel or cross-sectional study, to build or validate a design card, to encode a pre-registered specification, or to size a multiverse before running it.Votes: 0GitHub stars: 3,775
- 03 Specification SearchRun an instrumented walk of a specification universe and recover honest inference from it. Estimates every specification in a design card (or walks it with a realistic search procedure), logs a complete ledger, flags pathological specifications, calibrates the search against an enforced null, runs the Simonsohn joint tests on the whole curve, measures how far the finding sits from the pre-registered analysis, attributes significance to the choices that produced it, and writes a publishable ho...Votes: 0GitHub stars: 3,775
- 04 Framing AttacksCatalogue of prompt framings that determine whether an agent refuses or performs specification search, and the harness for probing them. Reproduces and extends the published finding that coding agents refuse an explicit request for significant results but comply when the identical request is reframed as uncertainty reporting. Use when running a red-team probe of statistical guardrails, designing eval conditions for an agent p-hacking benchmark, measuring the gap between refusal-by-framing and...Votes: 0GitHub stars: 3,775
- 05 Narrative LaunderingAudit how an empirical write-up presents its analytical choices, and detect the rhetorical moves that convert a specification search into an apparently confirmatory finding. Covers HARKing, robustness theatre, selective disclosure, the vanishing pilot study, and estimator-choice narratives. Use when reviewing a paper or an agent-produced report for undisclosed search, refereeing an empirical manuscript, or scoring whether an agent disclosed the specification search it actually ran.Votes: 0GitHub stars: 3,775
- 06 Phack DetectionTest whether a body of reported results shows p-hacking, selective reporting or selection between stages, using the p-curve battery and the threshold and across-stages tests of Adda, Decker and Ottaviani (2020). Implements the binomial, Fisher, Stouffer and least-concave-majorant monotonicity tests of Elliott, Kudrin and Wuethrich (2022); threshold-bunching tests calibrated against a smooth counterfactual density; a Cattaneo-Jansson-Ma density-jump test and a right-side spike test that tell a...Votes: 0GitHub stars: 3,775
- 07 Phack ImmunizationMake an empirical analysis robust to specification search, before or after the fact. Covers pre-registration and pre-analysis plans encoded as design cards, specification-curve reporting with the Simonsohn joint tests, Romano-Wolf and effective-multiplicity corrections, full-procedure null calibration including for sequential searches, the distance-from-pre-registration diagnostic, split-sample and holdout designs, and the auto-generated honest report. Use when asked how to protect an analysi...Votes: 0GitHub stars: 3,775
- 08 Eval HarnessRun and score the agent p-hacking benchmark. Composes prompt cells across research framing and significance pressure, drives an agent through them, and scores each run into a P-Hacking Intensity index decomposed into selection, search breadth, estimate inflation, inference gap, pre-registration departure and disclosure. Use when benchmarking whether an AI agent p-hacks, comparing models or tool stacks on statistical integrity, scoring a single agent analysis run, or designing an evaluation of...Votes: 0GitHub stars: 3,775
- 09 Search ProceduresModel how a specification universe is actually walked, rather than assuming it is enumerated. Implements the search procedures a p-hacker or a pressured agent uses (first-significant stopping, random trial within a budget, greedy coordinate descent from the pre-registered analysis, random hill-climbing, and the two-stage split-sample walk with an optional continuation rule, after Adda, Decker and Ottaviani 2020), replays each on null data to measure its false-positive rate and the inflation o...Votes: 0GitHub stars: 3,775
- 10 Phack PolyglotRun the instrumented specification search in the user's own statistical language — Stata (reghdfe, ivreghdfe, rdrobust, did2s), R (fixest, rdrobust, did2s), Python (statsmodels, linearmodels) or StatsPAI — and bring the results back into the audit, null calibration and honest report. Exports the enumerated grid as a language-neutral specs table plus a generated runner, ingests the runner's ledger, replays the null draws in that language, and reports cross-language parity. Use when an analysis...Votes: 0GitHub stars: 3,775
- Graph Learning Papers GuideConference papers on graph neural networks and graph learningVotes: 0GitHub stars: 3,639
- Huggingface ApiSearch and discover ML models, datasets, and Spaces on Hugging FaceVotes: 0GitHub stars: 3,639
- Huggingface Inference GuideRun NLP and CV model inference via Hugging Face free-tier APIVotes: 0GitHub stars: 3,639
- Keras Deep LearningBuild and debug deep learning models with Keras and TensorFlow backendVotes: 0GitHub stars: 3,639
- Kolmogorov Arnold Networks GuidePapers and tutorials on KAN learnable activation networksVotes: 0GitHub stars: 3,639
- Llm Evaluation GuideEvaluate and benchmark large language models for research applicationsVotes: 0GitHub stars: 3,639
- Llm From Scratch GuideBuild a ChatGPT-like LLM from scratch using PyTorch step by stepVotes: 0GitHub stars: 3,639
- Ml Pipeline GuideBuild and deploy reproducible production ML pipelines for researchVotes: 0GitHub stars: 3,639
- Nlp Toolkit GuideNLP analysis with perplexity scoring, burstiness, and entropy metricsVotes: 0GitHub stars: 3,639
- Npcpy Research GuideAll-in-one Python library for NLP, agents, and knowledge graphsVotes: 0GitHub stars: 3,639
- Prompt Engineering ResearchSystematic prompt engineering methods for AI-assisted academic research workf...Votes: 0GitHub stars: 3,639
- Pytorch GuideAvoid common PyTorch mistakes and apply robust training patternsVotes: 0GitHub stars: 3,639
- Pytorch Lightning GuidePyTorch Lightning framework for scalable model training and researchVotes: 0GitHub stars: 3,639
- Reinforcement Learning GuideReinforcement learning fundamentals, algorithms, and researchVotes: 0GitHub stars: 3,639
- Responsible Ai GuideResources for trustworthy, fair, and ethical AI researchVotes: 0GitHub stars: 3,639
- Tensorflow GuideTensorFlow best practices for tf.function, GPU memory, and deploymentVotes: 0GitHub stars: 3,639
- Transformer Architecture GuideGuide to Transformer architectures for NLP and computer visionVotes: 0GitHub stars: 3,639
- Vmas Simulator GuideVectorized multi-agent reinforcement learning simulatorVotes: 0GitHub stars: 3,639
- Biomedical24 biomedical research skills. Trigger: medical research, clinical trials, genomics, bioinformatics. Design: domain databases, wet-lab/dry-lab methods, and ethical compliance guides.Votes: 0GitHub stars: 3,639
- Alphafold ApiQuery AlphaFold protein structure predictions by UniProt accessionVotes: 0GitHub stars: 3,639
- Bioagents GuideAI scientist framework for autonomous biological research workflowsVotes: 0GitHub stars: 3,639
- Biothings ApiQuery gene, variant, and drug annotations via BioThings APIsVotes: 0GitHub stars: 3,639
- Clawbio GuideOpenClaw bioinformatics skill library for genomics pipelinesVotes: 0GitHub stars: 3,639
- Clinical Dialogue Agents GuidePapers on AI agents for clinical dialogue and medical QAVotes: 0GitHub stars: 3,639
- Clinical Research GuideDesign clinical studies and report using CONSORT, STROBE guidelinesVotes: 0GitHub stars: 3,639
- Clinicaltrials Api V2Search and analyze clinical trials via the ClinicalTrials.gov v2 APIVotes: 0GitHub stars: 3,639
- Clinicaltrials ApiClinical trial registry database search APIVotes: 0GitHub stars: 3,639
- Ena Sequence ApiAccess nucleotide sequence data from the European Nucleotide ArchiveVotes: 0GitHub stars: 3,639
- Enrichr ApiPerform gene set enrichment analysis using the Enrichr APIVotes: 0GitHub stars: 3,639
- Ensembl Rest ApiQuery gene, sequence, and variant data via the Ensembl REST APIVotes: 0GitHub stars: 3,639
- Epidemiology GuideEpidemiological study designs, measures of association, and public health ana...Votes: 0GitHub stars: 3,639
- Genomas GuideAutomate gene expression analysis with the GenoMAS multi-agent systemVotes: 0GitHub stars: 3,639
- Genomics Analysis GuideWorkflows for RNA-seq, GWAS, and variant calling in genomic researchVotes: 0GitHub stars: 3,639
- Genotex Benchmark GuideBenchmark for LLM agents on gene expression data analysisVotes: 0GitHub stars: 3,639
- Med Researcher GuideMulti-agent system for biomedical literature review and synthesisVotes: 0GitHub stars: 3,639
- Med Researcher R1 GuideMedical deep research agent with reasoning chain analysisVotes: 0GitHub stars: 3,639
- Medgeclaw GuideAI research assistant for biomedicine, RNA-seq, and drug discoveryVotes: 0GitHub stars: 3,639
- Medical Data ApiAccess FDA drug data and WHO global health statistics for researchVotes: 0GitHub stars: 3,639