Research & Data

research-harness

github.com

Set up and operate an experiment harness for ML research projects run by Claude Code on remote GPU servers — a frozen protocol (splits, evaluator, baseline numbers), a claim contract with a pass bar, results produced only by a frozen evaluator, gate-decided loop exits (pass / budget / stall), detached GPU launches with traces, and hooks that block edits to frozen files. Use this whenever starting or running experiments for a paper, reproducing a baseline, launching training or feature-extraction jobs on a GPU cluster, checking whether an idea passed its kill test, or when the user says experiments drift, numbers can't be trusted, or work stalls midway. Pairs with the research-paper skill (which decides WHAT to run); this one decides HOW runs are executed and judged.

$ npx skills add hardiksharma6555/research-harness-skill
Skill anzeigen→

claim-ledger

github.com

Claim ledger — fact-check a large Markdown report or research body one point at a time, riskiest first, with stable point IDs, an add-only verdict log and scripted report edits. Use when asked to fact-check, verify or audit a long report, to start or continue a ledger ("start the ledger", "next batch"), or to measure a ledger's drift.

$ npx skills add ryanwisth/claim-ledger
Skill anzeigen→

physics-paper-framing

github.com

Canon for the audience-facing bookends and submission framing of a physics paper: standard abstracts, Nature-style embedded summary paragraphs, Introduction-to-Conclusion revision alignment, authorship and acknowledgments, and cover letters. Use when writing or reviewing an abstract, Nature summary paragraph, introduction/conclusion consistency, cover letter, or pre-submission package.

$ npx skills add Harrinive/physics-paper-skills
Skill anzeigen→

informs-writing

github.com

Write, structure, rewrite, and polish academic manuscripts in LaTeX (informs4) for INFORMS flagship journals: Operations Research (OR), Management Science (MS), Manufacturing & Service Operations Management (M&SOM), and INFORMS Journal on Computing (IJOC). Use when drafting a paper or section from a core idea via exemplar papers (arXiv/SSRN/top-journal PDFs), rewriting drafts to remove AI prose patterns, pruning excessive notation and redundant definitions, fixing context-blind concepts and revision-history leakage, formatting with informs4.cls and Online Appendix conventions, or calibrating manuscripts to OR, MS, M&SOM, or IJOC editorial preferences.

$ npx skills add JiayuXu11/informs-writing-skills
Skill anzeigen→

humanize

github.com

Revise a LaTeX paper (.tex) for readability and make it read like a person wrote it — removing the tics of AI-generated prose (inflated vocabulary, signposting, "not only… but also", em-dash chains, rule-of-three lists, summary sentences that restate the paragraph) while keeping every claim, number, citation, equation and LaTeX command intact. Produces a transformed copy (`<name>_humanized.tex`) next to the original, which is never modified. Use this whenever the user asks to polish, proofread for style, improve the writing/flow/clarity of a paper or section, make text "sound less like ChatGPT/AI", "less robotic", "more natural", or says things like "humanizar o texto", "melhorar a redação/legibilidade", "revisar o inglês do artigo", "tirar a cara de IA", "deixar mais fluido" — in English or Portuguese — and also proactively suggest it when a paper the user is preparing for submission or revision is full of AI-sounding prose. Not for changing scientific content, fixing com...

$ npx skills add gilzamir18/GilzaCodeSkills
Skill anzeigen→

physics-paper-editing-section

github.com

Physics-first editing for whole physics sections of any length or technical passages over 12 sentences in LaTeX, Markdown, or plain text. Builds a section physics spine and global object ledger, edits argument-sized chunks through physics-paper-editing, and reviews the assembled text.

$ npx skills add Harrinive/physics-paper-skills
Skill anzeigen→

citation-tracking

github.com

Use this skill when the user wants to measure AEO performance, track AI search visibility, monitor brand mentions or citations in ChatGPT/Claude/Perplexity/Gemini, set up an AEO measurement program, build a baseline, or report on AI search results to a stakeholder. Triggers include "track AI search," "measure AEO," "AI visibility tracking," "monitor ChatGPT mentions," "track brand in Perplexity," "AEO reporting," "citation tracking," "AI search measurement," "LLM monitoring," "AI mention monitoring." This skill produces a measurement program covering mention rate, citation rate, position in response, and competitive presence, with a monthly cadence and clear reporting format. Works tool-agnostically with manual tracking or with paid AI search tracking platforms.

$ npx skills add Groundplane-Group/votel-skills
Skill anzeigen→

antibody-sequence-bioinformatics

github.com

Work with antibody, nanobody (VHH) and BCR sequence data - numbering schemes (IMGT, Kabat, Chothia, Martin, AHo), CDR and framework boundaries, VHH hallmark residues and cysteine checks, germline assignment with ANARCII, ANARCI, abnumber or IgBLAST, mapping CDRs onto a structure's residue numbers for loop-redesign contigs, interface contacts and hotspot coverage of a predicted complex, repertoire pipelines, the AIRR Rearrangement TSV format, clonotype grouping, humanness, and sequence liability motifs. Use when parsing, numbering, annotating, QC-ing or filtering antibody, VHH or designed binder sequences, when a CDR definition or region coordinate is in question, when a contig needs PDB residue numbers, or when writing code against AIRR, IgBLAST, ANARCI or OAS data. Every region coordinate carries the name of its numbering scheme. Use antibody-binder-design for the design workflow, antibody-literature-search to find sequences and structures, antibody-therapeutics-landscape...

$ npx skills add 0xcvaliente/immunology-skills
Skill anzeigen→

antibody-literature-search

github.com

Find and summarise antibody and immunology literature and public database records - papers on a target, antibody or method, the originator publication for a named mAb, UniProt entries, PDB, SAbDab and SAbDab-nano structures, Thera-SAbDab therapeutic sequences, IMGT germlines, clinical trials, patent sequences, and measured design data in Proteinbase. Use when asked what is known or published about an antigen, antibody, epitope or assay, to look up an accession, PDB ID, PMID or DOI, to summarise a paper, to profile a target before designing against it (a target dossier covering construct, structures, known binders and epitopes, orthologs, accessibility and clinical context), or to assemble evidence on an antibody target. Every identifier is resolved against the source before it is written. Use antibody-therapeutics-landscape for industry and format context, antibody-reagent-selection to choose a commercial antibody, antibody-sequence-bioinformatics to work with the sequence...

$ npx skills add 0xcvaliente/immunology-skills
Skill anzeigen→

antibody-therapeutics-landscape

github.com

Antibodies as drugs and as an industry - molecular formats (IgG subclass, Fab, scFv, VHH, bispecific, ADC, Fc engineering), drug-name decoding, the discovery-to-approval path, regulatory routes, developability, CMC and commercial vocabulary, nanobody (VHH) drugs, how to argue user fit and path to value for a design tool or pitch, plus biotech employer research and interview prep. Use when a prompt names an antibody drug, a mAb or nanobody format, an antibody or biotech company, asks what a biotech term means, who would use or buy a design result, or asks about a biotech role, job ad or interview. Approval counts, pipelines and company facts are volatile and get looked up, never recalled. Use antibody-literature-search to find papers, trials and database records, antibody-reagent-selection to choose a lab antibody, antibody-sequence-bioinformatics for sequence data.

$ npx skills add 0xcvaliente/immunology-skills
Skill anzeigen→

ndexbio/symposium-curate-data

github.com

Build a grounded literature corpus for a scientific hypothesis and publish it into a Symposium community record. Takes one hypothesis stated "If [Cause], then [Effect], because [Rationale]", searches the literature and data repositories for the sources that bear on it, expands one citation hop, resolves access, puts the corpus to the user for review, then hands it to Symposium to publish as ScientificPublication, Data and Argument artifacts. Use for: curate sources for a hypothesis, build a literature corpus, find papers supporting or contradicting a hypothesis, import scientific publications into a community record, gather evidence for a Symposium record.

$ npx skills add ndexbio/symposium-skills
Skill anzeigen→

scriptonomy-lab/strategy-lab

github.com

Turn a plain-English stock strategy into a validated strategy definition, backtest it only after the user confirms, explain the results using only numbers from the tool output, and start paper trading on explicit approval. Runs only the openclaw-bot commands.

$ npx skills add scriptonomy-lab/OpenClaw-Trading-Bot
Skill anzeigen→

mleswell-ai/research-synthesis

github.com

Synthesises evidence from multiple sources into a decision-ready, fully traceable report. Frames the question, weighs each source, records evidence in a claim-level ledger, builds claims across sources (thematic, narrative, framework, quantitative or mixed), computes how certain each claim is allowed to be, stress-tests the conclusions and verifies every citation. Use when asked for a research synthesis, evidence synthesis, literature review, systematic, scoping or rapid review, evidence summary or briefing, "what does the research say", the state of the evidence, or to combine, compare or reconcile papers, studies, reports, interview transcripts, survey responses or other research data. Also use to audit or strengthen an existing review. Not for summarising a single document or for quick factual lookups.

$ npx skills add mleswell-ai/research-synthesis-skill
Skill anzeigen→

Brajesh31/claude-cra-vulnerability-obligations-skill

github.com

Use when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they must report a vulnerability or incident, or what a specific CVE triggers legally. Maps a product with digital elements to CRA scope, product classification, Annex I vulnerability-handling duties, and Article 14 reporting obligations — every legal claim cited from official regulation text fetched live through the Ansvar Gateway MCP connector, joined with live CVE / CISA-KEV / EPSS vulnerability intelligence from the same connector.

$ npx skills add Brajesh31/claude-cra-vulnerability-obligations-skill
Skill anzeigen→

LLCao-AI-Group/great-work-evaluation

github.com

Evaluate a research, product or start-up proposal, experiment report or paper draft against Paul Graham's "How to Do Great Work" standard. Scores five dimensions on a -1 / 0 / +1 scale (true and new, honesty and rigor, generality, quality of the question, first step and value of failure), searches for the closest existing work, checks the strongest simple baseline, and fact-checks the author's own answers on scope, curiosity and "why you" when they are submitted alongside. Use this skill whenever someone asks to review, score, critique or get feedback on a proposal, project idea, paper plan, grant draft or early report, asks whether an idea is novel or worth pursuing, or mentions "great work", even if they do not name the skill.

$ npx skills add LLCao-AI-Group/GreatWork
Skill anzeigen→

davlug3/circuit-design-skill

github.com

Turn natural-language circuit requirements into a complete, evidence-led electronics design. Elicit critical specifications and preferences, make only conventional low-risk assumptions, research and select real components, calculate and simulate the design, and deliver a KiCad project with schematic and PCB, assigned footprints, BOM, SPICE netlist, and verification evidence. Use for new circuit design, circuit redesign, component sizing, KiCad/SPICE generation, simulation, and design verification.

$ npx skills add davlug3/circuit-design-skill
Skill anzeigen→

btrainee/literature-review-skill

github.com

Bioinformatics literature systematic review skill. Use when interpreting a scientific paper PDF in bioinformatics, genomics, oncology, or related fields. Extracts full text AND every main figure as high-resolution PNGs (PyMuPDF caption-anchored region rendering), then generates standardized deliverables: a Word deep-reading report (10-section structure with each figure embedded and analyzed: research question / method / key results / interpretation), a Nature/Cell-style PPT for group meeting sharing, and optionally a popular science article for WeChat Official Account. Covers the full workflow from PDF parsing, figure extraction, deep reading, structured analysis, to document generation.

$ npx skills add btrainee/literature-review-skill
Skill anzeigen→

tolborg-group/paper-interview

github.com

Interview the user about a scientific paper they have read, asking probing questions like a fair examiner so they can check and deepen their own understanding. Use when someone wants to be quizzed, questioned or examined on a paper, prepare for a journal club or exam, or test whether they understood a paper or one of its sections.

$ npx skills add tolborg-group/group-skills
Skill anzeigen→

Yurieff/metrics-pack

github.com

Turns a startup's revenue data into MRR (monthly recurring revenue), cohorts, NRR (net revenue retention) and one investor slide. Reads monthly update files, a per-customer revenue export, or a contracts register (client, contract value, start month, term). All arithmetic is done by a tested Python helper, never in prose. Separates billed months from contracted-but-not-yet-billed months, reports contracts shorter than three months as non-recurring, and says "cannot compute yet" for a 12-month NRR when no customer has run twelve months. Produces a plain-English note, four CSVs and one 16:9 slide. Invoke when the user says "build the metrics pack for X", "MRR, cohorts and NRR for X", "what is X's net revenue retention", or "/metrics-pack X".

$ npx skills add Yurieff/fundraising-skill-pack
Skill anzeigen→

Yurieff/competitors

github.com

Maps a startup's competitors – writes an explicit membership test, sweeps for operators through several independent routes, classifies each as direct / former direct / indirect, compares pricing like-for-like from published pages, researches total funding per competitor with an entity check, and sweeps M&A comparables with deal values and multiples. Produces a competitor note, one csv, one price chart, and a two-sheet shareable market-analysis workbook (competitors + M&A comparables). Bootstraps the company folder and researches the source material itself when none exists. Invoke when the user says "who competes with X", "competitor research on X", or "/competitors X".

$ npx skills add Yurieff/fundraising-skill-pack
Skill anzeigen→

Yurieff/market-size

github.com

Sizes a startup's market – builds TAM/SAM/SOM twice (bottom-up from buyers × price, and top-down from a published market figure), triangulates the two, then builds a third number the demand builds cannot give you: the capacity ceiling their own sales and delivery machine can carry. Compares all of it to whatever the deck claims, and reports the distance between what the market could support and what the company's own machine can reach. Produces a sizing note, one csv of every line item, and one chart. Bootstraps the company folder and researches the source material itself when none exists. Invoke when the user says "size the market for X", "what's the TAM for X", or "/market-size X".

$ npx skills add Yurieff/fundraising-skill-pack
Skill anzeigen→

autentisitet/python-sklearn-workflow

github.com

Designs leakage-safe scikit-learn splits, cross-validation, scoring, search, diagnostic curves, PCA scaling, model inspection, ColumnTransformer, and Pipelines. Use when building or reviewing an sklearn evaluation workflow. Do not use for ordinary prediction with an already-fitted estimator, plotting already-computed predictions, experiment tracking after evaluation design is fixed, deep-learning frameworks, estimator theory alone, or incidental sklearn imports.

$ npx skills add autentisitet/python-engineering-skills
Skill anzeigen→

swaggylei/dataset-difficulty-skill

github.com

Analyze image classification datasets before training for visual quality issues, semantic outliers, class confusion, augmentation instability, corrupt or duplicate samples, relative difficulty bands, and stratified splits. Use for dataset audits and training-readiness checks; do not use for detection, segmentation, video, or claims about downstream accuracy.

$ npx skills add swaggylei/dataset-difficulty-skill
Skill anzeigen→

kpp-coding-skill

github.com

使用 Kaiwu PyTorch Plugin(KPP)安装、构建与训练 PyTorch 能量模型,并接入 Kaiwu 采样器。适用于 RBM/BM、DBN、使用能量模型先验的 QVAE、能量引导离散序列生成 QDiffusion、为 PyTorch 模型做 MAIFS 特征选择,或 kaiwu.torch_plugin 的调试。明确需要 KPP 或场景适配时主动检查并安装 kaiwu-torch-plugin、处理依赖冲突、验证导入和训练。普通回归、一般神经网络、普通 VAE/扩散模型不触发;不依附 PyTorch 模型的纯 QUBO/Ising 组合优化不属于本 Skill 的范围。

$ npx skills add qboson/kpp-coding-skill
Skill anzeigen→