Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion.
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and…
Load this before deciding anything the evidence at hand cannot settle — a work item's premise, a root cause, a remedy's mechanism, another session's or a subagent's claim, a…
Load this before a test, a mutation, a revert arm or a green run is cited as proof that a fix holds — and again before writing "falsified" in a pull request.
Load this when uncertainty can be settled by running something — reproducing behaviour, an integration test, a hypothesis, unfamiliar code, a clean build, a bounded test…
Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after…
Deep reasoning makes better comedy. #1 on DeepResearch Bench (Feb 2026). AI meme generation with audience targeting, trend research, and multi-angle humor.
Solana memecoin discovery and trading sub-strategy. Part of paper-trader skill. Uses gmgn.ai, dexscreener.com, pump.fun for early token identification.
Expert skill for JavaScript memory leak detection using Facebook MemLab. Configure MemLab scenarios, execute memory leak detection runs, analyze heap snapshots, identify detached…
IRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH NEEDED, Application is STUDENT ANALYSIS prompts,…
Leitfaden Research- und Quellen-Tracking fuer Memos: Quellenarten, Zitierregeln dejure.org / openjur, BGH / BVerfG / EuGH, Versionierung. Pruefraster fuer Erstautor und Review.
Use when a Codex task involves UI design, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, component specs, design audits, or design-to-code…
Be one of the first to benchmark your agent's memory — and help shape how AI remembers. Runs a peer-review-grade evaluation suite (LLM-as-judge, nDCG/MAP/MRR with 95% CIs,…
Long-running multi-session work (research, eval loops, iterative benchmarks) with continuity -- resume prior lessons, capture per-run outcomes, build up stable truths over time.
Skill for implementing the 3-step Memory-First Protocol (Research, Response, Learning). Use when starting ANY task to understand past context, and MUST use when completing a task…
Research an external subject using web search, synthesize findings into a structured Basic Memory entity.
Use when a research note system needs architecture, when MOCs, frontmatter standards, and retrieval patterns must be designed for years of work, or when an existing vault has…
Use when a problem spans multiple disciplines or when single-domain thinking has produced stale analysis—applies Munger's latticework of mental models across physics, biology, and…
Activate mental-model-updater when new insights, experiences, or experimental results need to be integrated into existing mental models, skills, or knowledge structures.
Use when reasoning about how a system, user, or designer's internal model of behavior may diverge from reality — applies across UX, distributed systems, type systems, API design,…
Research e-commerce merchandise opportunities, category viability, price bands, competitors, profit assumptions, sourcing risks, and evidence gaps across Amazon and Chinese…
Build a research-backed Salla merchant persona. Pre-seeded with Salla's merchant segments (Nano, SMB, Mid-Market, Enterprise) and Saudi/GCC market context.
Plan and synthesize merchant research for Salla Platform PMs. Generates interview guides, synthesizes findings from multiple sources, and converts raw merchant signals into…
Plan and evaluate mesh generation for numerical simulations — estimate grid resolution from physics scales (interface width, boundary layers, wavelengths), check aspect ratios and…
Use when you have a baseline GNN model for predicting a continuous molecular property (e.
Screens research papers based on title/abstract and inclusion criteria, providing a structured Yes/No/Maybe decision.
Scrape competitor ads from Meta's Ad Library (Facebook, Instagram, Messenger, Threads, WhatsApp). Search by company name, Facebook Page URL, or keyword.
Systematic review and meta-analysis pipeline for medical research. Covers protocol registration (PROSPERO), search strategy, screening, data extraction, risk of bias assessment…
Investigation flow (Glob -> Grep -> Read), evidence-based research with file:line references, structured output format for AI consumption.
Use this meta-skill instead of answering directly when the current user asks to draft, repair, compile, or produce an academic/research paper or LaTeX manuscript.
Investigation flow (Glob -> Grep -> Read), evidence-based research with file:line references, structured output format for AI consumption.
Generates the "Risk of Bias" results section for a meta-analysis based on assessment tables and statistics.
Generates the "Results" section for meta-analysis sensitivity analysis based on statistical tables and titles.
Medical literature search strategy generator. Given a user's natural-language description (e.g., meta-analysis topic, PICOS elements, research question), automatically extract…
Use when you have a raw or extracted peak feature table (CSV or tabular format) containing mass-to-charge ratios, retention times, and intensity values across multiple samples…
Use when you have an untargeted metabolomics feature table (with m/z, retention time, and statistical significance values) and want to predict which metabolic pathways and…
Use when when you have multiple batches of metabolomics data in SummarizedExperiment
Use when you have extracted a large feature set of m/z values (hundreds to tens of thousands) from a Cardinal MSImagingExperiment object or similar MS dataset and need to assign…
Use when when preparing to run Over-representation Analysis (ORA) on metabolomics pathway data, after you have loaded both a metabolomics pathway database (e.g., KEGG, MetExplore)…
Use when you have a set of candidate metabolites for an unknown compound detected in a liquid chromatography–mass spectrometry (LC-MS) experiment, predicted RTs from a trained DNN…
Use when you have peak-abundance data (after molecular formula assignment, peak filtering by m/z, isotope, ppm error, and sample presence thresholds) and you need to quantify and…
Use when after running RAMClustR clustering on XCMS-detected LC-MS features in positive ionization mode, when you need to assign molecular weights to compound clusters and want to…
Use when after running do.findmain on a RAMClustR-clustered object to infer molecular weights and assign features to compound clusters, when you need to conduct structural…
Use when after preprocessing, imputation, and batch correction of LC-MS peak tables when you need to group redundant or related feature measurements (e.g., [M+H]+ and [M+Na]+…
Use when designing or validating a metabolomics pathway analysis experiment, especially when you have uncertainty about how many metabolites your detection platform will reliably…
Use when after normalizing a metabolomic feature matrix when you have both non-QC (study) samples and QC (quality-control) replicates in the same experiment.
Use when you have simulated or experimental mzML data from two or more fragmentation controllers (e.
Use when you have a measured m/z value from spatially-resolved metabolomics or mass spectrometry imaging and need to assign a molecular formula with high confidence.
Use when you have XCMS-processed LC/MS peak data from dual-labeled (e.g., 13C) and unlabeled (12C) metabolomics samples and need to distinguish features genuinely enriched by…
Use when when you have a small-molecule structure (SMILES, MOL, or SDF format) and need to identify probable metabolites or degradation products in a specific biological — from…
Use when you have (1) peak-picked LC-MS AIF features in a feature table with m/z and retention time, (2) corresponding xcmsSet and RAMClustR pseudo-MS/MS spectral objects from…
Use when you have an annotated list of metabolite compounds (with associated m/z features or compound IDs) and want to determine which KEGG metabolic pathways are significantly…
Use when when beginning an untargeted LC-MS annotation workflow, before attempting to match experimental m/z peaks to metabolite identities.
Use when you have a SummarizedExperiment object containing NMR or MS metabolomic data with aligned phenotype information (BMI, disease status, age, gender), and you need to…
Use when when you have a small-molecule structure (SMILES, MOL, or SDF format) and need to predict its metabolic fate across one or more biological systems.
Use when when you have generated a set of candidate metabolites for a given experimental MS/MS spectrum and need to determine which candidate is most likely to be the true…
Use when your input is a SummarizedExperiment containing multiple batches or injection sequences of metabolomics samples (study samples, QC replicates, calibration lines) with…
Use when you have defined one or more proton NMR spectral regions-of-interest (ROIs) with lower and upper chemical-shift bounds (in ppm) from an experimental NMR spectrum of a…
Use when after constructing a background set for ORA in metabolomics: you have loaded an experimental detection list and a metabolomics pathway database, applied background-set…
Use when you have peak intensity data from metabolomics experiments with annotated metabolites assigned to known groupings (KEGG pathways, Reactome, GNPS Molecular Families, or…