Review product, technical, experiment, and strategy documents for decision-readiness.
Download and analyze Shopee product reviews in bulk for competitive research, sentiment analysis, and market intelligence.
Researches and validates Shopify product opportunities using customer, demand, competitor, supplier, economics, operations, and risk evidence. Use before listing or sourcing.
Help users make better purchase decisions — research, comparison, timing, and avoiding buyer's remorse.
Research zakupowy — znajdź najlepszy produkt lub usługę w danej kategorii według kryteriów użytkownika i przedstaw ranking od najbardziej do najmniej polecanego (wady, zalety,…
Create vertical (9:16) interactive presentations optimized for YouTube Shorts, TikTok, and Instagram Reels.
Manipulate numerical data, contingency tables, and statistical findings so that no individual or organization is identifiable in the results of the an
Use when you have a collection of cleaned MS/MS spectra (in formats like mzML, mgf, msp, mzxml, or json) and need to predict molecular structural similarities between spectrum…
Lint and repair citation sidecars in a research corpus — structural integrity (missing Outgoing/Incoming sections, missing frontmatter ref/title/type, doubled-append duplicate…
Use when designing or auditing ACM SIGCOMM experiments — climbing the evidence ladder from microbenchmarks to testbed and trace replay to deployment, choosing baselines that match…
Use when running the final pre-upload audit of an ACM SIGCOMM submission — the abstract-registration-then-paper sequence on the SIGCOMM HotCRP site, the AoE deadline clock, the 12…
Use when deciding whether a project is a strong ACM SIGCOMM fit, choosing the research versus experience track, identifying the networking-stack mechanism at the core of the…
Use when designing or auditing the evaluation of a SIGGRAPH / TOG paper, covering head-to-head comparisons against the strongest prior method, ablations, performance/timing…
Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with…
Use when designing or auditing ACM SIGMETRICS evaluations, covering theorem-plus-validation rigor, stating and testing modeling assumptions, analysis-vs-simulation agreement, real…
Use when converting an accepted SIGMOD research paper into its PACMMOD journal version, covering the port from the ACM submission template to PACMMOD format, de-anonymization,…
Use when designing or auditing the evaluation of a SIGMOD paper, covering workload realism and standard benchmark usage, baseline tuning fairness, scalability and tail-latency…
Use when hardening the reproducibility story of a SIGMOD submission, covering PACMMOD's expectation that code, data, scripts, and notebooks be shared, experiment provenance from…
Use when reasoning about how a SIGMOD research paper moves through a PACMMOD round, covering double-anonymous CMT reviewing, the author feedback phase, accept/reject/revision…
Use when readying a SIGMOD research-track submission for a PACMMOD round, covering the abstract-plus-COI pre-deadline, Microsoft CMT mechanics, the 12-page ACM-template limit,…
Use when judging whether a project belongs at SIGMOD's research track, comparing it against PVLDB's rolling model, ICDE, PODS, KDD, CIDR, and TODS, weighing the industrial track…
Use when revising a SIGMOD research paper's prose and structure, covering the data-management framing readers expect on page one, running examples and architecture figures,…
Generates YAML signal configs for agent simulation experiments. Use when the user wants to define what signals to track, how to extract them from run artifacts, and how to…
Use when implementing a Signal Lab PRD slice end-to-end through a phased, resumable pipeline. Delegates work to subagents, keeps context in execution files, and optimizes for…
Converts evidence-backed trend signals, outlier posts, audience language, and competitor patterns into original platform-native content tests without copying a source's unique…
Govern complex AI-assisted work with a clarity-first, human-controlled, evidence-backed method. Use when planning, researching, designing, building, reviewing, troubleshooting,…
Conduct evidence-controlled research by defining the question, scope, freshness, source quality, factual versus inferential claims, contradictions, citations/provenance,…
Signals scout for PostHog A/B experiments. Watches running experiments for validity threats — sample ratio mismatch, contamination, exposure stalls, mid-run flag mutations — and…
Developer agent for the AIM Algoryx AGX dynamics simulator (sim/ directory). Understands C++/CMake builds, physics simulation, simulated sensors (lidar, camera), vehicle models,…
Use when after training contrastive embeddings that unify MS/MS spectra and molecular structures into a shared embedding space.
Performs molecular similarity searching using Tanimoto, Tversky, Dice, and cosine coefficients on bit/count fingerprints with explicit choice rules for symmetric vs asymm — from…
Analyze websites and domains using SimilarWeb traffic data. Get traffic metrics, engagement stats, global rankings, traffic sources, and geographic distribution for comprehensive…
Workflow for questions, clarifications, and information requests. Researches the codebase and answers on the Linear ticket without making code changes.
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat,…
Use when when you have installed or updated a DNA methylation analysis tool (e.g., ChAMP) and need to verify that it produces documented expected outputs on a reference simulation…
Simulation experimental design skill for efficient scenario analysis and optimization.
Use when planning, coding, debugging, auditing, comparing, or writing claims for Eclipse SUMO/TraCI traffic-signal experiments, including OSM/netconvert networks, TLS/NEMA,…
Orchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hypercube sampling), initialize and track batch job campaigns, monitor…
The sindri orchestrator. Runs one experiment per invocation. Reads state, checks the HALT sentinel and termination predicates, picks next candidate, dispatches an experiment…
Use when you have aligned single-cell ATAC-seq data as BAM files or fragment files (TSV format with genomic coordinates) and need to prepare it for spectral embedding, clustering,…
Use when after loading fragment counts into a SummarizedExperiment object (e.g., via getCounts) but before motif matching or deviation computation.
Qualify a single-cell Perturb-seq screen's no-phenotype calls with karyon — flag perturbations called "no effect" where the guide never actually knocked the target down (a silent…
Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset/seriousness characteri — from…
Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction.
Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction.
Use when when you have processed LC-MS/MS data with precursor m/z, ionization mode, collision energy (if available), and fragment peak lists (m/z and intensity pairs), and need to…
Optimize construction site logistics including material delivery scheduling, crane positioning, storage area allocation, and traffic flow using operations research and simulation.
Esplora e interroga il SITUAS (Sistema Informativo Territoriale delle Unità Amministrative e Statistiche, ISTAT) tramite la CLI `opensituas`.
Validated design decisions, CSS patterns, and visual direction from sketch experiments for BrewIndex. Auto-load during any UI implementation work on this project.
Analyzes on-chain token data including whale tracking, DEX volume, wallet PnL, and token unlock schedules.
Continuously tests and improves Claude Code skills using A/B experimentation and Auto Research ML loop.
Biología Celular — Estructura celular, genética, evolución, ecología y división celular para nivel secundaria/bachillerato/1º universidad.
Compose a site brief from offer.md + audience.md + voice.md + research files + the operator's dial / archetype picks. Used by /site as the brief-drafting step.
Skill de Química Básica para resolución de problemas de estructura atómica, tabla periódica, enlaces, estequiometría y reacciones químicas a nivel de Secundaria y Bachillerato.
Chains multi-step workflows constitutionally — research → plan → judge → execute → verify → log → vault — without human step-by-step prompting
TRANSVERSAL SKILL - Manages session state throughout the entire workflow. Invoked at START, after each commit, after decisions, and at GIT (end).
Ciencias de la Tierra — Geología, meteorología, oceanografía, climatología, ciclo del agua y recursos naturales para nivel secundaria/bachillerato.
Audit and safely repair cross-runtime Skill governance: canonical-source ownership, divergent or duplicate projections, exposure scopes and budgets, lifecycle drift, quarantine,…
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality.
Generate a production-ready AbsolutelySkilled skill from any source: GitHub repos, documentation URLs, or domain topics (marketing, sales, TypeScript, etc.).