Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Opinionated guidance for constructing and interpreting Honeycomb queries on trace and event datasets — operation selection (percentiles not AVG, HEATMAP for distributions), relational field patterns (root., parent., any., none.), calculated fields, query math, and result interpretation (P99/P50 ratios, heatmap bands, TOTAL/OTHER rows, raw JSON via query_result_json). Use this skill when the user wants to query spans, traces, or log/event data in Honeycomb — requests like "show me latency", "error rate", "find slow requests", "find outliers", "interpret results", "relational fields", "calculated fields", or "download raw results". This skill covers all dataset types except metrics datasets (dataset_type=metrics) — for those, use metrics-queries instead.
Performance patterns and gotchas for querying a Rerun catalog from Python. Reach for this when exploring an unfamiliar dataset, when a CatalogClient/dataset query is unexpectedly slow, or when shaping a per-segment / per-episode pipeline that hits the catalog from many places.
Ingest a LeRobot (HuggingFace) dataset into Rerun. Read when converting a LeRobot dataset to RRDs, splitting it into per-episode segments, or registering it on a Rerun catalog. Covers the built-in directory importer (log_file_from_path), the per-episode LeRobotReader, and when to drop to ParquetReader for custom control.
Use when the user is asking how Spree's domain models relate — Orders, LineItems, Variants, Products, Stores, Channels, Markets, Payments, Shipments, Customers, Adjustments. Architecture and relationships only. Common phrasings include "how does X connect to Y", "what's the relationship between", "where does Spree store X", "how do I query orders across stores", "how do channels work", "what's the difference between Cart and Order", "Store vs Channel vs Market". For adding new models / new API resources, use the `spree-resource` skill. For field-level detail, see `docs/developer/core-concepts/` in the installed `@spree/docs` package.
Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).
Drug-combination synergy analysis — quantify whether two drugs together are synergistic, additive, or antagonistic using the standard reference models (Bliss independence, HSA / highest single agent, Loewe additivity, ZIP, and the Chou-Talalay Combination Index). Use when you have measured single-drug and combination effects (inhibition/viability) and need a synergy score. Explains which model to use, what data each one needs, and how to read the score. NOT for looking up pre-computed synergy in a database (use the SYNERGxDB tool / cell-line-profiling skill).
Enzyme kinetics — Michaelis-Menten Km, Vmax, kcat (turnover), and kcat/Km (catalytic efficiency / specificity constant) from substrate-velocity data, plus inhibition-mechanism analysis (competitive / uncompetitive / non-competitive, Ki). Fits the MM equation by nonlinear regression (and reports Lineweaver-Burk for reference). Use when you have substrate concentrations and initial reaction velocities and need kinetic parameters or to classify an inhibitor. NOT for BRENDA database lookups of published constants (use the BRENDA tools).
Systematic analysis of Google Ads and Meta advertising spend to identify wasted budget. Produces actionable exclusion lists with thematic categorization and statistical validation. Use when onboarding new accounts, performing monthly hygiene, or preparing for budget optimization.
Retrieve relevant information from a knowledge base using semantic, keyword, or hybrid search to ground a query. Use when the task starts with a corpus or index that must be searched; use context-ranking when candidate chunks already exist and only need ordering.
Backtest crypto trading strategies from natural language ideas. Use when: user describes trading ideas, wants to validate strategies, mentions "backtest", "trading strategy", "buy low sell high", "RSI", "MACD", "oversold", "overbought", "crypto strategy", "validate strategy", "backtest", "DCA", or similar.
Apache Doris table design and cluster sizing best practices. MUST USE when writing, reviewing, or optimizing Doris CREATE TABLE statements, partition/bucket strategies, data models, or cluster configurations. ALSO MUST USE whenever the doris-architecture-advisor skill produces DDL — apply the Pre-Flight Checklist to every CREATE TABLE before output. Also triggers on any workload design involving: IoT, analytics, dashboard, CDC, time-series, log analysis, real-time warehouse, point query, data platform, or any scenario where table design decisions are being made. Also triggers on replacing or migrating from legacy analytics/search/serving stacks such as Impala, Kudu, Elasticsearch/ES, Greenplum, Presto, HBase, Hive, Hadoop, Redis, or Lambda-style multi-engine data platforms, even when Apache Doris is not named explicitly. Also use when user provides an Apache Doris connection string or asks to get started. Also triggers on slow query investigation, query profiling, runtime performance diagnosis, tablet skew analysis, and table health checks — any scenario where runtime evidence (profile output, tablet distribution) informs optimization. Cluster lifecycle, billing, and networking are managed-service operations, out of scope here — use your platform's cluster-management console for those.
Run KQL queries against Fabric Eventhouse for real-time intelligence and time-series analytics using `az rest` against the Kusto REST API. Covers KQL operators (where, summarize, join, render), Eventhouse schema discovery (.show tables), time-series patterns with bin(), and ingestion monitoring. Use when the user wants to: 1. Run read-only KQL queries against an Eventhouse or KQL Database 2. Discover Eventhouse table schema and metadata 3. Analyse real-time or time-series data with KQL operators 4. Monitor ingestion health and active KQL queries 5. Export KQL results to JSON Triggers: "kql query", "kusto query", "eventhouse query", "kql database", "real-time intelligence", "time-series kql", "query eventhouse", "explore eventhouse", "show tables kql"
Quarterly earnings analysis for US stocks using SEC EDGAR financial data. Use when asked to: analyze a company's latest quarterly results; review Q1/Q2/Q3/Q4 earnings; check if a company beat or missed estimates; understand revenue, margin, or EPS trends; get a beat/miss breakdown; review guidance or management commentary after an earnings release. Triggers: "analyze AAPL earnings", "did MSFT beat estimates", "NVDA Q4 results", "earnings update for GOOGL", "how did Tesla do last quarter".
Comprehensive guide for NumPy - the fundamental package for scientific computing in Python. Use for array operations, linear algebra, random number generation, Fourier transforms, mathematical functions, and high-performance numerical computing. Foundation for SciPy, pandas, scikit-learn, and all scientific Python.
Read-only audit of one persisted skore report: `audit/NN_<stem>.py` (jupytext percent), 1:1 with `experiments/` and `journal/`. Do not execute it. Run `materialize.py` once. Never call `skore.evaluate` or `project.put`. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re-audit an experiment, a re-run overwrote the same `put()` key, or they want a narrative of a past experiment without `journal/ideas/` files. STOP when `status.setup.pending` is non-empty (load `setup-ml-project`), or when there is no approved design, no report, or no agent feature: explain and send the user to setup, `evaluate-ml-pipeline`, or `model-ml-pipeline`. Also stop for raw-data exploration or sourcing a future experiment. HOW TO USE: confirm journal, experiment, smoke, and report; place the file from `templates/audit.py`; copy `templates/materialize.py` to scratch; execute once; derive G-AUDIT-FINDING; then the continue-or-close gate. Resolve skore symbols with `api get`.
API reference for CoinMarketCap market-wide endpoints including global metrics, fear/greed, indices, trending topics, and charts. Use this skill whenever the user mentions market API, asks about fear/greed index, wants global metrics or BTC dominance data, needs k-line charts, or is working with market sentiment. This is the complete reference for CMC market-wide API questions. Trigger: "market API", "fear greed API", "global metrics API", "CMC charts API", "/cmc-api-market"
Use this skill to set up, create, or generate an academic calendar for Education Cloud orgs. Creates Academic Year, Academic Terms (semester/quarter/trimester), Academic Sessions, registration windows, and add/drop deadlines from natural language or documents. Validates date ranges and handles overlapping sessions, linking terms to the year and sessions to their term. TRIGGER when: user asks to "create an academic calendar", "set up semester dates", "generate the academic year", "add terms and sessions", "configure registration windows", or "add/drop deadlines" — or uploads a calendar document (PDF, CSV, XLSX) containing term or session dates. DO NOT TRIGGER for querying or updating existing calendar records, scheduling courses, or configuring course offerings.
Token on-chain analysis via Gate-Info MCP: holder distribution, on-chain activity, and large or unusual transfers (scopes holders / activity / transfers). Smart Money is not available in this version. Triggers include ETH on-chain analysis, BTC holder distribution, whale movements, large transfers. Route single-address tracking to gate-info-addresstracker. Tools: info_onchain_get_token_onchain, info_coin_get_coin_info.
Optimize machine learning model hyperparameters using grid search, random search, Bayesian optimization, and Hyperband to maximize model performance within a compute budget. Use when the user requests hyperparameter tuning or provides relevant inputs for this workflow.
Analyzes limit-up pools, strong stocks, consecutive limit-up structures, and newly listed stocks, distilling market sentiment, theme strength, and risk notes. Use when the user asks about limit-up pools, consecutive limit-ups, strong stocks, limit-up trading sentiment, theme heat, or needs a limit-up pool review.
Manages CockroachDB cluster capacity across all tiers. Self-Hosted covers node decommissioning for permanent removal and adding nodes for expansion. Advanced/BYOC covers scaling node count and machine size via Cloud Console, API, or Terraform. Standard covers adjusting provisioned compute (vCPUs). Basic auto-scales — guidance covers spending limits and cost management. Use when scaling capacity up or down, permanently removing nodes, or managing costs.
Best practices for MariaDB system-versioned (temporal) tables — automatic row history built into the database. Use when tracking data changes over time, implementing audit trails, meeting GDPR or compliance requirements, doing point-in-time queries, or when the user asks about row history, data versioning, temporal tables, or querying past data states in MariaDB. This feature is unique to MariaDB among MySQL-compatible databases.
Guide for using molt verify to compare source and target databases for schema and row-level consistency after a migration. Use when running verify commands, tuning concurrency/sharding, handling schema mismatches, or validating data integrity post-migration.
Builds Nango Functions (TypeScript createAction/createSync) with checkpoint-first sync patterns, action and sync references, project/root checks, deletion strategies, and a docs-aligned dryrun/test workflow. Use when creating or updating Nango actions or syncs.
Receive and verify Scrapfly webhooks. Use when setting up Scrapfly webhook handlers for async scrape, extraction, screenshot, or crawler jobs, debugging X-Scrapfly-Webhook-Signature verification, or routing on X-Scrapfly-Webhook-Resource-Type.
Create, edit, and troubleshoot RevOS segments — saved audiences defined over the org's semantic model — through the RevOS MCP server, and attach them to a table so its rows are scoped. Use this whenever the user wants to save, define, or change an audience or list ("companies with an active subscription", "deals over 50k in the EMEA pipeline", "users who ordered twice"), add or change a condition on an existing segment, show only some rows in a table ("only the stalled deals", "filter this table to…"), or asks why a segment is FAILED, empty, or showing the wrong rows — even if they never say the word "segment". Read it before the first api_write on the `segments` or `table-views` resource.
Map who a person knows from one LinkedIn profile URL, when you cannot see their connection list. Derives a per-person angle set from their own work history, education and posts, fans those angles out to parallel agents, merges and scores every candidate on evidence strength, resolves each row to a real profile and current employer, and ships a spreadsheet you can slice by where each person works today (a filterable people tab plus an employer x tier pivot). Works for any function (engineering, recruiting, sales, research, exec) and any career shape. Use for "who does this person know", "find connections of this LinkedIn URL", "map this person's network", "who is in their orbit", "who do they know at a company", "infer connections from job history and post engagement", /social-connections.
Use when improving or comparing Ultralytics YOLO models in Platform or code, or running hyperparameter search/autotraining — Platform experiment comparison, the systematic improvement playbook, model.tune() genetic evolution, Ray Tune, search spaces, and deciding whether tuning is worthwhile. For one training run and its arguments, see yolo-training.
Reliably consume Alpaca Broker API real-time event streams over Server-Sent Events (SSE): account status, journal, transfer/funding, trade, and non-trade-activity events. Covers connection, authentication, replay cursors (since / since_id / since_ulid), heartbeat and comment lines, reconnection/backoff, ordering, and idempotent processing. Use when building an event consumer for Alpaca lifecycle events in any language
Build investment systems in the style of AQR Capital Management, the quantitative investment firm pioneering factor investing. Emphasizes academic rigor, transparent methodology, and systematic factor exposure. Use when building factor models, conducting asset pricing research, or designing systematic portfolios.
Configures log and metric export for CockroachDB Cloud clusters to external monitoring services including AWS CloudWatch, GCP Cloud Logging, and Datadog. Use when setting up log export for audit compliance, configuring metric export for monitoring, or troubleshooting log delivery issues.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.