Loading...
Loading...
Found 802 Skills
Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary metrics, the supported metric types (count, sum, ratio with `math` and `math_property`, retention with `retention_window_start` and `start_handling`), multivariate user handling ("Exclude" vs "First seen variant"), and how to read results once the experiment is live. Use when the user adds or edits a primary or secondary metric (e.g. "add a secondary metric tracking 'downloaded_file' per user"), sets up a ratio metric (e.g. "revenue from purchase_completed / pageviews"), sets up a retention metric (e.g. "$pageview → uploaded_file, 7-day window"), configures custom exposure (e.g. "only count users who hit /checkout"), changes multivariate handling, or asks "who is in the analysis?", "how do I measure impact?", "is this winning?", "what's the confidence level?", or "should I ship?".
Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics, revenue, customers, orders, trends, or any business data; user says 'how many', 'show me', 'what is the', 'top N', 'compare', 'trend', 'growth', 'breakdown'; user wants to explore, analyze, filter, aggregate, or summarize data from a database; agent needs to query data, connect a data source, handle errors, or manage MDL changes via the wren CLI.
Guides actuarial work for insurance and reinsurance—pricing and rate adequacy, reserving and IBNR, loss development and triangles, mortality/morbidity and lapse assumptions, experience studies and credibility, capital and risk metrics at overview level, product design tradeoffs (life, health, P&C, annuity), and regulatory reporting concepts (NAIC, IFRS 17, Solvency II overview—not legal advice). Use when the user mentions actuary, actuarial, IBNR, loss development, reserve analysis, mortality table, pricing insurance, experience study, IFRS 17, loss ratio, combined ratio, credibility, or asks for assumption documentation and model governance for insurance products—not generic FP&A (financial-analyst), investment banking valuation (comps-analysis, dcf-model), legal policy interpretation (commercial-counsel), clinical trials, software-only implementation (senior-software-engineer), or broad GRC without actuarial models (compliance-engineer).
Improve Coval trace quality after basic ingestion works. Use when traces are sparse, missing useful STT/LLM/TTS/tool spans, missing attributes needed for Coval built-in metrics, or when a customer wants maximum debugging and observability value from agent traces.
Analyzes Kubernetes resource usage metrics and historical data to suggest optimal CPU and Memory requests and limits. Use to reduce cloud costs, prevent OOMKills, and improve overall cluster reliability by right-sizing your deployments.
Quickly screen inbound deal flow — CIMs, teasers, and broker materials — against the fund's investment criteria. Extracts key deal metrics, runs a pass/fail framework, and outputs a one-page screening memo. Use when reviewing new deal flow, triaging inbound materials, or deciding whether to take a first call. Triggers on "screen this deal", "review this CIM", "should we look at this", "triage this teaser", or "deal screening".
Comprehensive portfolio analysis using Alpaca MCP Server integration to fetch holdings and positions, then analyze asset allocation, risk metrics, individual stock positions, diversification, and generate rebalancing recommendations. Use when user requests portfolio review, position analysis, risk assessment, performance evaluation, or rebalancing suggestions for their brokerage account.
Detect AI-generated code patterns ("slop") in PHP/Laravel and TypeScript/React source — comment narration, generic naming, premature interfaces, defensive overdose, mock-everything tests, and the absence of human "scars". Use when reviewing AI-assisted PRs, auditing code for taste/quality (not metrics — that's technical-debt), or hardening a code-review checklist. Triggers on "review for AI slop", "find AI patterns", "check code feels human", "audit code-quality taste".
Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / instructions.md / queries.yml / memory pairs, then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.
Workload-aware architecture design for Apache Doris. MUST USE when designing data architectures, choosing between data models, planning ingestion strategies, sizing clusters, or translating business requirements into Apache Doris system designs. Complements doris-best-practices with decision frameworks and sizing-first workflow. Use when user describes a workload involving: IoT, sensor data, telemetry, real-time analytics, dashboard, log analysis, log search, CDC sync, time-series, device monitoring, point query service, ad-hoc analytics, lakehouse federation, ETL/ELT pipeline, report analytics, clickstream, user behavior, observability, metrics, fleet tracking, or any OLAP workload requiring table design from scratch. Also triggers on prompts like: "design a table for...", "how should I store...", "build an architecture for...", "we have X devices sending data every Y seconds", "recommend a cluster size for...", "what data model should I use for...", "we need to ingest X GB/day", "migrate from MySQL/PostgreSQL to Apache Doris". Also use for legacy analytics/search/serving stack consolidation prompts even when Apache Doris is not named explicitly, including replacing or migrating from Impala, Kudu, Elasticsearch/ES, Greenplum, Presto, HBase, Hive, Hadoop, Redis, or Lambda-style multi-engine data platforms.
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**