Loading...
Loading...
Found 9,307 Skills
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.
Capability discovery and current-state verification for Heavy Path, ambiguous repo/runtime ownership, and runtime-dependent Standard Path work.
Use when writing or reviewing Move smart contracts on Sui. Applies to naming structs, error constants, regular constants, events, getter functions, capability types, hot potato types, and dynamic field keys. Use whenever creating new types, functions, or constants in Move code.
This skill should be used when the user wants to bulk-build ArcKit artefacts in parallel rather than running individual /arckit:* commands one at a time. Load whenever the task sounds like 'kick off a build', 'build everything', 'generate all artefacts', 'run all the commands', 'rebuild this project from scratch', 'resume the build', 'pick up where we left off', 'refresh the artefacts', 'run the recipe', 'build the whole project end-to-end', or 'parallel build', or mentions `--plan`, `--resume`, `--target`, `--refresh`, `--recipe`, or `.arckit/state.json`. The skill orchestrates parallel /arckit:* generation using subagent isolation: reads project state, computes the artefact dependency DAG, dispatches one subagent per target per wave (each subagent invokes a /arckit:* skill in its own context), validates outputs, commits the wave, and persists progress to .arckit/state.json for resumability.
Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Two responsibilities — (1) place the project's `ruff.toml` from the bundled template once the stack and workspace are in place, and (2) run ruff against any Python files Claude has just generated or edited. Stops at "the touched files pass `ruff check`." TRIGGER when (any of these): (1) a Python file was just created or edited via Write / Edit / MultiEdit — invoke this skill before declaring the task done so ruff is run on the touched files; (2) a fresh ML workspace was just scaffolded by `organize-ml-workspace` and the project has no `ruff.toml` at its root yet — drop the bundled template; (3) the user asks about lint, format, docstring style, or reaches for `black` / `isort` / `flake8` / `pydocstyle` (redirect to ruff — the stack's canonical linter, owned by `data-science-python-stack` Tier 1). SKIP when: the project is non-Python; the only edits in this turn are to Markdown / TOML / JSON / YAML; the file lives in a third-party vendored directory the user doesn't own. HOW TO USE: run ruff manually on the files you just touched — do not configure a PostToolUse hook for this. **Read the "Stop conditions" block and emit the Pre-flight checklist as visible text in your response — both are mandatory before running ruff.**
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.**
When the user wants to build or improve a sales bot's ability to create handoff summaries and conversation notes. Also use when the user mentions "conversation summary," "handoff notes," "call notes," "CRM updates," or "conversation documentation."
When the user wants to build or improve a sales bot's ability to pull in firmographic or contact data mid-conversation. Also use when the user mentions "data enrichment," "lead enrichment," "pulling company data," "contact data lookup," or "real-time data."
Usar al pedir implementar, desarrollar o ejecutar trabajo referenciado por una historia de usuario o tarea. Solo debe usarse si la historia o tarea se encuentra en estado `Ready`. Activar tambien cuando el usuario mencione "ejecutar tareas", "codificar", "desarrollar la US", "trabajar en el TK" o cualquier variante que implique escribir codigo para una historia o tarea ya especificada.
Fetch official brand/product/tool logos (Stripe, GitHub, Notion, AWS, Figma, etc.) as clean SVGs from SVGL (svgl.app) — as saved .svg files, inline markup, or installed React components. Check this whenever logos or SVGs come up, e.g. adding brand marks to integration/partner rows, footers, pricing tables, or slides; replacing a blurry logo with a vector; getting light/dark variants; or finding an official logo. Prefer it over hand-writing SVG markup or grabbing random files. Skip for generic UI icons, illustrations, charts, favicons from an existing logo, or designing a brand-new custom logo.
Review generated or changed WordPress code — plugins, themes, and blocks — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WordPress APIs: add_action/add_filter, shortcodes, meta boxes, AJAX handlers, REST routes, WP_Query or $wpdb, widgets, or WP-CLI commands. Use on 'review this plugin', 'is this safe to ship', 'make this translatable', 'speed up this query', or after tasks like 'write a plugin' or 'add an endpoint/shortcode/meta box'. Enforces escaping and sanitization, nonces plus capability checks, prepared database queries, core-API-first development, translation-ready strings, and query/caching discipline. DO NOT USE for WooCommerce-specific order, product, or checkout logic (use woo-guard), non-WordPress PHP, generic code quality review (use clean-code-guard), test code review (use test-guard), server or hosting configuration, or conceptual WordPress questions.
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.