Discover agent skills
Every skill here was scanned and validated. Pick one, and your agent handles the rest.
Filters
420 skills match “data cleaning”
Git
Commits, branches, merges, and rebases Git repositories, resolves conflicts, and recovers lost history. Use when the work touches a repo, commit, branch, merge, rebase, stash, tag, or submodule; when Git refuses a command — index.lock exists, push rejected as non-fast-forward, detached HEAD, dubious ownership, unrelated histories, conflict markers left behind; when something looks lost after a hard reset, a bad rebase, a deleted branch, or a dropped stash; when splitting a mixed change, wording commit messages, cleaning history before review, or force-pushing without wrecking a teammate's work; when a credential or a huge file got committed; when setting up worktrees, hooks, LFS, sparse checkout, signing, or separate work and personal identities. Not for CI pipeline YAML (github-actions, gitlab) or for composing the pull request description itself (pull-request).
VMware Aria Operations
Use this skill whenever the user needs VMware Aria Operations (VMware VCF Operations in VCF 9+) data — metrics, alerts, capacity, anomalies, reports. Directly handles: resource metrics plus metric key/property/relationship lookup, list/acknowledge/cancel alerts with notes and recommendations, alert definitions, capacity forecasts, anomalies, reports, resource maintenance mode, Aria's own node health and adapter collection state. Always use this skill for "check vSphere capacity", "what Aria Operations alerts are active", "show VMware anomalies", "generate an Aria report", "rightsizing recommendations", "VCF Operations alerts", "put this host in Aria maintenance mode", "is Aria Operations still collecting from vCenter", "what does Aria recommend for this alert", or any Aria Operations / VCF Operations / vRealize Operations task. Do NOT use for real-time vCenter alarms/events (use vmware-monitor), VM operations (use vmware-aiops), or NSX networking (use vmware-nsx). For load balancing/AVI/AKO use vmware-avi.
mt5-httpapi
HTTP client for a user-deployed mt5-httpapi MetaTrader 5 bridge. Use ONLY when the user has explicitly installed and configured mt5-httpapi AND provided MT5_API_URL. Read endpoints (account, symbols, rates, ticks, server-side technical-analysis enrichment via the wickworks sidecar, history, backtest report fetching) are safe to invoke. Trade-mutating endpoints on /orders and /positions require explicit per-action confirmation showing symbol, side, volume, and SL/TP; terminal shutdown/restart also require explicit confirmation naming the target terminal and operation. Creating, changing or deleting a chart deployment (/deployments) or closing a chart starts or stops a live EA and needs the same confirmation. Never invoke mutations on inferred intent. Do not use this skill for generic market-data, charting, or trading questions where the user hasn't named mt5-httpapi.
Playwright
Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).
Project Artifact
Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions/FAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live state, redeploys the same URL, and reports only the delta. For software projects whose workstreams are PRs, also read swe.md (the X.Y PR-numbering convention; pulling PR state with gh/git; a per-PR detail block). Needs the built-in Artifact tool (claude.ai login). Not for single-PR changes or public docs.
SEO Audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.
OpenNews Financial Market News Skill
Real-time crypto, equities, macro, and financial market news aggregator — 85+ data sources across 6 categories covering digital assets, U.S. stocks, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals. Sources include Bloomberg, Reuters, FT, CNBC, CoinDesk, Twitter/X, Binance, Coinbase, OKX, Hyperliquid whale trades, price/funding/liquidation alerts, and 12 AI prediction signals. AI-analyzed with impact score, trading signals, and bilingual summaries. **Free tools available without token**.
JSON
Parses, validates, transforms, and designs JSON payloads that survive real parsers, real clients, and real data sizes. Use when a parse fails at a byte offset or on a trailing comma, an id or an amount loses precision, accents and emoji come back as mojibake, a field is null when it should be absent, duplicate keys silently win, a JSON Schema passes what it should reject or a `$ref` will not resolve, a multi-gigabyte file will not fit in memory, a jq, JMESPath, or JSONPath expression returns nothing, two documents must be diffed or patched, a webhook signature fails after the body was re-serialized, untrusted input must be parsed safely, or a response shape has to change without breaking existing clients. Covers NDJSON, JSON Patch, canonical form, JSON columns in SQL, and JSON5/JSONC config files. Not for constraining LLM output (`structured-output`), for YAML, TOML, XML, or CSV (their own skills), or for designing REST endpoints (`rest-api`).
Rust
Writes, debugs, and optimizes Rust code, crates, and Cargo builds: ownership, lifetimes, traits, async, unsafe, and FFI. Use when the borrow checker rejects code, when rustc reports value moved, cannot borrow as mutable, does not live long enough, missing lifetime specifier, trait bound not satisfied, or not dyn compatible; when a future cannot be sent between threads, a Mutex guard crosses an await, a task blocks the async runtime, or select! loses data; when code deadlocks, panics on unwrap, or hits BorrowMutError; when cargo builds are slow, features unify unexpectedly, two versions of one crate collide, or the build fails only in CI; when writing unsafe, C FFI, proc macros, serde derives, no_std firmware, or wasm; when cross-compiling to musl or another target; when profiling, benchmarking, or shrinking a Rust binary. Not for C++ or language-agnostic concurrency theory.
Elasticsearch
Designs, queries, and operates Elasticsearch: mappings, analyzers, query DSL, aggregations, bulk indexing, shard sizing, and cluster health. Use when writing a search query or an index mapping, when a search returns nothing or the wrong documents, when a term query on a text field returns zero hits without an error, when results rank badly, when aggregations fail with "fielddata is disabled", when the cluster turns yellow or red, when shards stay unassigned, when indexing is slow or a bulk request returns per-item errors, when disk hits the flood-stage watermark and indices go read-only, when circuit breakers trip, or when paging past 10,000 hits breaks. Covers ILM rollover, reindexing, snapshots, upgrades, kNN and hybrid vector search, autocomplete, synonyms and analyzers, nested modeling, geo queries, ES|QL, Painless, ingest pipelines, data streams, security, language clients, and OpenSearch compatibility. Not for standalone vector stores (vector-databases) or lightweight site search (meilisearch).
SQL Query and Schema Expert
Writes, reviews, and optimizes SQL queries; designs schemas, indexes, and constraints; plans migrations for any relational database. Use when a query is slow, EXPLAIN shows a sequential scan, or an index is ignored; when rows come back duplicated, missing, or with inflated totals after a JOIN; on deadlocks, lock timeouts, "too many connections", or transactions that never commit; when designing tables, keys, and column types, normalizing or denormalizing a model, or deciding between a JSON column and real columns; for ALTER TABLE on a live table, expand-migrate-contract rollouts, backups and restores, replication lag, connection pooling, partitioning, bulk CSV imports, and moving data between engines; for window functions, CTEs, keyset pagination, upserts, full-text search, multi-tenancy, row-level security, and timezone handling in MySQL, SQLite, MariaDB, or SQL Server. Not for PostgreSQL server internals such as vacuum tuning and work_mem sizing, and not for ORM schema modeling inside a framework.
Vue
Builds, debugs, and reviews Vue 3 apps: reactivity, components, composables, Pinia state, Vue Router, forms, and performance. Use when the UI does not update after a state change, a reactive object loses reactivity on destructure or reassignment, .value is forgotten, a watcher never fires or loops ("Maximum recursive updates exceeded"), props or v-model stop syncing, a template ref is null, SSR reports a hydration mismatch, a route param change does not reload the component, Pinia warns "getActivePinia() was called but there was no active Pinia", the console shows "Failed to resolve component" or "Extraneous non-props attributes", a thrown error blanks the page, a long list or large object makes typing lag, a chart or map library breaks after being put in ref(), scoped styles do not reach a child, or when migrating Vue 2 Options API to Composition API and script setup. Not for Nuxt-specific SSR, routing, and data fetching (nuxt), Vite build configuration (vite), or React and Svelte (react, svelte).
Nodejs
Builds, debugs, and hardens Node.js servers, CLIs, and npm packages: async, modules, streams, memory, and process lifecycle. Use when writing or reviewing code that runs on Node, when a process hangs or refuses to exit, leaks memory, gets OOM-killed, pins one CPU core at 100%, or dies on an unhandled rejection; when the error reads EADDRINUSE, EMFILE, ECONNRESET, ERR_MODULE_NOT_FOUND, ERR_REQUIRE_ESM, or "__dirname is not defined"; when import and require interop breaks, streams buffer everything in RAM, a server returns intermittent 502s behind a load balancer, or SIGTERM drops in-flight requests; when npm install, lockfiles, peer dependencies, workspaces, native module builds, or publishing misbehave; when a suite passes locally and fails in CI; or when containerizing, profiling, and shutting down a service cleanly. Not for browser-only JavaScript, TypeScript type-system design, or the Bun and Deno runtimes.
USPTO Database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
PubChem Database
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
Just Fucking Cancel
Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and provides cancel URLs. CSV-based analysis with optional Plaid integration for ClawdBot users.
Briefing
Daily briefing: gathers calendar (gcalcli-calendar), active todos (todo-management), and weather (openmeteo-sh-weather-simple) into a concise summary.
Competitor Profiling
When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,' 'competitor landscape,' 'competitor dossier,' 'competitive audit,' or 'research these competitors.' Input is a list of competitor URLs. Output is structured competitor profile markdown files. For creating comparison/alternative pages from profiles, see competitors. For sales-specific battle cards, see sales-enablement. For researching accounts you're selling to, see prospecting.
Fulcra Morning Briefing
Compose a personalized morning briefing using the latest fulcra-context skill for sleep, biometrics, calendar, activity, and weather context. Adapts tone and detail to how the human actually slept.
Open Broker - Hyperliquid Trading CLI
Hyperliquid trading plugin with background position monitoring and custom automations. Execute market orders, limit orders, manage positions, view funding rates, run trading strategies, and write event-driven automation scripts with automatic alerts for PnL changes and liquidation risk.
Huahua Daily
查询和分析花花日记中的基金持仓、行情、交易、量化与社区数据，并创建需要用户在 App 内确认的交易或批量导入请求。输入是本地图片、完整导出或大型文件时使用配套 huahua CLI。
Web Scraping
Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infinite scroll, or pages that require clicking/searching/filtering. Use when the user asks to scrape a site, collect listings, gather fields from many pages, monitor website changes, or turn webpage content into structured summaries/JSON/CSV.
Scrapling MCP
Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) to call the `scrapling` MCP server for execution; this skill provides strategy, recipes, and best practices.
Finishing a Development Branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work