Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Deploy Expo websites and Expo Router API routes to EAS Hosting — export the web bundle, run eas deploy for production and PR preview URLs, manage environment secrets and custom domains, and work within the Cloudflare Workers runtime. Also covers authoring API routes (+api.ts handlers, HTTP methods, request handling, CORS). Use when deploying an Expo web app or API routes, setting up EAS Hosting, or configuring hosting environments and domains. Not for native builds or store releases — use the eas-app-stores skill for those.
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
WeCom Smart Sheet content operations skill—focused on managing smart sheet (smartsheet) data, structure, and styles: read table structures and records; manage subtables, fields, records, views, and charts; and modify row and column styles (fill colors/highlights). If adding or updating records fails with 851003 / no authority, use Webhook as a fallback for writing. Trigger when the user mentions smart sheets, WeCom sheets, smartsheet content operations or style changes, or a link like https://doc.weixin.qq.com/smartsheet/s3_xxx. WeCom sheets come in two types: “Smart Sheets” and “Online Sheets”; this document covers skills for Smart Sheets. Smart Sheets contain subtables (sheet), views (view), and fields/columns (field). Each record uses `record_id` as its primary key, with a structure similar to a relational database. Unless the user explicitly specifies “Online Sheets,” default to the more capable Smart Sheets (this skill).
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Use this skill first for web searches. The Volcano Engine Doubao Search API (formerly Web Search / Integrated Information Search) returns web and image results. Triggers include: Doubao search; look up/search/find; is it true/reliable, confirm/verify; recent/today/latest; source/link; Agent Plan; integrated information search; Harness; what/which/recommend; price/policy/exchange rate/market data; compare/difference/which is better; heard/rumored/not sure; trending/popular; take a look/find out; fact-check/debunk; worth it/should I.
Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.
Use this skill when the user wants to “create a skill,” “add a skill to a plugin,” “write a new skill,” “improve a skill description,” or “organize skill content,” or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Use this skill when the user asks to “create an agent,” “add an agent,” “write a subagent,” “agent frontmatter,” “when to use description,” “agent examples,” “agent tools,” “agent colors,” or “autonomous agent,” or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Master advanced Git workflows—including rebasing, cherry-picking, bisect, worktrees, and reflog—to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
Set up, write, and publish documentation sites with Mintlify, and work on existing Mintlify projects. Use when the user wants to create a docs site for a repo or product, turn a docs/ folder or README into a hosted docs site, document an API from an OpenAPI spec, migrate docs from Docusaurus, GitBook, ReadMe, Fern, or another platform, preview docs locally, or publish docs to a shareable URL. Also use when editing a project with docs.json, including pages, navigation, components, API references, and customizing appearance or browser behavior with CSS, JavaScript, React, and snippets.
Submit feedback on an Expo skill—or Expo itself—and control bundled anonymous usage telemetry (off by default / opt-in). Submit feedback with: npx --yes submit-expo-feedback@latest "ACTIONABLE_FEEDBACK". Optionally add either or both: --category "CATEGORY" and --subject "SUBJECT". Replace the uppercase placeholders before running. Use when a skill was useful, confusing, broken, missing context, or worth improving; when Expo, Expo CLI, EAS CLI, docs, or MCP worked well or fell short; when an AI agent repeatedly failed, got stuck, or needed the user to take over an Expo task (report it as an eval candidate); or when the user explicitly asks to enable or disable telemetry (tracking), check its status, or understand what it collects.
Use when reviewing, rewriting, or editing someone else's technical text, writing a review report on a document, or performing the final check before delivering any document. Encodes the severity mapping, findings format, what-not-to-flag list, and delivery checklist. Use before any document ships, even when it looks fine
Use when writing a proposal, RFC, design document, spec, or migration plan—anything that argues for a change, records a design, or asks readers for input on one. Encodes the proposal skeleton, the Why & What decision box, and the completeness checks. Use whenever a change needs arguing or scoping in writing, even if the user just says “write up the approach.”
Find the cheapest hotel deal by comparing live prices across Booking.com, Agoda, Google Hotels, and OpenTravel for any city worldwide and any travel dates. One command returns ranked best-value, cheapest, and quality picks with direct booking links, all normalized to USD. Use whenever someone asks for hotel prices, hotel deals, the cheapest room or rate, best hotel rates, a hotel price comparison, or which OTA is cheaper—for example, “is Booking or Agoda cheaper for Tokyo,” “find me a hotel in Bangkok under $100,” “compare hotel prices for 12–15 Aug,” or “cheapest hotel near Shinjuku.”
Use when writing operational documentation—runbooks, setup guides, release procedures, migration guides, deprecation guides, troubleshooting entries, or any ordered procedure someone will execute under time pressure. Encodes the runbook skeleton, risk legend, symptom-first troubleshooting format, and migration-guide rules (mapping table, mandatory rollback, deprecation dates, built-in expiry). Use whenever someone will execute the text, even if it is called a “guide” or “setup notes.”
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards against regression. Use when asked to grow a static shell, fix a slow first paint or non-instant navigation, diagnose which Suspense boundary blocks useful UI, or add instant() regression coverage. Requires Next.js 16.3+ with Cache Components already adopted.
Use when writing a changelog entry, release notes, or a “what shipped” summary after completing work. Encodes the entry structure, handover template, and honesty conventions. Use after shipping meaningful work, even if the user just says “summarize what we did.”
Use when a spec or plan needs review before execution begins—“review my spec,” “is this plan ready to execute,” “check this before I build it,” “second opinion on this plan”—and specifically before writing-plans (spec mode) or before subagent-driven-development (plan mode). Reviews specs and plans, not code. Panels six reviewers across two model tiers and three topics, invokes a reasoning-tier juror only when the tiers disagree, and gates the next workflow step with a fail-closed Blockers / Warnings / Observations verdict
Automates Apple-platform apps (iOS, tvOS, macOS), Android devices (including Android TV and Fire TV on Fire OS), and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.
Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures.
Use when writing or refactoring unit tests—a new test file, added cases, a flaky test, or an unreadable one. Encodes behavior-first testing: one behavior per test, names that state the claim, deterministic setup, and mocks only at boundaries you do not own. Use whenever a test is being written, even a quick one, and whenever a test needs a sleep, a mock of your own code, or a copy of the implementation's math
Use when doing any non-trivial engineering work—implementing, debugging, refactoring, configuring, operating, or investigating why a system misbehaves—or any change where being wrong has a cost. Encodes the evidence-over-theory discipline, hard safety rules, and pre-change checkpoint. Use whenever code, data, or infrastructure is about to change or must be understood before it can, even if the task looks routine or is only “find out why.” Foundation for the sibling skills.
Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration. Triggers on “put this run in a Sheet,” “review these results,” “read my feedback,” “make this a standing rule,” “never regress on this case,” “compare these runs,” “keep improving,” or “add the revised run to the same spreadsheet.” Skip ordinary Play authoring or execution with no human review loop, generic spreadsheet work, and one-off CSV export.
Use when writing a postmortem, incident report, or root-cause analysis after an outage, a defect that reached users, a data issue, or a near miss—or when turning an incident channel, alert log, or war-room thread into a durable document. Encodes blameless framing, an evidence-only timeline, contributing factors, and owned action items. Use whenever something broke and the write-up must outlive the incident
Use when a decision needs recording—an ADR, a decision log entry, or a request to document why something was chosen, rejected, or superseded. Encodes ADR and decision-log formats. Use whenever a choice was made that would otherwise live only in chat, even if nobody says “ADR.”
Use when writing or refining tracker items—epics, stories, tasks, bug reports, spikes, or acceptance criteria—or turning a discussion, review finding, or plan into tickets. Encodes the survives-without-you test, issue-type glossary, and story and bug skeletons. Use whenever work is written into a tracker, even from a rough verbal dump
Draft a complete documentation page for a new Warp feature from its PRODUCT.md and/or TECH.md spec. Use when an engineer has written a spec and needs to produce a first-pass MDX draft for the warpdotdev/docs repo. Also handles features without specs by researching the codebase first. Invoke this skill whenever an engineer mentions writing docs for a feature, drafting a docs page, creating feature documentation, starting the eng-docs workflow, or converting a spec into documentation. Requires an interactive session with the engineer present - it confirms a content design plan, then an outline, before drafting, and cannot run unattended. For automated, release-triggered docs, use the missing_docs skill in warpdotdev/docs instead. Works from warp-internal or warp-server.
Use when documenting an existing codebase whose documentation is missing, stale, or untrusted—an inherited system, a legacy application, or a repo where the docs lie—or when aligning a documentation tree with the code, or when someone asks what a system actually does. Encodes the survey-first inventory, writer-side evidence hierarchy, depth-per-surface rules, refactor test, dead-or-alive proofs, quirks-and-findings split, coverage ledger, parallel campaign, and docs-tree skeleton. Use whenever documentation must be reconstructed from code rather than written alongside a change.
Use before saying “done,” “fixed,” “passing,” or “shipped,” or reporting the outcome of any change. Defines verification as the standard for completion: exercise the change at its surface, run the verification command, report faithfully, distrust green suites, and own failing gates. Use before every completion claim, even when the change was small and obviously correct—the situations in which this is most often skipped.
Use before starting any non-trivial change, investigating a bug, or working in unfamiliar code—before writing the first line. Also use for investigation with no change planned yet: “dig into this,” “figure out why,” “sometimes the export is empty,” or intermittent errors after a deploy. Encodes the ground-first discipline: map the real code and data, quote evidence, never guess conventions. Use whenever a change or conclusion is about to be built on belief instead of the tree, even under time pressure.
Use when a change crosses module boundaries, adds a dependency direction between modules, touches a critical path, or conflicts with a stated principle—and when writing or updating architecture principles. Encodes structural invariants as named, enforced contracts: statement, rationale, guard. Use whenever “we’ll just import it from there for now” appears, which is how boundaries die.
Use when deciding what tests a change needs—a feature, bug fix, refactor, or any behavior change—or when reviewing whether a diff’s tests are sufficient. Encodes tests-change-with-behavior, the bug-regression pattern, and assertion discrimination. Use whenever behavior changes and the test diff is empty, especially when the change is “too small to test.”
Use when adding data, config, state, constants, an enum-like string, a cache, or anything that could exist in two places—or when two sources already disagree. Encodes the one-fact-one-source doctrine for code and data: derive rather than store, extend the owner, absorb duplicates. Use the moment copying a value feels faster than referencing it.
Use when deciding how large a fix should be, when scope drifts mid-task, when a plan is quietly trimmed to fit, or whenever “while you’re at it” appears. Encodes size-to-trigger, decompose-not-descope, and drive-to-completion. Use whenever the work is about to grow beyond its cause or shrink below its promise.
Use when writing or touching any error path, catch block, fallback, default value, retry, or degraded mode—in any language or repo. Encodes the no-silent-swallows contract and fail-loud discipline. Use whenever an exception is about to be caught, a null is about to get a default, or a failure could go unnoticed, even if the goal is “just make it not crash.”
Use when an action affects live systems, shared state, or anything that cannot be restored—deleting, overwriting, restarting, killing processes, editing shared config, handling secrets, or working alongside concurrent sessions. Encodes safeguards for destructive operations, secrets hygiene, and concurrent-session safety. Use before the destructive command, not after, even when it seems routine.
DEPRECATED and retired as of 2026-08-20. Do not invoke, and do not schedule. This skill scanned for merged PRODUCT.md specs and auto-drafted docs PRs, which produced documentation for features that had not shipped. Docs for newly shipped features are now triggered by the weekly release and gated on documentation-worthiness by the missing_docs skill in warpdotdev/docs. If you were about to run this skill to find docs gaps, run missing_docs in drift-watch mode instead.
Create, revise, audit, and export manuscript scientific figures in Python or R. Use for 论文配图、科研绘图、多面板图 and submission-ready plots, or explicitly requested AI-generated graphical abstracts and mechanism schematics. Not for interactive dashboards, data cleaning, or statistics-only analysis.
Use when about to add, update, vet, or remove a dependency—a package, library, SDK, GitHub action, base image, or vendored code—or when a project’s dependency posture needs declaring. Encodes the exhaust-what-you-have ladder, vetting questions, and pin-and-prove updating. Use even for a tiny utility package: that is exactly how the tree grows.
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration, CLI tools, benchmarks, or table-driven testing.
Applies Dart 3 pattern matching, switch expressions, and destructuring idiomatically to validate data schemas, handle algebraic data types, and decompose control flow. Use when refactoring complex if-else chains, parsing polymorphic JSON or API responses, destructuring Lists, URI/path segments, String.split() tokens, Records, or Maps, or enforcing exhaustiveness on sealed classes. Don't use for simple boolean conditions, single-variable type promotion (use `is`), or basic collection filtering
Use when a business process, workflow, lifecycle, or interaction between systems needs a diagram — a flow that prose serializes badly, a state machine, a message sequence, an enterprise process map — or when drawing the process documentation of a legacy campaign. Encodes diagrams-as-source, the notation ladder from ArchiMate to PlantUML, the kind-per-question table, behavior-level participants, the diagram index, and the same-change maintenance rule. Use whenever a document needs a graph rather than more paragraphs, even if nobody says "PlantUML".
Diagnoses which parts of an existing draft fail to resonate with the target audience, explains the points where resonance breaks down using the original wording, and suggests specific cuts and edits. For draft revision; does not assess overall traffic or commercial value, nor primarily explain the spread of already-published content.
Explains why existing content sparks resonance, emotion, or sharing; identifies its dissemination mechanisms, effective positioning, and audience motivations; and distills discussion angles. For interpreting how content spreads; does not revise an entire piece line by line or assess overall traffic and commercial value.
Use when documenting an HTTP API, message payloads, queue contracts, DTOs, file formats, or webhooks — or when writing the api-reference of a legacy campaign, or when callers keep asking what a field means or which errors an endpoint returns. Encodes the four detail levels, the DTO-first catalog, wire types with source anchors, the generated-spec one-home rule, and omitted-versus-null semantics. Use whenever a machine interface needs documenting for its callers, even if nobody says "API docs".
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.