Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Dung khi bat dau lam viec voi mot san pham hoac khach hang moi — skill nay tao FILE CONTEXT ma hon 60 skill khac se doc, gom san pham, khach hang, dinh vi, proof, objection, brand voice va KPI. Chay mot lan, dung lai mai ve sau. Kich hoat khi user nhac 'tao context', 'setup product marketing context', 'bat dau du an moi', 'AI chua hieu san pham cua toi', 'khai bao thong tin san pham'. Khong dung cho — context cho thuong hieu CA NHAN thi dung skill 22-personal-brand-context; nghien cuu insight sau thi dung skill 09-insight-khach-hang.
Maintain a project's canonical terms and settled decisions that future work should reuse, and record follow-ups a session discovers but does not resolve. Use when project-specific terms are being clarified, when a choice that may constrain future work is being considered or settles, including during planning, or when a session applies a temporary workaround whose root cause stays open or observes an out-of-scope defect with evidence. Do not use for simple definitions, routine implementation details, or carrying out an already-settled decision.
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.
Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.
Guidance for the Microsoft Purview Unified Catalog (data catalog) — business-friendly discovery, governance domains, data products, glossary terms, and data quality on top of the Data Map. Covers governance domains, data products, and curation. WHEN: Purview data catalog, unified catalog, data products, governance domain, business glossary, data quality, data discovery for analysts, curate data assets, data stewardship.
Python bridge to ImageJ2/Fiji for macros, plugins (Bio-Formats, TrackMate, Analyze Particles), NumPy↔ImagePlus/ImgLib2 exchange, and ImageJ Ops. Automates Fiji headlessly from Python. Use scikit-image for pure Python without Fiji plugins; napari for visualization.
Provides comprehensive guidance for pytest testing framework including test writing, fixtures, parametrization, mocking, and plugins. Use when the user asks about pytest, needs to write Python tests, use pytest fixtures, or configure pytest for Python projects.
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
Pipeline skill for computing HEDIS quality measures from claims and clinical data. Use when the user asks to calculate HEDIS measure rates, check continuous enrollment, build denominator/numerator logic, detect care gaps, compute utilization rates, identify high-cost claimants, or score risk stratification indices. Triggers include "calculate HEDIS", "measure rate", "continuous enrollment check", "care gap detection", "denominator query", "numerator logic", "utilization rate", "high-cost claimant", "Charlson score", "LACE score", "claims analysis", "quality measure SQL".
React component composition patterns for building flexible, maintainable UIs. Covers compound components, context-based state, explicit variants, and React 19 APIs. Use when designing component APIs, refactoring prop-heavy components, or building reusable component libraries.
Debug React applications by inspecting components, props, and the component tree. Use when the user is debugging React apps, wants to inspect component props/state, find which component renders an element, or understand the React component hierarchy.
React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, useFieldArray, the subscribe() API, and the Watch / FormStateSubscribe / FieldArray render-prop components. Covers RHF 7.82 additions including resetDefaultValues() and the disabled field-array option. Use this skill when building client-side controlled forms with the React Hook Form library. This skill does NOT cover React 19 Server Actions, useActionState, or server-side form handling (use the react-19 skill for those).
Provides comprehensive guidance for React Hooks including useState, useEffect, useContext, useReducer, useMemo, useCallback, custom hooks, and hook patterns. Use when the user asks about React Hooks, needs to use hooks in functional components, create custom hooks, or optimize hook performance.
Convert any React component/app into an Axure-importable prototype component, generating spec-compliant configuration declarations and runtime wrapper code. For cases where an existing React project needs to be exported as an Axure interactive prototype.
Working with the redis-docs MCP server (search / fetch / ask at redis.io/mcp)—how its index is shaped and how to read what it returns. Use when those tools are available and you are about to look something up in the Redis documentation, or when a result is confusing—fetch returned one short section instead of a page, several hits share one url, ids look like #sec:w1, metadata.version reads 1.0.0, a search came back empty, or ask was rate-limited or said the docs do not cover it. Also covers what redis.io does and does not index
Based on the target job JD, a Chinese resume, and the user's confirmed real experience, this skill completes JD parsing, evidence mapping, gap diagnosis, material follow-up questions, tailored resume rewriting, ATS/HR/interviewer review, and application communication material generation for job hunting in mainland China. It is used for new graduates, experienced hires, career changers, and roles in internet, AI, product, operations, sales, technology, data, design and more; use it when the user asks to optimize a Chinese resume for a JD, improve match rate, generate talking points for Boss Zhipin or headhunters, or check interview consistency.
Professional resume builder with PDF export, ATS optimization, and analysis capabilities. Use when users need to (1) Create new resumes from scratch, (2) Customize/tailor existing resumes for specific roles, (3) Analyze resumes and provide improvement recommendations, (4) Convert resumes to ATS-friendly PDF format. Supports chronological, functional, and combination resume formats.
This skill MUST be used when the user wants to infer product attributes from review files, score product quality, and deliver a Word (.docx) report, or explicitly requests review-scoring-docx. Triggers include 「評論評分 Word」、 「產品屬性比較報告」 with Word output, and reviews-to-scores-to-docx. It SHOULD be used for review-based product comparisons whose agreed deliverable is Word. It MUST NOT force Word output for general review analysis or substitute quality scores for attribute salience.
Review a Remotion video with AI vision. Starts with a cheap local check of rendered still frames, then has TwelveLabs watch the full render and score it against a JSON rubric (pacing, composition, text legibility, audio sync and more) with timestamped fixes, applies the fixes and re-reviews. The feedback loop that closes the production circle
Use when reviewing or judging a finished api-spec—the engineering wire contract (operations, request/response schemas, auth, error model, pagination, versioning, examples)—to decide whether a client can call every operation and a server can implement it from the contract alone. An acceptance gate, not authoring. Judges a single-sourced 11-condition contract-completeness bar: style + base + versioning + deprecation policy; every operation listed + traced; every operation fully typed on both sides + status codes (happy-path-only fails); auth + per-operation authorization; a complete error model (one shape + every failure case + retryability); shared types referencing the data-model; pagination + a tie-breaker; examples matching the schemas; one-directional vs the api-reference; consistent with the shipped API; delta-scoped amend. Style-agnostic (REST/GraphQL/gRPC, no OpenAPI reflex). Emits exactly `VERDICT: approve|revise`. Not authoring, the data-model, the api-reference, or generic design docs (design-review).
Use Riverpod mutations for UI-driven async operations like form submit; Mutation.run, MutationIdle/Pending/Success/Error, Mutation.reset, keyed mutations. Use when showing loading/error/success for a single action (e.g. submit button) without polluting provider state. Use this skill when the user asks about mutations, loading state for actions, or form submission with Riverpod.
Persist Riverpod notifier state offline with Storage and persist(); riverpod_sqflite, JsonPersist, key, destroyKey, cache duration, testing with in-memory storage. Use when saving state across app restarts or offline. Use this skill when the user asks about offline persistence, persisting state, or Riverpod storage.
Override Riverpod providers for tests, debugging, or environment-specific behavior; ProviderScope and ProviderContainer overrides, overrideWith, overrideWithValue. Use when mocking providers in tests, injecting different implementations, or scoping provider behavior. Use this skill when the user asks about overrides, testing Riverpod, or mocking providers.
Reduce rebuilds with ref.watch(provider.select(...)); select a subset of state so widgets rebuild only when that part changes. Use when optimizing performance or when a widget uses only one field of a large object. Use this skill when the user asks about select, reducing rebuilds, or optimizing Riverpod watch.
Use when driving or inspecting Roblox Studio through the Studio MCP tools — running Luau in Studio, play/stop, screenshots, reading/searching the datamodel or scripts, generating meshes/materials/models, inserting assets, moving the character, or when the MCP link is dead (no Roblox tools show up). A capability menu + gotchas + connection troubleshooting.
Use this skill to stand up an Android instrumentation test source set with the canonical `AndroidJUnit4` runner, the correct `AndroidJUnitRunner` Gradle wiring, and supporting infrastructure (Test Orchestrator, runtime permission grants, size annotations, SDK suppression, hermetic animation defaults). Covers `androidx.test:core:1.7.0` / `:runner:1.7.0` / `:rules:1.7.0` / `androidx.test.ext:junit:1.3.0` coordinates, `androidx.test.platform.app.InstrumentationRegistry`, and the `androidTestUtil` configuration trap for `androidx.test:orchestrator`. Use when the user reports `Test runner not found`, `AndroidJUnit4 deprecated`, `InstrumentationRegistry deprecated`, asks "why is my orchestrator not running", "how do I pass `-e` args to the test", "how do I grant a runtime permission in a test", or "instrumented test won't compile".
Use when the user installs or starts using Runway Dev, needs to sign in or create a Developer Portal account, connect Dev MCP, verify account/project access, or finish setup after a developer_not_found error. Guide the user through the browser steps and continue with the task once setup succeeds
Sa-Token advanced security features skill. Covers secondary authentication (safe-auth second verification), account bans (full ban / categorized ban / graduated ban), impersonating others and identity switching, multi-account authentication (StpUserUtil/StpKit), global listeners (login/logout/kick-out/ban/renewal events), global filters (SaServletFilter/SaReactorFilter), password encryption (MD5/SHA1/SHA256/AES/RSA/BCrypt/TOTP), session queries (terminal list / global Token search), Http Basic/Digest authentication, firewall (IP allow/deny lists / rate limiting), custom authorization annotations, dynamic route authorization, reverse-proxy URI repair, async Mock context, and data architecture Redis key-value design. Use when the user needs to implement second verification for sensitive operations, graduated account bans, simulated user operations, multiple account systems (separate User/Admin), global event listeners, or password encryption tools. For basic login authentication, use the sa-token skill.
Sa-Token API security defense skill. Covers API parameter signing (sa-token-sign) for tamper and replay protection (the four-step evolution of timestamp+nonce+sign), API Key (sa-token-apikey) partial authorization and Scope control (revocable / rights-restrictable), and temporary Token (SaTempUtil, embedded in the core package) for short-lived link invitations. API signing supports multi-application (multi secret-key) mode and multiple digest algorithms (md5/sha256/sha512). API Key supports multi-account systems and a database persistence mode. Temporary Token supports prefix trimming, reverse lookup, and JWT integration. For basic login authentication, use the sa-token skill first.
Specialized skill for Sa-Token SSO single sign-on. Covers complete solutions for three SSO modes: mode one (same domain + shared Redis/Cookie), mode two (cross-domain + shared Redis/URL redirect), mode three (cross-domain + separate Redis/Http ticket). Setting up the SSO-Server authentication center, SSO-Client integration, single sign-out, custom login pages, frontend-backend separated SSO (H5 approach), message push, anonymous clients, domain validation, NoSdk non-Java integration, custom API routes, platform center redirects. Use when the user needs unified login/logout across multiple systems, to set up a single sign-on authentication center, or cross-domain SSO integration. For basic login authentication, use the sa-token skill first.
Multi-client outbound for lead gen agencies — infrastructure architecture, client isolation, domain strategy, warmup at scale, white-labeling, unified reporting, client onboarding playbooks, and cross-client operations. Use when one client's domain reputation is dragging down others, new client onboarding takes too long, mailbox warmup isn't scaling across clients, can't isolate sending infrastructure per client, or need a repeatable playbook for agency-wide reporting. Do NOT use for Smartlead-specific platform config (use /sales-smartlead), single-domain deliverability (use /sales-deliverability), or individual campaign strategy (use /sales-cadence).
Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.
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.