Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user needs to judge whether a company's culture is good or bad — whether for investment decisions, job hunting, or partnership evaluation. Typical triggers: the user says "how's this company's culture", "how do I tell if a company is trustworthy", "is this company worth joining/investing in", "what's the founder/CEO like". Core framework: 本分 (do the right things + stop immediately once you find you're wrong) + 平常心 (cut out distractions and return to essentials) + 诚信 (integrity as a zero-tolerance bottom line) + 消费者导向 (end users first). Not applicable to: pure financial analysis, short-term speculative decisions, pure technical evaluation.
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
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.
Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user asks for "today's AI news", "AI updates", "latest AI developments", or mentions wanting a "daily AI briefing".
Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".
CSS component library for Tailwind CSS 4 providing pre-built UI components with semantic class names. Use when building web interfaces with HTML/Tailwind that need: (1) Rapid UI development with consistent styling, (2) Accessible component patterns (buttons, forms, modals, etc.), (3) Theme-aware color systems that work across light/dark modes, (4) Responsive layouts with Tailwind utilities. Works with daisyUI v5+ which requires Tailwind CSS v4+.
Analyze datasets using Python with pandas, numpy, and visualization libraries. Generates statistical summaries, identifies patterns, creates charts, and provides insights. Use when analyzing CSV/Excel files, exploring data, creating visualizations, or when users mention data analysis, statistics, charts, or datasets.
QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility
50+ chart types with selection criteria, dashboard composition, data tables, KPI cards, sparklines, heatmaps, and accessible data presentation, with React code (Recharts, D3, Nivo) and data-viz tokens. Use when designing charts, dashboards, or any data-dense screen.
Design and audit data warehouse metrics layers, semantic models, KPI definitions, source lineage, grain, dimensions, ownership, freshness, quality tests, backfills, access, dashboards, finance/product reconciliation, and metric change control. Use when teams need trusted metrics instead of duplicated BI formulas.
Explore SQLite and PostgreSQL databases: list tables, inspect schemas (columns/types/constraints), preview data, generate Mermaid ER diagrams, and run safe read-only queries. Triggered by requests to explore a database, view table structures, describe tables, generate diagrams, or query data, and by keywords like database exploration, schema, ER diagram, or SQL query.
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
Dating master: an emotional insight and coaching system based on pragmatics (Grice), attachment theory (Bowlby/Gottman), and signaling game theory (Spence). It sees the whole of a relationship from a god's-eye view, pinpoints the essence of the problem, and gives a clear direction. The user pastes a chat log or describes a romantic scenario, and it outputs the other person's true intent, a diagnosis of the relationship dynamics, an assessment of signal quality, and action guidance. Trigger words: 「情场高手」「帮我看看」「分析一下」「这段感情怎么办」「ta什么意思」「dating decoder」 Research date: April 2026.
Use for debugger-driven runtime root-cause analysis in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, and other GameDev or mixed-language projects. Trigger when runtime state or control-flow evidence is needed — actual values, branch taken, call order, thread context, whether execution reaches a chosen line — and cannot be derived confidently from source or logs; when pinning the relevant path would otherwise mean reading many files or tracing a deep call chain; or on an explicit request to debug, set breakpoints, step, or inspect runtime values. Do not use for compile-time or syntax errors, source-obvious bugs, failures already pinpointed by logs/tests, or code merely named debug/Debugger.
Apply systematic debugging, profiling, and root cause analysis across codebases and technology stacks. Use when investigating bugs, flaky behavior, crashes, stack traces, production issues, memory leaks, performance regressions, or any unexpected behavior where guessing would waste time.
Research a topic deeply across multiple sources and produce a sourced, bite-sized brief the user can read in 5 minutes. Use this whenever the user says 'research,' 'deep dive on,' 'tell me about,' 'what's the latest on,' 'do a brief on,' 'TL;DR of [topic],' 'catch me up on,' or asks about something they want to understand quickly but well. Works for AI tools, companies, people, technical concepts, market trends, news events, scientific topics. Output is a markdown brief with sources, pros/cons, and your read on what matters.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
Build a deposition preparation outline for a witness — extract their relevant documents from case materials, organize points around the case theory, and surface impeachment material. Use when the user says "prep [witness] for deposition", "build a hearing outline", or "prepare [name] for a pre-hearing conference/trial".
Before starting a nontrivial task, compute how much understanding the work demands and split it into "already understood" vs "learn first". Use when the user invokes /depth-check, asks "what do I need to understand before touching this?", "이거 시작하기 전에 뭘 알아야 해?", "어디까지 파악하고 들어가야 해?", or is about to start work in territory they may not know well. Maps the task's blast radius, grades the depth each area requires, and emits the short list of questions to answer before coding.
Visual identity development and validation through the official `DESIGN.md` schema and CLI. Use when creating, refreshing, syncing, previewing, exporting, or diffing design tokens. Not for page layout, rendered variants, product copy, feature specs, production code, or code review.
Synchronize every user story in a revised design document with one canonical GitHub Issue and milestone. Use for creating, updating, or resuming story issues from a design doc, including feature-delivery. Existing issues are updated in place and changed completed stories are reopened.
Detect Mimikatz credential-dumping activity via command-line pattern matching, LSASS access signatures, binary/hash indicators, and in-memory detection of known Mimikatz modules. Use when threat hunting for T1003 credential access, triaging EDR/SIEM alerts on LSASS access, scoping compromise during incident response, or validating detection coverage in a purple team exercise.
Audit Azure Storage accounts for public blob containers, missing encryption, overly permissive SAS tokens, disabled logging, and network access violations using Azure CLI, PowerShell, and Microsoft Defender for Storage. Use for storage security audits across subscriptions, responding to Defender for Storage anonymous-access alerts, verifying compliance controls, or setting security baselines when onboarding a subscription.
This skill MUST be used when the user wants to process a backlog of dev tickets end-to-end with a known project / branch / merge target / task tracker / design reference workflow, but without committing to any specific platform (Jira / Linear / GitHub Issues / Notion / Figma / Zeplin / etc.). Trigger on requests like 「幫我跑任務」、「照我的流程把 backlog 做完」、「review failed 的全部處理掉」、「用我那套開發流程做事」、"work through my task list", "run my dev loop", "process my tickets end-to-end". MUST NOT be used for a single ticket, which belongs to the other dev-workflow skills. MUST ask the user up-front for project root, working branch, merge target, task list location, design reference location, and how to mark a task done — then loops through tickets implementing → verifying → committing → opening PR → merging → syncing → updating the tracker. MUST NOT bake in platform-specific API calls; figure those out at run time from the user's answers.
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.