Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Revision hand — helps find the truth in what someone wrote and cut the filler. Focuses on structural tightening plus filler removal: deleting boilerplate openings, cutting degree adverbs, breaking fake parallelism, clearing slogan endings. Has a quick-blade mode (delete only, no rewriting) and a full mode. Accepts any draft. Can take a voice-dissolver voice list as a protected zone. Triggers: help me revise my draft, help me edit this, it's not well written but I don't know what's wrong, too much filler, doesn't sound like me, help me polish it, make it read smoothly, tighten it up, cut the filler, make it sound more human, too wordy. Not for: heavy AI flavor but the structure is fine (→ humanize-ai de-flavoring), content checkup (→ chinese-write-checker), title/layout/punctuation polishing (→ packaging-workshop).
Designs embedding strategies that combine semantic (text-based) and structural (graph-based) information at node, edge, path, and subgraph levels for knowledge graphs. Use when selecting embedding granularity, choosing complementary semantic and structural approaches, designing fusion strategies (concatenation, attention, contrastive alignment), or when user mentions node embeddings, embedding fusion, vector representations for graphs, or combining text and graph signals.
Explains how a subsystem, feature flow, or runtime path works (architecture, data flow, file map, gotchas), with an optional critique by fresh-context critics. Read-only. Use when the user says "how does this work?", or when asked how a subsystem or flow works or where logic belongs. Not for why code is shaped as it is; use investigating-design-rationale. Not for explaining a PR or diff; use explaining-code.
Generate a financial due diligence checklist and analysis framework for any investment, acquisition, or partnership. Use when asked for a due diligence checklist, M&A financial review, investment analysis framework, or vendor financial assessment. Produces a document request list, key analytical questions, red flags checklist, and a summarised financial health assessment.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
This skill should be used when the user asks to "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "这个设计合理吗", "is this the right approach", "为什么要这样做", "why are we doing it this way", "有没有更好的方案", "is there a better solution", "challenge assumptions", "挑战假设", or needs to evaluate architectural decisions, design choices, or problem-solving approaches without relying on analogies or conventions.
A complete reference for FiveM native functions, auto-updated from [cfxnatives.dev](https://cfxnatives.dev) and organized by namespace. Use this skill to get accurate native signatures, parameters, return types, and examples when developing FiveM resources.
Provides comprehensive guidance for Flask framework including routing, templates, forms, database integration, extensions, and deployment. Use when the user asks about Flask, needs to create web applications, implement routes, or build Python web services.
TRIGGER when: user asks to draw, illustrate, or visualize any process, structure, or concept — "画个流程图", "draw an architecture diagram", "帮我画个对比图", "visualize this process", "make a diagram for this doc", or mentions 流程图/架构图/示意图/对比图/时序图/泳道图/时间线. Also trigger when user provides a document/article and asks for illustrations or diagrams. DO NOT trigger for: chart/plot requests (bar charts, line graphs — those need a charting library, not draw.io), or artistic image requests (logos, mascots, drawings of objects/people — those need an image tool).
Write, fix, review, debug, and validate Flutter tests for apps, packages, and plugins. Use when adding unit tests, widget tests, integration tests, MethodChannel or plugin mocks, Mockito or mocktail test doubles, golden or accessibility checks, CI test commands, test failures, MissingPluginException, pump or pumpAndSettle problems, finder errors, build_runner mock generation, device integration testing, web integration testing, or flaky Flutter tests.
When the user wants to investigate financial discrepancies, fraud, or hidden assets. Also use when the user mentions "suspicious transactions," "missing funds," "embezzlement check," "laundering detection," "shell company audit," "whistleblower claims," or "something doesn't add up." Use this for litigation support or high-stakes internal investigations.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
[Required · mandatory] Company-mandatory frontend development standards. Read this skill before writing or modifying any frontend code. Covers all development constraints including mandatory Composition API standards, naming conventions, API calling rules, Pinia state management and component splitting.
Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at any point, and generate interactive health dashboards. From casual "show me this week's workouts" to deep "analyze my recovery vs training load".
Perform Google Calendar operations (viewing, creating, updating, deleting events) with gog CLI (v0.10.0). Triggers on "what's on today?", "tomorrow's schedule", "add a meeting", "register an event", "check my calendar", "cancel an event", "create a Google Meet", etc.
Senior product manager assistant, offering comprehensive product management support including PRD document creation and review, product strategy consulting, retention growth analysis, competitive research, and feature prioritization. Suitable for creating or reviewing product documents such as PRD/MRD/BRD/user stories; diagnosing product issues (low retention, poor conversion, growth bottlenecks) and providing actionable strategies; conducting competitive analysis and market research; designing feature plans and optimizing user experience. Use this skill when the user mentions product management topics such as "PRD", "requirements document", "product planning", "user retention", "feature design", "competitive analysis", "product metrics", "growth strategy", "user experience optimization", "feature prioritization". It should also be triggered even if the user does not explicitly say "product" but discusses App feature design, user growth, business models, requirements analysis, etc.
Use the Geti application end to end through its REST API — the project → dataset → annotate → train → deploy pipeline served by the FastAPI backend in `application/backend/`. Use when a user (not a contributor) wants to create a project, upload media, add annotations, launch a training or quantization job, track job status, configure a source → model → sink inference pipeline, and enable live inference. Covers the `/api/...` endpoints and the async job model, not backend code changes.
Discover which models, recipes, and tasks the getitune library (the Geti training library) supports before training. Use when a user asks what models are available, how to list recipes, how to filter by task or name pattern, how `list_models(...)` and `getitune find` behave, or how to resolve the "model name matches multiple tasks" error. Covers classification, detection, instance/semantic segmentation, and keypoint detection recipes.
Export a trained getitune model (the Geti training library) to a deployable format. Use when a user wants to run `engine.export(...)` or `getitune export`, choose between OpenVINO IR and ONNX, set FP32 vs FP16 precision with `ExportFormat` / `Precision`, or understand where exported artifacts are written and how they load back for inference. Covers the export/load contract between training and OpenVINO/ONNX inference.
Optimize an exported getitune model (the Geti training library) with post-training quantization. Use when a user wants to run `OVEngine.optimize()` / `engine.optimize()` to produce an INT8 model via NNCF, understands calibration-set requirements, or needs to re-validate and run inference with a quantized model versus the original FP32/FP16 model. Covers OpenVINO NNCF post-training quantization and the accuracy/size trade-off.
Prepare and point datasets at the getitune library (the Geti training library) for training, testing, and prediction. Use when a user asks which dataset formats are supported, how the `data=` argument of `create_engine(...)` / `--data_root` works, why format auto-detection fails, how to lay out COCO/YOLO/Pascal VOC/Datumaro-native data, how to use a zip archive, or how to pass an Ultralytics YOLO `data.yaml`. Covers Datumaro-based auto-detection and per-task data expectations.
Run inference and evaluation with a getitune model (the Geti training library). Use when a user wants to call `engine.predict()` / `engine.test()` or `getitune predict` / `getitune test`, run inference with a PyTorch checkpoint versus an exported OpenVINO IR (`.xml`) or ONNX (`.onnx`) model, or understand how `OVEngine` loads deployed models via ModelAPI. Covers PyTorch, OpenVINO, and ONNX inference backends.
Train a computer-vision model with the getitune library (the Geti training library) using its Python API or CLI. Use when a user wants to train, fine-tune, or evaluate a model with `create_engine(...)` and `engine.train()/engine.test()`, run `getitune train`/`getitune test`, pick or override a recipe under `getitune.recipe.<task>`, choose a device (cpu/gpu/xpu/cuda), warm-start from a checkpoint, or debug a training run. Covers classification, detection, instance/semantic segmentation, and keypoint detection.
This skill should be used when working with GitHub CLI (gh) for pull requests, issues, releases, and GitHub automation. Use when users mention gh commands, GitHub workflows, PR operations, issue management, or GitHub API access. Essential for understanding gh's mental model, command structure, and integration with git workflows.
Enter a project idea or GitHub link to automatically search for related open-source projects and generate a structured analysis report (tech stack/strengths and weaknesses/score), and download the code packages of the top 3 highest-scoring projects. Supports both intent-based search and direct-link analysis modes.
Complete GitHub Pages deployment and management system. Static site hosting with Jekyll, custom domains, and GitHub Actions. USE WHEN user mentions 'github pages', 'deploy static site', 'host website on github', 'jekyll site', 'custom domain for github', OR wants to publish a website from a repository.
Use whenever generating or suggesting a git commit message or Pull Request title, even when the user mentions neither gitmoji nor Conventional Commits. Not when the repository enforces a conflicting convention, and not when the user dictates the message verbatim.
Stock analysis and price movement forecasting. Trigger when the user expresses an intent to analyze, evaluate, or forecast, such as “Analyze Tencent,” “How has 0700 performed recently?”, “Is XX worth buying?”, “Forecast the future trend,” or “Generate an analysis report.” Do not trigger this Skill for simple queries such as “What is Tencent’s current price?” or “What is the ticker for Moutai?” Supports Hong Kong, A-share, and US stocks. Integrates multiple data sources, including news, fundamentals, technical indicators, capital flows, and macroeconomic information, to produce a multidimensional analysis and a structured report combining text, images, and visual charts. Requires a multimodal primary model (such as glm-5v-turbo) that can read images.
Global content search | Use when keyword search on Xiaohongshu/Bilibili/Douyin, note/video details, comments, or creator/UP upload monitoring is mentioned. Prefer access via Agent Reach / OpenCLI / bili-cli / public read-only APIs; when Agent Reach is unavailable, Guaikei API can serve as a last-resort fallback for Xiaohongshu.
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.