Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create or initialize a durable writing home with VOICE.md, STYLE.md, examples/, and drafts/. Use when Scribe identifies a first-time writer with no established writing context after resolving the target, or when the user explicitly asks to set up, scaffold, initialize, or migrate a self-contained writing folder.
The darkmatter TypeScript toolchain contract: Bun catalogs, Effect 4, effect-orpc, Postgres-first data, tsgo, Vitest, oxlint/oxfmt, changesets, Alchemy deploys, and required checks. Use when writing, fixing, building, or shipping TypeScript in a darkmatter repo. Use codebase-design for module boundaries and effect-typescript for deep Effect patterns.
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.
EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III high-risk use case areas, provider and deployer obligations (Arts. 9–17, 26), GPAI model obligations including the July 2025 Code of Practice (Arts. 51–55), conformity assessment and CE marking (Arts. 43–48), EU AI database registration, Art. 50 transparency (chatbots, synthetic media, AI-generated content), governance (AI Office, AI Board), penalties (Art. 99), confirmed phase-in timeline (Digital Omnibus, Reg. (EU) 2026/1744, in force July 27, 2026: Annex III deferred to Dec 2, 2027; Annex I to Aug 2, 2028), and cross-framework mapping to ISO 42001, NIST AI RMF, and GDPR. Use for any EU AI regulation, AI system classification, or AI compliance question. Current as of November 2026. GPAI enforcement active: Art. 91 information requests reported since Aug 2026 (procedures: Reg. (EU) 2026/1755).
Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus example input→expected-output pairs. Pairs with [write-skills](../write-skills/SKILL.md) (the authoring principles every fix obeys).
Run a full Flows app platform review against a React/TypeScript CDF codebase, following the cognitedata/dune-app-reviews scoring criteria. Produces three artifacts: review-files.md (per-file inventory), review-packages.md (dependency audit), and review-report.md (scored report with must/should/nice-fix items). Use when the user asks for a Flows app review, pre-submit review, approval review, app certification review, code quality audit, CDF platform review, or "run dune-review" on a codebase before submission.
The shared git layer other skills borrow: the worktree path, name, and lifecycle, a worktree's declared setup and teardown, the base branch, rebase versus merge, branch sync, hotfix branches, merged-branch cleanup, lost-work recovery, and stacked branches. Use when the user says "make me a worktree for #42", "where's the worktree for this branch", "tear down this worktree", "set up this worktree", "make this worktree's dev database", "what's the base branch here", "should I rebase or merge", "sync this branch with main", "start a hotfix for the login crash", "backport this hotfix", "clean up my merged worktrees", "I lost a commit", "stack this on #43", or runs "/gitkit", and whenever another skill needs any of those answers
How to use the gpui-component UI library in GPUI applications, and the normative Design and Coding Guides that govern it. Use when building UIs with gpui-component components (Button, Input, Select, Dialog, Tabs, Sidebar, List, Table, etc.), setting up the library, handling component state or theming, finding the right component for a UI need, and when designing layouts, spacing, visual hierarchy, or interaction states, writing interface copy, or making application architecture, state-ownership, or public API decisions.
Subscribe to WeChat Official Account articles—at 6 a.m. daily, track competitors, similar accounts, and followed accounts, and receive a feed of articles from your subscriptions. If the API returns insufficient credits (code=3210), automatically open Alipay to top up and continue the search.
Expert-level hotel management, reservation systems, guest services, revenue management, and hospitality technology. Use when the user mentions hotel, reservation, PMS, or revenue management, or when the task involves Hotel Management Systems, Technologies, Standards and Protocols, or Reservations Management
Plan, write, time, style, and validate motion-graphic beats for long-form talking-head HyperFrames videos. Use when Codex is asked to add or improve visual beats, glassmorphism lower thirds, crumpled-paper full-screen takeovers, transcript-synced callouts, pacing coverage, YouTube retention graphics, or render-ready overlays in an existing HyperFrames video project.
Methodology for detecting client SOC patches, attacker activity, and security-state changes that occur during a red-team engagement, and converting those observations into deliverable findings. Built from authorized red-team work where the client patched a confirmed SQLi within 30 minutes of detection and an external attacker locked multiple new accounts during a single test session. Use when (a) running any active engagement against a monitored target, (b) a previously confirmed finding stops reproducing, (c) baseline timing shifts unexpectedly, or (d) you notice response patterns changing during testing.
Migrate React Navigation 7.x or 8.x navigators from JSX-based Dynamic API Navigator and Screen elements to Static API object configuration. Use when converting React Navigation screen trees, static navigation containers, nested navigators, groups, linking/deep-link config, render callbacks, getComponent screens, custom navigators, or static/dynamic API boundaries while preserving behavior and TypeScript types.
Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Systematic planning for medium-to-large tasks. Gathers context, identifies domain skills, and writes phased plans to brain/plans/. Does NOT implement. Use for new features, multi-file refactors, or architectural changes—not small fixes. Triggers: “plan this”, “break this down”.
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.
Query Tonghuashun Wencai data using natural language in Chinese, including market data for A-shares, indices, funds, Hong Kong and US stocks, and convertible bonds. Use when the user needs to retrieve stock screening, financial, capital flow, technical indicator, or other data from Wencai using natural language.
React performance optimization guidelines. Use when writing, reviewing, or refactoring React components, hooks, effects, data fetching, or bundle optimization. Includes useEffect best practices — when NOT to use effects and better alternatives. Triggers: "when writing React code", "reviewing a React PR", "why is this component re-rendering", "reviewing code for performance issues", "optimizing bundle size".
Prepare and execute a Plannotator release—draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing a release, bumping versions, writing release notes, tagging a release, or publishing. Also trigger when the user says things like “let's ship”, “prep a release”, “what's changed since last release”, or “time to cut a new version”.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Use when the user asks to decompose, break down, or generate tasks for an existing Strikethroo plan ID in this repository. Triggers include generate tasks, break down the plan, decompose plan, and create the task blueprint. Do not use to create a new plan, execute tasks, or for generic project planning outside Strikethroo.
Use when the user mentions tosutil, TOS object storage, bucket/object operations, batch upload or download, object metadata, TOS connectivity, or errors such as 403/network/argument failures. 围绕火山引擎对象存储 tosutil 生成与校验命令、规划桶/对象操作并诊断错误；当用户提到 tosutil、TOS 桶对象管理、批量上传下载或相关排障时调用。
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, and INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for an LCP deep dive (5 phases), CLS investigation (loading vs. interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
A tool for retrieving Amazon Movers & Shakers data. Use this skill to find popular products with surging sales on Amazon, discover breakout product trends, or get a list of Movers & Shakers products. Supports category filtering and outputs product basics, prices, ranking trends, and other data to provide market source data for product selection on Temu.
Create Apple-inspired bento grid presentation cards for showcasing project stats, timelines, and achievements. Generates self-contained HTML files with zero-gap grids, stat cards, pill tags, bar charts, and dark quote cards — optimized for screenshot export. Supports both light (Apple signature #f5f5f7) and dark (#000) themes. Use when the user asks to build stat cards, bento grids, project summary cards, dashboard cards, Apple-style presentation layouts, project overviews, achievement showcases, or any visual summary of numbers and milestones. Also use when the user wants to create slides, infographics, or visual reports with a clean Apple aesthetic.
集中兵力：多件事同时争抢时间、注意力或预算时，列出全部待办，选定唯一主攻目标并公开锁定，彻底解决、验证后再转向下一个。当待办过多、推进分散、“每件都做了一点但都没做完”、需要决定先做什么时触发；只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces. When several tasks compete for time, attention, or budget, enumerate them, lock onto a single main target, finish and verify it completely, then move on. Trigger when priorities sprawl, effort is scattered, or you must decide what to do first; skip when there is one task, tasks are independent and parallel, or the user explicitly wants them advanced together.
Default design system—darkmatter’s dark-first, terminal-inspired design system, built on Tailwind CSS v4, React 19, and Radix UI. Use as the default design system when working in an app without an established design system or guidelines. Use for dashboards, trading/monitoring consoles, forms, tables, settings, navigation, or any screen that should look and feel like darkmatter’s brand. This is the canonical source for darkmatter components, tokens (the OKLCH --n-* ramp), theming, and layout—prefer it over generic shadcn/ui.
Safe-change playbook for the darkmatter/gitops repo—pre-commit validation (kubeconform with CI-identical flags, yq for YAML manifests, jq for SOPS JSON, git diff --check), SHA-pinned images, KSOPS/SOPS secret-editing rules, rollback via revert, and how ArgoCD reconciles. Use for any change to darkmatter/gitops (manifests, Helm values, apps/*.yaml, secrets), when asked to bump an image tag, wire a secret, or roll back a deploy. Also use when tempted to kubectl apply/edit/patch anything—the answer is no.
Evaluate UI designs against usability heuristics, UX laws, interaction patterns, interaction design principles, information architecture, and content quality. Conduct heuristic evaluations, structured design critiques, pattern-based reviews, posture analysis, excise audits, IA evaluations, and UX writing reviews. Provides specific, actionable feedback grounded in established principles rather than subjective opinion.
Use when building Django web applications or REST APIs with Django REST Framework. Invoke when working with settings.py, models.py, manage.py, or any Django project file. Creates Django models with proper indexes, optimizes ORM queries using select_related/prefetch_related, builds DRF serializers and viewsets, and configures JWT authentication. Trigger terms: Django, DRF, Django REST Framework, Django ORM, Django model, serializer, viewset, Python web.
Use whenever the user wants to interact with Figshare - searching public datasets/articles, downloading Figshare files, listing their own articles/collections/projects, creating or updating articles, or uploading files (including large multi-part uploads) via the Figshare v2 REST API. Trigger on mentions of "figshare", figshare DOIs (10.6084/m9.figshare.*), figshare.com URLs, or phrases like "upload my dataset to figshare", "publish to figshare", "get figshare article".
Architect cross-tool conversion flows that match the audience and stage, from landing page to lead magnet, nurture sequence, offer, and advanced funnels. Be candid about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience and stage). Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, and multi-tool funnel orchestration. Also triggers when a team’s growth tools work individually but not together, when audience segments share one nurture path, or when a funnel is being architected from scratch.
Expert game audio designer and implementer specializing in interactive sound design, adaptive music systems, spatial audio, and audio middleware integration. Brings deep knowledge of FMOD, Wwise, and native engine audio systems to create immersive sonic experiences that respond dynamically to gameplay. Use when "game audio, sound design, game music, FMOD, Wwise, spatial audio, 3D sound, audio middleware, game sfx, adaptive music, interactive audio, audio bus, game mixing, audio occlusion, reverb zones, audio pooling, sound manager, audio, sound, music, game-audio, fmod, wwise, spatial-audio, middleware, mixing, sound-design" mentioned.
Turn messy Unity or Unreal build/release automation into one bounded game-pipeline packet after naming the signal tier first: fast branch-gate CI, nightly/package- candidate builds, or release/certification candidates. Use when a game team needs to design or repair GitHub Actions, Unity Build Automation, Jenkins, TeamCity, or similar CI for engine builds — especially when they mention flaky packaging, cache superstition, giant build-job blobs, slow cook / package cycles, artifact confusion, SDK/signing drift, or manual candidate promotion that should become reproducible. Route one red log first-pass diagnosis to `game-build-log-triage`.
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.