数据库 MCP（PostgreSQL / MySQL / Redis）

Adds, updates, moves, or removes content on the Dynamo Fern docs site — standard docs pages, catalog-driven recipe and feature-benchmark pages, examples, recipes, and translations — keeping everything in line with the documentation style guide. Use for any change under docs/, recipes/, or examples/ (new page, edit, tab or section move, rename, removal, recipe/benchmark page, .zh-CN translation, version cut), when deciding which docs tab a page belongs in (Kubernetes Guide vs CLI Guide vs Reference vs Use Cases), and whenever content needs its frontmatter, headings, links, callouts, or terminology fixed.

Security-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object property level authorization (excessive data exposure and mass assignment), broken function-level authorization, unrestricted resource consumption, SSRF, injection, and auth/token flaws. Every finding comes with a working proof-of-concept request. Use when the user asks to pentest, security-test, audit, or find vulnerabilities in an API, endpoint, or backend service.

Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the `strix cloud` CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance reports, start PR reviews, buy credits, and set up schedules or webhooks. Use for managed, continuous, scheduled, team-tracked, or sandboxed-agent security testing.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)

Pair a remote AI agent with your browser. (gstack)

Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

Configure deployment settings for /land-and-deploy.

Fast headless browser for QA testing and site dogfooding. (gstack)

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

One-time setup of the sandbox prerequisites used by the reproduce-issue skill and the reproduce-verifier agent — Docker, the isolation runtime (gVisor on Linux / Colima on macOS), healthy container networking, and the nx-review-sandbox toolchain image (built from the repo's mise.toml). Idempotent; re-run any time to verify or repair. Use when the user says "set up the review sandbox", "install the sandbox prereqs", "build the sandbox image", or a reproduce-issue preflight reports something MISSING.

Guidelines on using Design System styles and components. Use when working on .vue files in packages/frontend. Triggers for tasks that include component architecture, styling, UI changes, or feature work.

Answer questions about the Supabase docs app (apps/docs) using documented architecture, build pipeline, and review-pattern notes, and apply feature-design principles (codebase reuse, coding minimalism) when proposing or critiquing changes. Use when the user asks "how does X work in the docs app?", "where does Y live?", "is this approach OK for the docs app?", or before writing non-trivial changes under apps/docs/ — especially anything touching the MDX pipeline, markdown generation, content components, federated docs, or contributor-facing authoring patterns. Can answer architecture questions with Mermaid diagrams when helpful.

Adds, migrates, or updates n8n Public API v1 endpoints with @PublicApiController — public DTOs, API-key and RBAC scopes, cursor pagination, OpenAPI + coverage wiring, and tests. Use when working under packages/cli/src/public-api/v1/ or when exposing an existing service through /api/v1.

Write and repair HTML/CSS/SCSS for Discourse core, plugins, themes, and theme components. Use when authoring or modifying templates (.gjs/.hbs), stylesheets (.scss), component markup, class names, responsive layout, FormKit/select-kit styling, or CSS regressions. Covers Discourse's BEM-with-standalone-modifiers naming, the CSS custom-property color palette (theming + dark mode), template/HTML conventions, CSS repair patterns, and where stylesheets live.

Launch and drive the WorldMonitor browser dashboard (Vite app at /dashboard) to prove user-facing behavior with screenshots and transcripts. Use when a change needs proof in the real app rather than only unit tests — panels, map layers, settings, search, country briefs, boot — or when asked to run, screenshot, or verify the dashboard.

Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the `yc` CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.

Create Linear tickets or GitHub issues following n8n conventions. Use when the user asks to create a ticket, file a bug, open an issue, or says /create-issue.

Use when launching cloud VMs, Kubernetes pods, or Slurm jobs for GPU/TPU/CPU workloads, training or fine-tuning models on cloud GPUs, deploying inference servers (vllm, TGI, etc.) with autoscaling, writing or debugging SkyPilot task YAML files, using spot/preemptible instances for cost savings, comparing GPU prices across clouds, managing compute across 25+ clouds, Kubernetes, Slurm, and on-prem clusters with failover between them, troubleshooting resource availability or SkyPilot errors, optimizing cost and GPU availability, or migrating an existing Slurm workload (converting sbatch scripts, salloc sessions, job arrays or srun invocations into SkyPilot task YAMLs, and mapping Slurm commands, directives and SLURM_* environment variables to their SkyPilot equivalents).

Manage CLI tool integrations exposed via the API. List, configure, and invoke CLI tool plugins that extend OmniRoute's automation surface.

Trigger system backups, restore from backup files, and manage the SQLite database lifecycle. Supports export, import, and incremental snapshot strategies.

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/<id>/ that implements the frozen `Skin` contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add a skin", "create a skin", "new skin", "reskin the app", "make a <domain> skin", or wants the app re-themed as a new product. Do NOT use for editing the shell itself (src/shell/**), the shared token vocabulary (src/app/globals.css), or the shipped skins unless explicitly asked.

@copilotkit/react-core — mount the CopilotKit provider (from @copilotkit/react-core/v2) in a Next.js App Router / React Router v7 / TanStack Start / SPA app, drop in CopilotChat/CopilotPopup/CopilotSidebar (v2 chat components ship from react-core/v2 — NOT react-ui, which is CSS-only in v2), access and subscribe to agents with useAgent / useAgentContext / useCapabilities, switch between multiple agents, manage durable Intelligence threads with useThreads, register browser-side tools via useFrontendTool, render tool calls with useRenderTool / useComponent / useDefaultRenderTool, gate execution with useHumanInTheLoop, wire file attachments with useAttachments, configure suggestion pills, and register activity- and custom-message renderers. publicLicenseKey is canonical (publicApiKey is deprecated alias). Load the reference under references/ that matches your task.

Use Orca's computer-use CLI for OS/window-level inspection and input in visible local app windows. Use when a task must read or operate a native app or an external browser window (for example, Chrome, Edge, or Safari) or an app webview. Do not use for Orca's embedded browser or page-only browser automation. Use `orca-cli` for Orca's embedded pages and a page-automation tool such as Playwright or CDP for external pages.

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, or decomposing work across agents. Use `orca-cli` instead for full ownership handoffs, including requests phrased as "hand off", "handoff", "handover", "give this to another agent", or "another worktree" when the user did not explicitly ask to supervise, monitor, wait for results, or coordinate a DAG. Use `orca-cli` for terminal control, lightweight terminal prompts, shell commands, Orca worktree management, reading or waiting on terminals, and automation of the browser embedded inside Orca. Use Computer Use for external browser windows, webviews, Orca app UI, or desktop UI outside Orca's embedded browser only when the task requires OS/window-level control such as focus, menus, dialogs, coordinates, or screenshots. Use `orca-cli` for Orca's embedded pages and a page-automation tool such as Playwright or CDP for e

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", "share skills", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for external browser windows, webviews, or desktop UI only when the task requires OS/window-level control such as focus, menus, dialogs, coordinates, or screenshots. Use `orca-cli` for Orca's embedded pages and a page-automation tool such as Playwright or CDP for external pages.

GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git commands.

Tinybird CLI commands, workflows, and operations. Use when running tb commands, managing local development, deploying, or working with data operations.

Creates product analytics or SQL-backed box plot insights in PostHog. Use when a user asks to create, build, or save a box plot, visualize a numeric distribution, compare quartiles or medians across dates or groups, or turn SQL results into a box plot. Chooses between a standard Trends box plot and a SQL insight, validates the distribution data, saves the insight, and verifies it.

Provides instructions for integrating the Google Mobile Ads (GMA) SDK. Use this skill when the user wants to get started with, install, integrate, set up, or configure the SDK for AdMob or Ad Manager, GMA Next-Gen SDK or mobile ads framework in an Android, iOS, or Unity application.

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st

Use immediately for any pasted OpenClaw GitHub issue or PR URL/number, and for OpenClaw issue/PR orchestration, review, triage, root-cause repair, PR rewrite, duplicate search, opener identity/who wrote it, author account age/activity, comments, labels, close, land, or maintainer evidence checks.

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the `cacheComponents` flag, work through a flood of blocking-prerender / instant validation errors, run the `cache-components-instant-false` codemod, or decide between opting routes out with `export const instant = false` and fixing them in place.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Debug and support PostHog Experiments (A/B tests) for a customer looking at their own results. Use whenever an experiment support ticket is pasted or a customer asks a results question, most commonly "why aren't my exposures even?", "why is one variant getting no traffic?", "why am I missing / seeing too few exposures?", "why does the bias banner show?", or "why don't PostHog's numbers match my SQL?". Pulls the experiment's real data read-only, matches it to a known-cause catalog, and produces a customer-facing explanation, fix, and review of the pertinent numbers. Loads diagnosing-experiment-results as its deep diagnostic library. DO NOT TRIGGER when: creating an experiment (use creating-experiments), only configuring rollout (configuring-experiment-rollout) or metrics (configuring-experiment-analytics), asking lifecycle questions (managing-experiment-lifecycle), or the underlying feature flag is what's misbehaving rather than the results (use debugging-feature-flags).

Use, configure, theme, extend, and orchestrate Hermes Agent.

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Write TypeScript for Discourse core, plugins, and themes. Use when authoring new .ts/.gts files (components, modifiers, helpers, services, utils), typing an existing public API, or converting existing .js/.gjs files to .ts/.gts. Covers the component/modifier/plain-class Signature patterns, TSDoc for Signatures, typing untyped dependencies, compile-time type tests, the strict-grade bar under the loose global tsconfig, and the faithful-port and rename pitfalls that the type-checker does NOT catch.

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini or Atlas Cloud AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

Conventions for Discourse frontend code, JavaScript and TypeScript alike (.js/.gjs/.ts/.gts), in core, plugins, and themes that the linter does not enforce. Use when writing, reviewing, or preparing to commit class-based code or templates. Covers the private-symbols pattern (#, unprefixed, _), class member ordering beyond the lint buckets, blank lines before documented fields, no banner comments, safe in-template comments, attribute/argument/modifier ordering on invocations, and the comment necessity gate.

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.

Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-analytics-sources, replicating curated column semantics in HogQL, reading exposed engineering_analytics_* warehouse views where product logic is involved (CI cost, fingerprinted failure lines, commit attribution), saving queries with insight-create, and scheduling delivery with subscriptions-create. Use when asked to "save this as an insight", "put CI health / merge times on a dashboard", "email me PR throughput weekly", "chart CI cost", "track time to first review", "subscribe to these numbers", "alert on CI success rate", or "what data/tables/views does engineering analytics read". For ad-hoc CI and merge questions use diagnosing-ci-and-merge-bottlenecks; to investigate one specific CI failure use investigating-ci-failures.