Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Interfaces with a model in the loop. Streaming text without layout thrash, thinking and reasoning states, tool calls and their status, approvals, citations, the composer, stop and regenerate, scroll pinning, markdown rendering, latency masking, and honesty about what the system is doing. Use when building chat, copilots, agent dashboards, AI features inside a product, or anything that shows model output as it is produced.
Set up, integrate, build, debug, and ship AgentMark prompts, datasets, experiments, and evals. TRIGGER: setting up / integrating AgentMark into any app or agent, including when an SDK is named (raw Anthropic/OpenAI, Vercel AI SDK, Bedrock, a framework) — the named SDK is the integration TARGET, never a reason to skip; any `.prompt.mdx`, `agentmark.json`, `agentmark.client.ts`, `agentmark_client.py`, an `agentmark/` or `.agentmark/` dir, or `@agentmark-ai/*` imports; `npx create-agentmark` or any `agentmark` command (`init`, `dev`, `doctor`, `run-prompt`, `run-experiment`, `generate-types`, `link`, `pull-models`); driving AgentMark Cloud (`agentmark-mcp`, headless provisioning, git deploys); any mention of AgentMark, prompt versioning, experiments, evals, deployments, or trace observability. SKIP only with NO AgentMark intent or markers: provider-neutral prompt code; generic prompt-engineering or observability questions; competing platforms (Langfuse, LangSmith, Phoenix, Braintrust, Traceloop).
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
Analyze text for AI-style signals, false-positive risk, and directions for naturalizing rewrites. Supports text or URL input. Trigger words: AI-flavored / de-AI-flavor / make it read like a human wrote it / does this read like AI / Zhuque detection. Analyze text for AI-style signals, humanize wording, assess detector risk. Not for bypassing detectors.
The ai-video-caption-generator skill brings accurate, AI-powered captioning to your video workflow through a simple conversational interface. Transcribe speech, generate styled subtitles, and burn captions directly into your footage without touching a timeline editor. Key features include multi-language caption generation, custom font and color styling, speaker-aware formatting, and timestamp-aligned SRT/VTT export. On first use, the skill auto-configures credentials via the NemoVideo API so you can start captioning immediately without manual setup. Ideal for content creators, educators, marketers, and accessibility specialists. Supports mp4, mov, avi, webm, and mkv formats.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use for anything AI/agent/conversational built on Algolia: algobot CLI, Agent Studio, RAG systems, conversational product discovery, genAI content generation from search results (carousels, descriptions, headers), chatbots or recommendation agents using Algolia as retrieval, config-as-code workflows, multi-environment deploy (dev/staging/prod), memory and personalization, MCP tool integrations, conversation history / GDPR retention, or adding a chat widget alongside InstantSearch. Trigger on: "algobot", "Agent Studio", "RAG with Algolia", "conversational experience", "AI agent" + Algolia, "genAI carousel", "chat widget", or building AI features on top of Algolia search. Do NOT use for Agent Studio evaluations or eval-driven agent improvement - use agent-studio-evaluations. Do NOT use for raw index ops (records, synonyms, settings) - use algolia-cli. Do NOT use for pure frontend search UI (InstantSearch, autocomplete) with no AI/agent layer.
Alibaba Cloud PAI-DLC (Deep Learning Containers) job management skill. Covers: distributed training job CRUD, monitoring (logs and events), and GPU sanity check. Triggers: "DLC", "PAI-DLC", "create-job", "list-jobs", "get-job", "stop-job", "update-job", "get-pod-logs", "get-job-events", "get-pod-events", "list-job-sanity-check-results".
This skill should be used when the user asks to "import Alibaba Cloud resources into Terraform", "terraform import Alibaba Cloud", "bring existing cloud resources under Terraform management", "migrate Alibaba Cloud resources to Terraform", "generate terraform state", "import alicloud resources", "Alibaba Cloud IaC migration", "Alibaba Cloud Terraform import", or needs to manage existing Alibaba Cloud resources with Terraform. Guides users step-by-step through environment check, authentication, resource discovery, HCL generation, state import, validation, and dependency graph. Supports both one-time migration and incremental sync.
Use when managing Alibaba Cloud beebot (Chatbot) via OpenAPI/SDK, including the user asks to configure, query, or troubleshoot Alibaba Cloud chatbot resources, including bot inventory, configuration changes, status checks, and API-level diagnostics.
Use when running a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reasoning, embedding, rerank, and edit variants. Use to execute one small request per skill and record results.
Use when installing or configuring OpenClaw with DingTalk, Feishu, Discord, and additional channels with Bailian/DashScope models on Linux hosts. Use when provisioning a new OpenClaw node, troubleshooting gateway/channel startup, standardizing openclaw.json mapping, or automatically discovering extra channels from https://docs.openclaw.ai/channels.
Use when benchmarking similar product documentation and API documentation across Alibaba Cloud, AWS, Azure, GCP, Tencent Cloud, Volcano Engine, and Huawei Cloud. Given one product keyword, auto-discover latest official docs/API links, score quality consistently, and output detailed prioritized improvement recommendations.
Analyze PyTorch CUDA memory snapshots from torch.cuda.memory._dump_snapshot(), torch.cuda.memory._snapshot(), or memory_viz artifacts. Use when the user wants to understand GPU memory usage, top allocation sites, deallocation timing, OOMs, allocator fragmentation, inactive cached memory, memory leaks, retained tensors, or Python reference cycles in PyTorch workloads. Supports diffing two snapshots from the same run to pinpoint growing allocation sites.
Perform dead-disk forensics on an acquired disk image using The Sleuth Kit, Plaso, and bulk_extractor — verify integrity and mount read-only, map partitions, recover deleted files, build a file-system and super-timeline, carve unallocated space, mine registry hives and OS artifacts, and detect anti-forensics. Use when handed a .E01/.dd/.raw/.vmdk/.vhdx disk image or forensic acquisition to examine, recovering deleted files, building a file-system timeline, or carving artifacts from unallocated space.
Reverse engineer Go binaries by recovering function names and types from pclntab and moduledata using GoReSym, redress, and IDA/Ghidra Go plugins, and by reading Go's non-standard calling convention, interface dispatch, and string layout. Use when a binary contains Go runtime strings, when strings show runtime.main or go:buildid, when a stripped binary is unexpectedly large, or when analyzing Go malware or a Go-based service.
Analyze suspected malware safely — containment, static triage, sandboxed detonation, unpacking, capability and C2 extraction, IOC production, and YARA rule authoring. Use when handed a suspicious file, hash, or sample, when triaging an alert artifact, or when producing detection content from a specimen.
The most common use for anniversary-video-maker is assembling a slideshow of couple photos, wedding clips, and milestone moments into a polished video with music and captions. It handles photo sequencing, transition timing, text overlays, and audio syncing so you don't have to stitch everything together manually. Whether you're marking a first anniversary or a golden one, this skill helps you produce a shareable video that actually looks intentional rather than thrown together. Works with mixed media inputs including images, short clips, and audio tracks.
Use this skill any time the user wants in-depth research or comprehensive analysis on any topic. This includes: industry analysis, competitive landscape mapping, market sizing, trend analysis, technology reviews, investment research, sector overviews, due diligence, benchmark studies, patent landscape analysis, regulatory analysis, and academic surveys. Also trigger when: user says 帮我调研一下, 深度分析, 行业研究, 市场规模分析, 竞争格局, 技术趋势, 做个研究报告. If deep research or comprehensive analysis is needed, use this skill.
Write clear, developer-facing API documentation. Use when asked to document an API endpoint, write API reference docs, create a developer guide, or turn a raw spec/Postman collection into documentation. Produces endpoint documentation with descriptions, parameters, request/response examples, and error codes.
Use when designing BK-CI API contracts, such as resource path design, HTTP method selection, request and response objects, error codes, and versioning strategy. Prefer this when the user is defining interfaces rather than implementing business logic.
Apidog import/export and quality gates: import OpenAPI, Postman, Swagger, and Apidog native formats; export OpenAPI, HTML, Markdown, Postman, and Apidog native formats; validate spec completeness, tag grouping, schema/body coverage, counts, modules, and resource visibility.
Use when reasoning about how Apple delivers and serves its experiences — the observable web delivery/infra (multi-CDN, mzstatic image-transform URLs, image formats, HLS adaptive video, caching, HTTP/2-3) and the reverse-engineered, INFERRED server-side architecture (CloudKit, APNs, StoreKit, Sign in with Apple, Private Cloud Compute, iCloud sync). Part of the apple-design family. Keywords: apple cdn, akamai, mzstatic, image transform url, srcset picture, HLS m3u8, http3 quic, cache-control immutable, content-hash fingerprint, frame-sequence delivery, createImageBitmap, KTX texture, video scrub, cloudkit, APNs push, StoreKit, sign in with apple, private cloud compute, icloud sync, conflict resolution, backend, infrastructure, reverse-engineered, inferred architecture.
Use when discussing object-oriented design principles or component-level structure — phrases like "SOLID", "Single Responsibility", "Open-Closed", "Liskov Substitution", "Interface Segregation", "Dependency Inversion", "SRP", "OCP", "LSP", "ISP", "DIP". Defines the five SOLID principles, with the honest caveats Uncle Bob's original treatment glosses over and the cases where they shouldn't be applied dogmatically.
Archery SQL audit platform CLI for managing SQL workflows, queries, instances, diagnostics. Use when the user asks about SQL审核, database operations, Archery platform management, or needs to submit/review/execute SQL against database instances.
MySQL and MariaDB specifics for Atlas: dev database and URL scope (schema vs server), character sets and collations, users, roles and grants, enum and set columns, generated columns, foreign-key indexes, functional and prefix indexes, triggers and stored programs, table copies and MY lint checks, partial migration failures (no transactional DDL), GET_LOCK, managed services (RDS, Aurora, Cloud SQL, Azure), schema and migration tests, and custom lint rules. Use with the atlas skill whenever Atlas manages a MySQL or MariaDB database
Guided onboarding of a repository onto Atlas, one verified stage at a time: plan the units and the workflow, define the schema as code, set up the migration workflow, add CI with the Atlas Registry, deploy to staging, and promote to production. Each stage ends on a check the agent runs itself, such as a dry run with no changes or a deployment recorded in Atlas Cloud. Use when the user asks to onboard, adopt, or set up Atlas for a project or a team, or to resume an onboarding
This skill should be used when the user asks to "audit this codebase", "audit this code", "security audit", "code audit", "find vulnerabilities", "check for bugs", "review code quality", "find dead code", "check for anti-patterns", "performance audit", "check for code smells", "technical debt", or "code health check".
Audit the health of a PostHog project's data warehouse — find every broken or degraded pipeline item across sources, sync schemas, materialized views, batch exports, and transformations. Use when the user asks "what's broken in my warehouse?", "give me a health check", "audit my data pipeline", "why are some dashboards stale?", or wants a one-shot triage summary before deciding where to spend time. Produces a prioritized report of issues grouped by severity and type, with recommended next steps.
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.