Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Verified, sourced facts about real-world entities and how they connect — companies, people, investors, funding rounds, M&A, laws, regulations, sanctions, countries and places, industries, products, financial metrics, macro indicators, FX rates. Every value carries a source and date. Use when a task needs to: filter or discover entities by criteria; traverse relationships (founders, executives, ownership chains, investors, jurisdictions, sanctions); look up laws or sanctions; get macro/market/ financial figures as latest-sourced values or history; or get recent facts where training recall is stale — for research (due diligence, competitor mapping) or structured output (tables, lists). Returns typed JSON, not web pages; prefer over web search or scraping for verified entity facts. Not for opinions, live ticks (price this second, weather, scores), or facts already in context.
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provides CAPA process management, root cause analysis, effectiveness verification, and continuous improvement coordination. Use for CAPA investigations, corrective action planning, preventive action implementation, and CAPA system optimization.
Plan and execute a career transition and produce a Career Transition Pack (progress metric + push/pull map, target archetypes, option scorecard, opportunity pipeline + outreach scripts, skills plan, 4–12 week experiment plan). Use for career change, career pivot, career transition, switching roles. Category: Career.
Use Catsu for unified, high-performance embedding API calls across 11 providers (OpenAI, VoyageAI, Cohere, Jina, Mistral, Gemini, Together AI, Mixedbread, Nomic, DeepInfra, Cloudflare) through a single consistent interface. Covers model selection and discovery, automatic retry with exponential backoff, cost and token tracking, Matryoshka dimension reduction, input type hints (query vs document), async/await support, and per-request API key overrides. Use when: generating embeddings, comparing embedding providers, building search or RAG systems, or integrating embeddings into Python or Rust applications.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Interrogate a UX idea, requirement, flow, feature, or design direction before execution. Use when a designer asks to be challenged, wants assumptions exposed, wants a red-team review of the premise, or needs hard questions that test whether the proposed work should exist at all.
Create, edit, and deliver editable chart cards in Feishu Docs when preparing reports. Supports 30+ built-in chart types, including bar/column (stacked, grouped, percentage, overlapping comparison), line, area, scatter/bubble, dual-axis, pie/doughnut, rose, radar, funnel, word cloud, Sankey, heatmap, Treemap/Sunburst, as well as business charts such as waterfall/bridge, Mekko, bullet, dumbbell, butterfly, and small-multiple panels. Chart types, annotations, and editing capabilities broadly match ThinkCell. By default, follows MBB (McKinsey/BCG/Bain) consulting-style charting standards and offers report-grade analytical annotations such as difference labels (total, hierarchical, compound growth rate), trendlines, reference lines/regions, and highlight coloring. Supports connecting to Feishu Sheet/Base/Fengshen data sources and keeping them synced; recreating charts from reference images; creating new Feishu Docx documents or inserting/replacing Chart Assistant cards in existing documents; exporting transparent-background PNGs and inserting them into Feishu Docs as selected by the user; and explaining and validating Chart Assistant configurations. Use whenever the user explicitly mentions Chart Assistant, editable charts or configurations, built-in Chart Assistant templates or cards, data-source syncing, turning Fengshen or Feishu Sheet/Base links into editable charts, or requests MBB/consulting-style charts or recreation from a reference image—even if they do not mention the skill name. Do not take over ordinary requests like “make a chart” or “draw a trend chart” unless they require the product capabilities above; do not trigger the chart-creation workflow when only a textual explanation is requested and no chart is to be created
Extract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data from a chart image, transcribe numbers from a graph, digitise a chart, or turn a screenshot of data into a table. Produces a structured table with extracted values, confidence levels, and a reconstructed chart source. Best used with Claude Opus 4.7 or newer for reliable chart data extraction.
Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks
Analyze local ChatLab chat records via the clb CLI. Use when the user asks an external agent to inspect conversations, find evidence, summarize topics, compare members, or analyze the relationships of specific people or groups based on already-imported ChatLab data.
Universal ChromaDB integration patterns for semantic search, persistent storage, and pattern matching across all agent types. Use when agents need to store/search large datasets, build knowledge bases, perform semantic analysis, or maintain persistent memory across sessions.
Use when a user's request is vague, ambiguous, or underspecified. Explores the codebase first, then runs an iterative Q&A loop grounded in the findings until ambiguity is gone. Outputs a clear, well-scoped context brief so the user can plan sharply. Triggers on "I want to...", "I need...", "let's build...", "can you help me...", "we should...", or any request where the full scope isn't immediately clear.
Build with Claude Messages API using structured outputs (v0.69.0+, Nov 2025) for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, model deprecations (3.5/3.7 retired Oct 2025). Use when: building chatbots/agents with validated JSON responses, or troubleshooting rate_limit_error, structured output validation, prompt caching not activating, streaming SSE parsing.
Pull the image sitting on the user's clipboard into the conversation so you can actually look at it. A local bridge exposes the clipboard as a per-user Unix socket ($HOME/.clipboard.sock; CLIPBOARD_SOCKET overrides); this skill retrieves the bytes, saves them as a real image file, and reads that file into context. Use it whenever the user points at something visual you cannot see — "look at my clipboard", "I just took a screenshot", "check out this error", "why does this look wrong", "here's the design", "see the paste" — including when they only imply they copied something, and including when they describe on-screen content without giving you a file path. Reach for it instead of guessing, asking them to describe the picture, or asking them to save the file somewhere first.
The complete exploitation chain after cloud credentials (AK/SK) are leaked. Use after obtaining cloud platform Access Key and Secret Key through information leaks, .env files, git leaks, or SSRF metadata. Use when credentials in formats such as AWS AKIA*/ASIA*, Tencent Cloud AKIDz*, Alibaba Cloud LTAI* are obtained. Covers the full attack chain from credential configuration → permission enumeration → resource takeover → backdoor persistence. Complements cloud-iam-audit (which focuses on policy analysis) — this skill focuses on hands-on exploitation actions once credentials are obtained. CAM/COS/CVM/SCF exploitation in Tencent Cloud competition scenarios is a key focus. Use this skill whenever any cloud API key, temporary credential, or STS Token is discovered
Cloud IAM permission auditing and privilege escalation. Use when cloud platform credentials (AWS AK/SK, Azure SPN, GCP SA, Tencent Cloud SecretId/SecretKey) are obtained and the permission scope and privilege escalation paths need to be assessed. Covers IAM/CAM policy analysis for AWS/Azure/GCP/Tencent Cloud, common privilege escalation paths (PassRole, AssumeRole, Lambda/SCF escalation), cross-account attacks, and CloudTrail/CloudAudit evasion. Use this skill whenever any cloud credential, AK/SK, or SecretId/SecretKey is discovered
Assess whether a project is ready for cloud-native deployment. Evaluates statelessness, config, scalability, and produces a readiness score (0-12). Use when user asks about containerization readiness, Docker/Kubernetes compatibility, deployment feasibility, whether their app can run in containers or the cloud, or wants a pre-deployment assessment. Also triggers on "/cloud-native-readiness".
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Includes critical guidance on choosing between Agents SDK (infrastructure/state) vs AI SDK (simpler flows). Use when: deciding SDK choice, building WebSocket agents with state, RAG with Vectorize, MCP servers, multi-agent orchestration, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors.
Build with D1 serverless SQLite database on Cloudflare's edge. Use when: creating databases, writing SQL migrations, querying D1 from Workers, handling relational data, or troubleshooting D1_ERROR, statement too long, migration failures, or query performance issues.
Build semantic search with Cloudflare Vectorize V2 (Sept 2024 GA). Covers V2 breaking changes: async mutations, 5M vectors/index (was 200K), 31ms latency (was 549ms), returnMetadata enum, and V1 deprecation (Dec 2024). Use when: migrating V1→V2, handling async mutations with mutationId, creating metadata indexes before insert, or troubleshooting "returnMetadata must be 'all'", V2 timing issues, metadata index errors, dimension mismatches.
Build durable, long-running workflows on Cloudflare Workers with automatic retries, state persistence, and multi-step orchestration. Supports step.do, step.sleep, step.waitForEvent, and runs for hours to days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, coordinating API calls, scheduling multi-step tasks, or troubleshooting NonRetryableError, I/O context, serialization errors, or workflow execution failures. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI agent development, or migrating existing/GitHub apps that need VPC access to MySQL/PostgreSQL/Redis. Also use when diagnosing CloudRun container deploy failures (deploy_failed, readiness/probe failed, image won't start, docker.io pull loops) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
Multi-agent code review run as a debate. Critics raise findings in parallel, an Author defends the change, Critics concede or maintain, and a Judge rules on what stays contested. Findings are classified by kind and blocking, and handled durably when previously decided. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to findings and record intentional non-fix decisions beside the relevant code. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes or adding decision comments
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram from source code.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Use when the user wants Claude to send images to OpenAI Codex — Codex-side review of an existing screenshot/mockup/wireframe, generate an image via Codex's image_gen tool, or edit an existing image via Codex — or explicitly invokes "codex-vision" / "/codex-vision". Wraps the upstream `codex exec -i` CLI with three modes (review / generate / edit) and an opt-in tmux session prefixed `claude-codex-` so the user can attach and watch. SKIP when the task is text-only, or when the user needs a durable multi-turn repo task — use codex-tmux-dev for long-running image+coding work. The bare word "codex" is not a trigger; the bare word "screenshot" is not a trigger. For generate/edit, require explicit Codex intent unless the user invoked the skill by name. Explicit `/codex-vision` invocation overrides every other gating rule below.
Writes a phone script for a cold or lukewarm call from a B2B service company (dev or IT outsourcing, agency, AEC/BIM outsourcing, consultancy) to one buyer role. Built around a real reason for the call, one or two guesses about the buyer's situation, a single question about what the problem costs, proof that fits in one breath, and an ask for a concrete slot or for the right person. Includes exits for the objections service sellers hear most: "we have an in-house team", "we already have a vendor", "send your rates", "no projects right now". Use when the user says "cold call script", "call script for [role]", "how do I open this call", "what do I say when I call", "скрипт дзвінка", "холодний дзвінок", "що казати на дзвінку", or describes a target and wants a phone framework. Script is written in the prospect's language. NOT the pre-call brief for a booked meeting (meeting-prep), NOT a written reply to an objection in a thread (reply-objection-handler).
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.