Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill when the user wants to install, configure, download, or synchronize online resumes for candidates who applied to currently open BOSS/Zhipin recruiter jobs. Provides a cross-platform boss-agent-cli setup, standard CDP/Chrome conventions, persistent resume root, job/candidate JSON indexes, full and per-job incremental sync, and randomized delay during bulk downloads.
Use when reviewing the code/configuration changes on a Datex Studio feature branch. Traces dependencies, reads unified diffs across all changed configs, and produces a structured review with bugs / quality / security / performance / simplification / alignment findings plus a verdict. Trigger for: "review branch X", "code review this branch", "review the changes on <branch>", "audit branch before merge", "quality check this branch". For drafting a commit message on the same branch, use `commit-message-generator`.
Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP. Use when a user asks to create a dashboard, put several metrics/charts together on one page, assemble a dashboard for a topic (product analytics, retention, revenue, activation, etc.), or add/remove/replace insights on a dashboard they already have. Covers deciding create vs update, reusing existing insights vs creating new ones, and using PostHog's vetted dashboard templates as reference for what a strong dashboard on a topic looks like.
Use when building MCP (Model Context Protocol) servers to enable LLMs to interact with external services through well-designed tools. Triggers include requests to create MCP servers, integrate external APIs or services, or build MCP tools in Python (FastMCP) or Node/TypeScript (MCP SDK).
Upgrades a Capacitor app from v8 to v9 (prerelease, installed with @next until GA). Covers preflight (Node 24, Xcode 27, Android Studio 2026.1.1, UIScene adoption from 8.5), `npx cap migrate`, and the manual checklist - iOS 16 target, @UIApplicationMain to @main, removed CAPBridge APIs, AGP 9.2.1, Gradle 9.5.1, SDK 37/minSdk 26, gradle.properties cleanup, built-in Kotlin, jcenter removal, core-ktx, proguard-android.txt rename, optional Cordova runtime, `cap run --url`, push `alert` removal, splash fade default. Use for "upgrade to Capacitor 9", errors like "'@UIApplicationMain' is deprecated", "Could not find method jcenter()", getDefaultProguardFile('proguard-android.txt') failures, duplicate Kotlin plugin, duplicate class core-ktx, "unknown option '-l'". Do not use for 8.4 to 8.5 UIScene only (use capacitor-uiscene-migration), plugin libraries (use capacitor-plugin-upgrade-v8-to-v9), or older majors.
Prepare accountable executive decisions, decision support, briefings, information triage, calendar choices, and institutional memory. Use for chief of staff or CoS, executive operations, founder operations, operating rhythm, strategic attention, executive office, board materials, organizational sensing, team health, leadership transitions, gatekeeping, decision memos, executive briefing, strategic time, attention allocation, calendar triage, or meeting audits for a solo operator or organization. Do not use for generic personal assistance, employee surveillance, inferred commitments, automatic task mutation, meeting facilitation, org structure design, or business operating-process design; route to the owning specialist.
Rules for canister code on a cloud engine (CloudEngine subnet, e.g. OpenCloud). Engine canisters hold 0 cycles: never attach cycles you computed: drop `(with cycles = …)` clauses (IC0504). Cross-subnet calls must be bounded-wait and cycle-free (`(with timeout = N)`, `Call::bounded_wait`) or rejected: 'Unbounded-wait calls and calls with cycles are not allowed to CloudEngine subnets'. HTTPS outcalls use the ordinary wrapper and are free; never via the proxy ('Replicas had different responses', InsufficientCycles). XRC, threshold ECDSA/Schnorr, vetKD, the Bitcoin API and EVM/SOL RPC (Bitcoin, Ethereum, VetKeys) go via the engine's proxy canister: before writing that code, ask the user for its id or to deploy one in the console. Hand-encode arguments: ic-vetkeys and ic-cdk chain-key helpers attach cycles. Derived keys belong to the proxy. Use when planning, writing or debugging engine canister code, signing or deriving keys, or on these errors. Do NOT use for deploying a proxy (deploy-to-cloud-engine).
Delegate coding, review, diagnostics, planning, structured output, and local browser research tasks to independent Codex sessions via the Codex CLI. Use cases include starting new tasks with `codex exec`, continuing multi-turn sessions with `codex exec resume`, read-only review with `codex exec review`, and cases needing `--json` event streams, `-o` final-message output to disk, image input, or Computer Use browser actions.
Writes personalized cold emails by researching prospects, crafting attention-grabbing openers, and scoring drafts against a quality rubric. Use when the user asks to write cold emails, outreach emails, sales prospecting messages, outbound email campaigns, or B2B email sequences.
Use when generating a commit message for a Datex Studio feature branch. Reads the branch's pending changes, config diffs, and dependencies, resolves the work item the branch traces back to, then drafts a well-formed title + body carrying that reference. Trigger for: "generate a commit message for branch X", "write a commit message", "draft a commit for this branch", "what should the commit say", "suggest a commit message", "does this commit reference a ticket", "traceability check". Runs interactively or unattended — one-shot mode, signalled in the prompt, never asks and delivers through a named tool. For reviewing the branch's code quality, use `branch-code-reviewer` instead.
Trigger this skill when an AI agent encounters the following situations in legal reasoning: (1) multiple legal provisions apply to the same facts (competing statutory provisions); (2) evidence contradicts or is inconsistent with other evidence (evidence conflicts); (3) a case has multiple points of dispute requiring a determination of hearing or analysis order (prioritizing disputed issues); (4) different legal sources (statutes, regulations, judicial interpretations, local regulations, etc.) make different provisions on the same question (conflicts of legal sources); (5) there is tension between a party's claims and the application of law that needs to be reconciled. This skill is a core hub capability of legal reasoning, and almost all complex legal analysis involves some form of conflict resolution.
Principles and patterns for effective collaborative work (coworking). Use for aligning agents on communication etiquette, workspace hygiene, and feedback loops. Use proactively when coordinating multi-agent workflows, managing vault hygiene, or standardizing status updates. Examples: - user: "How should we work together?" -> review coworking principles - user: "Give me a status update" -> use 3P status reporting pattern - user: "Keep the workspace clean" -> apply vault hygiene rules - user: "Coordinate the specialists" -> follow collaboration patterns
Audit your calendar with Cowork's calendar tools -- measure meeting load and fragmentation, identify which recurring meetings earn their slot, propose consolidations and focus blocks, and draft the diplomatic messages that reclaim your week.
Sweep your folders and downloads for tax documents and build a CPA-ready package -- checklist by form type, everything renamed and organized, a missing-document chase list, and flagged items worth asking your accountant about. Organization, not tax advice.
Use this skill when the user wants to create a new issue, report a bug, submit a feature request, or discuss a requirement before implementation. "create issue", "report bug", "create-issue", "submit issue", "新建 issue", "提需求", "提 bug". Requires Gitee MCP Server to be configured.
This skill should be used when a user needs help debugging a Snowflake SQL query, understanding a Snowflake query failure, isolating incorrect results, fixing joins or filters, diagnosing performance problems, or turning a vague warehouse error into a concrete root cause and corrected query. It is a standalone Snowflake query debugging skill for ad hoc SQL work across databases, schemas, and environments.
Find visual references for a page or component, or turn a website or screenshot into a design brief. Use ui-pattern-research to choose interaction patterns and design-md to extract existing conventions. Output sourced design directions tailored to the current product.
When designing distributed systems for scalability, reliability, and consistency. Covers CAP/PACELC theorems, consistency models (strong, eventual, causal), replication patterns (leader-follower, multi-leader, leaderless), partitioning strategies (hash, range, geographic), transaction patterns (saga, event sourcing, CQRS), resilience patterns (circuit breaker, bulkhead), service discovery, and caching strategies for building fault-tolerant distributed architectures.
Create, edit, and validate DingTalk AI Card (A2UI) JSON files with native DWS commands. Use for cards built from requirements or images, structural protocol errors, named component or function contract lookup, and cloud templates created, retrieved, or revised by template ID and version. Send a card to the current user only when a preview is requested.
Explain the design rationale and domain concepts behind the Ledger Device Management Kit (DMK) API, including Clear Signing, Secure Channel, Ledger OS (BOLOS), Device Actions vs Commands, sessions, transports, derivation paths, and Genuine Check. Use when a developer asks 'what is X?' about a DMK concept, 'why does X work this way?' about an API design decision, or 'what's the difference between X and Y?' for DMK components.
Map developer intent and natural language to the correct Ledger Device Management Kit (DMK) components, operations, and API methods. Use when a developer's request is phrased informally, incompletely, or in terms of outcomes rather than API methods, when the intent is ambiguous and needs mapping to a specific DMK component or operation, or when a developer asks 'how do I...', 'what's the difference between...', or describes a symptom rather than an API.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Generate high-density editorial HTML info cards in a modern magazine and Swiss-international style, then capture them as ratio-specific screenshots. Use when the user provides text or core information and wants: (1) a complete responsive HTML info card, (2) the design to follow the stored editorial prompt, (3) output in fixed visual ratios such as 3:4, 4:3, 1:1, 16:9, 9:16, 2.35:1, 3:1, or 5:2, or (4) both HTML and a rendered PNG cover/card from the same content.
Advanced window and view management patterns for Electrobun desktop applications. This skill covers multi-window architectures, BrowserView for embedded webviews, window lifecycle management, window orchestration, tab systems, and complex window hierarchies. Use this skill when building applications with multiple windows, implementing browser-like tab interfaces, managing parent-child window relationships, creating floating panels or toolbars, implementing picture-in-picture modes, managing window state persistence across sessions, or building applications that require sophisticated window coordination. Triggers include "multiple windows", "tab system", "BrowserView", "window orchestration", "floating window", "child window", "window state", "window manager", "multi-window app", or discussions about complex window management in Electrobun desktop applications.
Build or modernize an employee handbook for a small business with no HR department -- interviews the owner for actual practices, drafts every core policy in plain English, flags the state-specific requirements that need local verification, and outputs a document employees might actually read.
Query EVM chain data via Etherscan API v2. Use for on-chain lookups where Etherscan v2 applies: balances, transactions, token transfers (ERC-20/721/1155), contract source/ABI, gas prices, event logs, and verification of transaction completion. Also trigger when another tool submits a transaction and you need to confirm it finalized on-chain.
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks section, Evidence rows, and Progress log; ACCEPTANCE.md is gone — acceptance criteria live in the unit doc and Evidence rows are the receipts.
System prompt design and instruction crafting for AI agents. Covers persona definition, constraint specification, output formatting, tool use instructions, multi-turn behavior, and guardrail design. Use when writing system prompts for AI products, designing agent personas, specifying behavioral constraints, crafting tool-use instructions, or building multi-step agent workflows.
Performs Kerberoasting (MITRE ATT&CK T1558.003) using Impacket's GetUserSPNs.py to request Kerberos TGS tickets for SPN-registered service accounts, then cracks the extracted RC4/AES-encrypted hashes offline to recover service account credentials. Use during authorized Active Directory penetration tests or red-team engagements for credential access against service accounts via Kerberos ticket-granting-service requests.
Read and write Feishu (飞书) docs, sheets, Base (bitable), Drive files, calendar events, tasks, wiki, and IM messages via the Feishu Open Platform REST API. Use when the user mentions 飞书 / Feishu / Lark, a Feishu document or sheet link, their Feishu calendar, or wants to send a Feishu message.
A bidirectional integration channel between Feishu (Lark/Feishu) and OpenClaw. Uses a Feishu bot to receive and send messages, supporting private chats, group chats, @mention detection, card messages, and file transfer. Use this skill when you need to interact with an AI assistant through Feishu, trigger AI responses from received Feishu messages, or send messages from OpenClaw to Feishu. Difference from feishu-automation: this skill focuses on message channel integration, while feishu-automation focuses on automating operations on the Feishu platform (multi-dimensional tables, documents, etc.).
Use when recreating a Figma design as Hydrogen + Weaverse pages in this repo — turning a Figma file, frame, or flow into reusable Weaverse sections. Triggers on a figma.com URL, "build this design", "implement this Figma", or "create the storefront from the design". The Figma counterpart of cloning-websites-to-weaverse.
Build and review assumptions-led financial models, unit economics, pricing, fundraising scenarios, and SaaS operating metrics. Use when calculating CAC, LTV, payback, runway, ARR, churn, NDR, Rule of 40, or sales efficiency; when modeling revenue, costs, cash flow, outcome-linked partnerships, revenue-share fees, pricing, cap tables, or financing. Do not use this skill for unrelated requests; route to the nearest named specialist.
Design, implement, or repair production observability in Flutter using operational logs, error and crash capture, breadcrumbs, traces, release context, privacy controls, and verification. Use for diagnosability and incident signals; not product analytics, profiling-only optimization, or a general code review.
Implement or review Flutter platform channels, Pigeon APIs, FFI and build hooks, native plugin implementations, platform views, add-to-app boundaries, web interop, and native lifecycle integration. Use when Dart must communicate with native platforms; route reusable package APIs, federation, and publication readiness to flutter-package-development.
Design or review Flutter state ownership, update flow, and package integration. Use for setState, Listenable, Provider, Riverpod, Bloc, Redux, or custom state problems; preserve the project's established approach unless migration is requested.
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.