Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Scandit ID Capture (`IdCapture`) in Flutter projects — scanning passports, driver's licenses, ID cards, residence permits, visas via MRZ, VIZ, barcode, or mobile documents. Use for integration, accepted-document and scanner configuration, captured-field result handling, anonymization, add-on capabilities (voided-ID detection, European driving-license back decoding, AAMVA barcode verification), and SDK version migration.
Turn rough ideas into structured, validated idea documents through collaborative dialogue. Explores context, asks clarifying questions one at a time, proposes alternative approaches with feasibility evaluation, and produces documents ready for requirements definition. Use when: ideation, brainstorm, new idea, explore an idea, I want to build, what if we, let's think about, propose approaches, evaluate this idea, idea document, アイデア出し, 案出し, ブレスト, アイデアを整理, 検討したい.
This skill should be used when the user asks about IFRS, International Financial Reporting Standards, IFRS 15 revenue, IFRS 16 leases, IFRS 9 financial instruments, IFRS 10 consolidation, IAS 36 impairment, IFRS 13 fair value, IFRS disclosure notes, IFRS recognition, first-time adoption IFRS, or IFRS vs GAAP. Guides application and explanation of IFRS financial reporting—recognition and measurement by standard, presentation and disclosure (IAS 1, IFRS 7), fair value hierarchy, going concern and materiality, significant judgments and estimates, first-time adoption (IFRS 1), consolidation and business combinations, local GAAP convergence context, and audit-ready note disclosure structure—not US GAAP-only ASC deep dives (note high-level differences only), tax law advice, legal entity structuring, full external audit execution (auditor), ERP configuration (senior-software-engineer), or management accounting without a reporting-standards lens.
Unified IMA OpenAPI skill supporting note management and knowledge base operations. Use this skill when the user mentions a knowledge base, data repository, notes, memos or note-taking, or wants to upload files, add web pages to a knowledge base, search knowledge base content, or search/browse/create/edit notes. Even if the user does not explicitly say "knowledge base" or "notes", trigger this skill whenever the intent involves uploading files to a knowledge base, bookmarking web pages, knowledge search or personal document access (such as "make a note of this for me" or "search the knowledge base for XX").
Software development engine for coding. A production-grade skills system for web apps and mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems
Describe images, screenshots, diagrams and charts from visual inspection. Preserve visible text, counts, labels, directions and uncertainty; distinguish observation from interpretation. Use for image summaries, screenshot explanations and diagram descriptions.
Build, review, debug, configure, or plan Apify Impit browser-impersonating HTTP clients with current docs. Use for impit 0.14 (npm 0.14.x, PyPI 0.14.x), Impit.fetch, ImpitOptions, TLS/HTTP fingerprinting, JA4, Chrome/Firefox/OkHttp/iOS fingerprints including chrome151, HTTP/3, streamed request bodies, proxies, cookieJar, tough-cookie, ignoreTlsErrors, Node/Python/Rust bindings, Crawlee ImpitHttpClient, and replacing got-scraping or plain fetch/axios when bot detection blocks non-browser TLS fingerprints.
Design and audit incident status page operations covering component taxonomy, incident declaration, public/private updates, subscriber notifications, templates, severity, SLO impact, customer segmentation, uptime history, maintenance windows, post-incident follow-up, support coordination, and trust-preserving communications. Use when reliability incidents need accurate external communication.
Multi-channel information search and verification for new products and new technologies, saving reliable information to the knowledge base. Prefers authoritative tech media and ignores outdated sources. Use this skill when the user mentions "最新信息", "新产品", "新技术", "搜索资料", "查资料", or "了解 XX".
Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites - (1) company research, (2) financial modeling, (3) valuation analysis, (4) chart generation, (5) final report assembly. Each task produces specific deliverables (markdown docs, Excel models, charts, or DOCX reports). Tasks 3-5 have dependencies on earlier tasks.
Use when starting work on a Jira ticket and you need full context — not just summary, but attachments (screenshots, mockups), comments (where repros usually live), linked issues, and custom fields. Use when `acli jira workitem view` returns a description that's just a media reference like `image-20260427-021811.png` and you can't see what the bug is. Use when an AI agent is about to guess at a bug from the summary or about to ask the user to paste a screenshot it could fetch itself. Use when authenticated curl against the Jira REST API returns 401, 403, or 406.
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initialize from any available deal artifact (SPA, deal summary, closing checklist) and connect to deal-context.md and closing-checklist.yaml from the M&A cold start. Use when the user says "integration", "post-closing", "consents pending", "contract assignment", "integration status", or "what's left on the deal".
Design resilient HTTP, messaging, and scheduled integrations for Kotlin plus Spring services with explicit timeout budgets, retries, idempotency, circuit breakers, DLQ behavior, and failure observability. Use when integrating with unstable external systems, designing retry logic, handling duplicate delivery, preventing thundering herds, or making message-driven and scheduled workflows safe in production.
Route ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing a workflow. Use when user is unsure where to start/how to approach work, asks for the right workflow, or combines intents such as fixing and refactoring. NOT for a clear task.
Performs discounted cash flow valuation using the appropriate model variant (DDM, FCFE, or FCFF) with configurable growth stages. Produces year-by-year cash flow projections, terminal value, equity bridge (subtract debt, add cash, subtract option value), per-share intrinsic value, and sensitivity analysis. Use when valuing a company intrinsically, building a DCF model, estimating fair value, or when user mentions DCF, discounted cash flow, intrinsic value, terminal value, or free cash flow valuation.
Add data to an ongoing investigation — documents, interview transcripts or observations. Batch-process against documented screening criteria, surface material items, and log everything reviewed for coverage verification. Use when new evidence, interview transcripts or documentary material arrive in an ongoing investigation.
Add Face ID / Touch ID / fingerprint authentication to an Ionic Capacitor app via @aparajita/capacitor-biometric-auth. Trigger when adding biometric login, app lock, secure reauthentication, or Face ID/Touch ID gating to a sensitive feature.
Operate the joelclaw event bus, gateway, observability, and agent loop infrastructure via the joelclaw CLI. Use for: sending events, checking runs, starting/monitoring/cancelling agent loops, debugging failed runs, checking health, restarting the worker, inspecting step traces, managing subscriptions, gateway operations, OTEL queries, semantic recall. Triggers: 'joelclaw', 'send an event', 'check inngest', 'start a loop', 'loop status', 'why did this fail', 'debug run', 'check worker', 'restart worker', 'runs', 'what failed', 'subscribe', 'gateway', 'otel', 'recall', or any Inngest/event-bus/agent-loop task.
Build trading systems in the style of Jump Trading, the high-frequency trading firm pioneering FPGA-based trading. Emphasizes hardware acceleration, network optimization, and nanosecond-level execution. Use when building FPGA trading systems, network-optimized infrastructure, or ultra-low-latency order execution.
This skill should be used when users want to create, convert, or manage Justfiles for command automation. It handles converting Makefile, npm scripts, or shell commands to Justfile format, generating project-specific templates, and providing Justfile syntax guidance. Triggers on requests mentioning justfile, just command, command runner, Makefile conversion, or task automation.
JSON Web Tokens for authentication. Covers token structure, signing, and validation. Use for stateless authentication. USE WHEN: user mentions "JWT", "token authentication", "access token", "refresh token", asks about "stateless auth", "token signing", "token validation" DO NOT USE FOR: session-based auth (use session management), OAuth flows (use oauth2 skill), NextAuth.js (use nextauth skill)
UI animations necessity judgment, recommendations for motion design, implementation strategies, and performance/accessibility reviews. Targets include hover, active, focus, popover, tooltip, dropdown, dialog, tab, segmented control, card, button, toast, accordion, carousel, scroll-linked animation, View Transitions, and more.
How to operate the Kuroco admin API (admin_api) with the CLI tool "kuroco-admin". Explore API models and methods (discover, advise, fetch llms.txt), retrieve schemas, and run admin operations such as creating content or registering members with a single command from Bash. Use when the environment cannot be configured for an MCP connection or when you want to run admin_api from within shell scripts. For admin operations from an AI agent, Admin MCP (the kuroco-admin-mcp skill) is recommended.
[KWC KS Controller development-phase Skill] Activates only when the app/ks/controller/ directory exists. Focuses on writing .kws metadata and implementing TypeScript/KingScript code for KingScript script controllers. Does not handle project creation, build or deployment (delegated to kwc-project-scaffold). When KingScript language specification and SDK usage are involved, reference the kingscript-code-generator skill package. If the task involves the kd CLI, build or deployment, you must switch to kwc-project-scaffold.
Research and use customer language across Product and Marketing. Use when writing product copy, crafting landing page messaging, or need to understand how customers describe their problems. Sales Safari methodology for finding watering holes, extracting pain language, and creating resonance.
Write, scaffold, explain, and refactor code using the `lorisleiva/laravel-actions` package. Use this skill whenever the user mentions Laravel Actions, `AsAction`, `php artisan make:action`, action classes, converting a controller, job, listener, or command into an action, dispatching an action as a job, using an action as a controller or listener, or adding validation, authorization, testing, or mocking around an action.
Feishu document toolkit: upload markdown as styled docs, optimize existing pages, fetch as markdown, analyze structure, apply keyword highlights, verify quality. Use when user wants to: upload md to feishu, optimize feishu doc, fetch feishu page, analyze document, highlight keywords, verify feishu doc. Triggers on: lark-hirono, feishu upload, feishu optimize, feishu fetch, feishu analyze, feishu highlight, feishu verify.
Review product legal terms and policy surfaces covering Terms of Service, privacy policy links, acceptable use, refunds, trials, renewals, cancellation, billing disclosures, AI disclaimers, marketplace rules, store policies, consent, regional notices, versioning, change notice, and support/legal escalation. Use when product flows or public copy create legal commitments or user obligations.
This skill should be used when implementing features from Linear issues with full TDD workflow, automated planning, parallel code reviews (security and Rails best practices), systematic feedback implementation, and automated PR creation with Linear integration. Use when the user provides a Linear issue ID (e.g., "TRA-9", "DEV-123") and wants a complete implementation workflow from issue to PR.
Run parallel reviewer subagents across a target repo or diff to surface findings across correctness, security, maintainability, performance, tests, dead code, and dependency health, dedup them against a persistent ledger and Linear, then triage survivors into Linear tickets. Use when the user wants a code review, repo health audit, or to turn review findings into tickets.
Mine LITCOIN — a proof-of-comprehension and proof-of-research cryptocurrency on Base. Use when the user wants to mine crypto with AI, earn tokens through reading comprehension or solving optimization problems, stake LITCOIN, open vaults, mint LITCREDIT, manage mining guilds, deploy autonomous agents, or interact with the LITCOIN DeFi protocol.
Literature review writing tool for top-tier journal papers. Based on the research topic or research question provided by the user, it automatically retrieves real academic literature, verifies its authenticity, and writes the literature review section following the writing standards of top journals (such as AMJ, ASQ, SMJ, MISQ, OS, JCR, JMR, etc.). It uses a funnel structure, emphasizing the connections between studies, evolution trends, and research gaps. Triggered when the user mentions needing to write a literature review, provides a research topic or research direction, or asks for a review written in top-journal style. Note: this skill is for writing literature reviews, unlike paper-analyzer (which is for breaking down existing papers).
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.