Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when implementing client-side form features in Frappe/ERPNext: field visibility, cascading filters, calculated fields, custom buttons, server calls, form validation, child table logic, debugging. Covers step-by-step workflows from Setup > Client Script through migration to custom app JS. Keywords: how to implement client script, form logic workflow, dynamic UI, calculate fields, frm.call, frappe.call, frappe.xcall, client script testing, field dependency, custom button, how to hide field, show field based on value, add button to form, calculate total, dynamic form.
Use when implementing OAuth providers, Connected Apps, Webhooks, Payment Gateways, or Data Import/Export in Frappe. Prevents authentication failures from wrong OAuth flow, missed webhook deliveries, and data corruption during bulk imports. Covers OAuth2 provider/client, Connected App DocType, Webhook DocType, Payment Gateway integration, Data Import, Data Export, frappe.integrations module. Keywords: OAuth, Connected App, Webhook, Payment Gateway, Data Import, Data Export, integration, API key, OAuth2, webhook trigger, connect to external service, OAuth setup, webhook configuration, import data, export data.
Use when implementing scheduled tasks and background jobs in Frappe v14/v15/v16. Covers hooks.py scheduler_events, frappe.enqueue, queue selection, job deduplication, testing with bench execute/scheduler, monitoring via Scheduled Job Log and RQ Dashboard, error handling, long-running job patterns, email digest, data cleanup, and report generation. Keywords: schedule task, background job, cron job, async processing, queue selection, job deduplication, scheduler implementation, run task automatically, background process, scheduled task not running, async task.
Use when building custom dialogs, extending List View, creating Page controllers, or adding Kanban/Calendar views and realtime updates. Prevents UI freezes from synchronous calls, broken dialogs from wrong field definitions, and missed socket events. Covers frappe.ui.Dialog, frappe.ui.form.MultiSelectDialog, List View customization, frappe.pages, Kanban Board, Calendar View, frappe.realtime, socket.io publish/subscribe. Keywords: Dialog, List View, Page, Kanban, Calendar, realtime, socket.io, frappe.ui, MultiSelectDialog, publish_realtime, popup dialog, custom dialog, list view customize, realtime update, live data, kanban setup.
Use when implementing document Workflows, approval chains, or state-based transitions in Frappe. Prevents stuck documents from missing transitions, broken approval chains, and permission errors on workflow actions. Covers Workflow DocType, Workflow State, Workflow Action, transition rules, allowed roles, conditions, workflow_state field, apply_workflow. Keywords: workflow, approval, transition, Workflow State, Workflow Action, state machine, approval chain, workflow_state, approval chain, document approval, multi-step approval, workflow stuck, status transitions.
Use when configuring backups, restoring sites, encrypting backup files, scheduling automated backups, or planning disaster recovery. Prevents data loss from missing backups, failed restores, and unencrypted sensitive data. Covers bench backup, bench restore, backup encryption, S3/remote storage, scheduled backups, disaster recovery procedures. Keywords: backup, restore, encryption, S3, scheduled backup, disaster recovery, bench backup, bench restore, how to backup, restore database, backup failed, data recovery, automated backup.
Use when writing client-side JavaScript for ERPNext/Frappe form events, field manipulation, server calls, or child table handling in v14/v15/v16. Covers exact syntax for frappe.ui.form.on, frm methods, frappe.call, and browser-side validation. Keywords: client script, form event, frm, frappe.call, frappe.ui.form.on, JavaScript, UI interaction, field validation, form event syntax, how to write client script, frm example, frappe.call example.
Use when writing Python Document Controllers for ERPNext/Frappe DocTypes. Covers lifecycle hooks (validate, on_update, on_submit), controller override, submittable documents, autoname patterns, UUID naming (v16), and the flags system. Keywords: document controller, lifecycle hook, validate, on_update, on_submit, autoname, naming series, flags, v14-v16, controller example, lifecycle hook order, when to use validate, Python DocType class.
Use when configuring Frappe hooks.py for app events, scheduler tasks, document events, fixtures, boot session, jenv customization, or website routing. Covers v14/v15/v16 including extend_doctype_class. Keywords: hooks.py, doc_events, scheduler_events, fixtures, app_include_js, override_whitelisted_methods, extend_doctype_class, hooks.py example, how to register hook, available hooks list, extend_doctype_class example.
Use when writing Python code for ERPNext/Frappe Server Scripts including Document Events, API endpoints, Scheduler Events, and Permission Queries. Prevents the #1 AI mistake: using import statements in Server Scripts (sandbox blocks ALL imports). Covers frappe.* methods, event name mapping, and correct v14/v15/v16 syntax. Keywords: Server Script, frappe, ERPNext, sandbox, import, doc event, validate, on_submit, before_save, server script example, import not allowed, sandbox rules, which script type to use.
When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For downloadable content lead magnets (ebooks, checklists, templates), see lead-magnets.
Build the customer-facing Freemius Checkout UI in a React app — the Checkout Provider (overlay context), Subscribe (subscription pricing table), Topup (one-off / credit pricing table), Paywall, and custom checkout buttons. Use when adding a pricing page, an "upgrade"/"buy credits" button, an overlay checkout, or a paywall to a React frontend. Covers the React Starter Kit Checkout components and the frontend Checkout SDK (`@freemius/checkout`), plus the thin checkout-specific backend endpoints the front end depends on (the purchase-sync `POST /api/purchase`, `GET /api/checkout/pricing`, and the hosted-redirect handler); the underlying checkout-creation and entitlement-sync engine still belongs to `freemius-core`.
Build the Freemius Customer Portal in a React app — a self-service surface where a signed-in user manages their subscription (upgrade / change plan), cancels (with a churn-reducing retention coupon), edits billing information, and views payments & downloads invoices. Use when adding an "Account", "Billing", "Manage subscription", or "Invoices" page. Covers the React Starter Kit Customer Portal component and the SDK's headless portal processor (`freemius.customerPortal`); server-side checkout/entitlement sync is `freemius-core`.
Installs or upgrades gate-cli to the latest official GitHub release and sets up gate-skills on Cursor, Claude Code, Codex, or OpenClaw/mcporter. Triggers on 'install gate-cli', 'upgrade gate-cli', 'update gate-cli', 'Gate skills', 'Gate Verify', 'tx check-in', 'setup Gate Cursor', 'Gate Claude Code', 'Gate Codex', 'OpenClaw Gate', 'mcporter Gate'.
Use this skill whenever the user wants Gate Exchange asset allocation optimization for spot holdings (list eligible assets, load config, evaluate/preview, place orders, query history). Trigger phrases include "asset allocation optimization", "allocation configuration", "portfolio allocation", "rebalance spot to stablecoin", "Top 5 market cap allocation", "optimize holdings to BTC", "preview allocation optimization", "allocation optimization order list".
Use when a tabular dataset (CSV, Excel, Parquet, Stata, SAS) needs a data dictionary. Profiles every variable (type, levels, range, missingness) into codebook.md and codebook.json and flags coded values of unknown meaning as [NEEDS DICTIONARY] instead of guessing.
Use this skill when a user provides a torrent name or file name and wants to fix recognition issues, or asks to add/manage custom identifiers (自定义识别词). This skill generates identifier rules based on the WordsMatcher preprocessing logic, checks for duplicates against existing rules, and saves them through the structured MoviePilot API gateway. Because custom identifiers are global, generated rules must default to conservative, sample-specific regex patterns instead of broad matches unless the user explicitly wants global cleanup. Applicable scenarios include: 1) A torrent or file name is incorrectly recognized (wrong title, season, episode, etc.); 2) The user wants to block unwanted keywords from torrent names; 3) The user needs episode offset rules for series with non-standard numbering; 4) The user wants to force recognition of a specific media by source-native ID; 5) The user wants TV recognition to use a specific TMDB episode group.
Adopt GitHub Agentic Workflows (gh-aw) in any repository. Investigates existing workflows, identifies gaps, creates agentic workflows, and handles CI/merge issues. Auto-activates for gh-aw adoption, agentic workflow setup, or workflow automation requests.
Shared git conventions for personal repos covering remote naming, primary remote choice, conventional commit shape, worktree placement, and commit/PR writing style. Use when setting up or renaming remotes, choosing where to push or open PRs, deciding where a worktree lives, or when another git skill points here.
Work with GitLab attestations for software supply chain security including artifact verification and provenance. Use when verifying software artifacts, managing attestations, or working with supply chain security. Triggers on attestation, verify artifact, provenance, supply chain security.
Operate GitLab through the glab-axi CLI - issues, merge requests, CI/CD pipelines, projects, labels, CI/CD variables and secrets, releases, search, and raw API access. Use whenever a task touches GitLab: listing or filing issues, reviewing or merging merge requests, checking pipeline status and failed job logs, managing CI/CD variables and secrets, cutting releases, or querying the GitLab API.
Manage GitLab runner controllers and authentication tokens. Create, inspect, update, delete controllers; manage scopes; and generate, rotate, and revoke tokens. Admin-only experimental feature for managing runner controller lifecycle. Triggers on runner controller, controller token, controller scope, experimental runner, admin runner.
Access Google Workspace (Drive, Docs, Sheets, Gmail, Calendar, Chat, Meet, Admin) via the `gws` CLI. Use this skill when the user wants to read, write, or manage Google Docs, Sheets, Drive files/folders, Gmail messages, Calendar events, or any other Google Workspace resource. Triggers on: Google Docs, Google Sheets, Google Drive, Google Calendar (via gws), Google Chat, Google Meet, spreadsheet operations, document editing, file uploads, sharing permissions, Gmail triage, or any mention of `gws` commands.
Hike Capital's knowledge base of investment cognition and methodology. Load this skill when the user needs to reference Hike investment-logic thesis frameworks, investment MEMO / Tablet writing standards, or industry-analysis and due-diligence methodologies, or to resolve common forms of address such as Kevin, 宇超, and 思行 into specific team members and get their Feishu names and user_id. Always use this skill for resolving internal Hike members' names and looking up user_id — not generic contacts tools. It covers the THESIS & RISK loop, three-perspective argumentation, the MEMO ten questions, and the team directory. Use hike-lightyear for project data, hike-seek for talent, and hike-portfolio-report for portfolio operating-data reports.
The CLI for Hike Capital's Lightyear investment project management system. Load this skill when the user needs to query the project database, pull project lists, filter projects by stage/industry/valuation/quadrant, view post-investment stages and the investment pipeline, get system statistics, or mentions terms such as Lightyear, 光年, project intake, project meeting, investment decision meeting, closing, or quadrant. It provides lightyear_cli for project data queries and multi-dimensional filtering. Use hike-seek for talent, hike-portfolio-report for portfolio operating reports, and hike-knowledge for investment MEMO/decision MEMO standards.
Operating-data report generator for Hike Capital portfolio companies, currently supporting only Halara (other portfolio companies are out of scope for now). Load this skill when the user needs to generate a Halara weekly/monthly/quarterly report, view Best Sellers or the bestseller list, analyze operating data, monitor sales, view product rankings, review growth, or track ranking changes, or mentions terms such as Halara report, Halara data, or product analysis; it produces an HTML report.
Shanxing Zhitansystem CLI. Talent network: Use when the user needs to look up or add talent, search the talent pool, filter by field/company/owner, view talent assigned to me or awaiting evaluation/follow-up, rate talent, view or add interview records, or link talent to a Lightyear project. Meetings: Use when the user needs to view their meeting list, meeting minutes (MEMO) and feedback status, submit meeting feedback, generate or finalize meeting minutes, add attendees, or create a retroactive meeting entry. All Zhitansystem meeting operations for project or networking meetings—including minutes, feedback, and attendees—use this skill; only native Lark operations such as calendar events and room bookings belong to the lark series of skills. Financial report data: Use when the user needs to view financial report research tasks or upload the JSON of the three-part report package (financial metrics/media insights/stock charts) to Zhitansystem. Use hike-earnings-core / hike-earnings-media / hike-earnings-chart to generate or extract the report documents themselves. Load this skill when terms such as 智探, seek, talent network, talent pool, talent, interview, project meeting, networking meeting, meeting, meeting minutes, meeting feedback, pending financial report, three-part financial report package, or upload financial data are mentioned. Use hike-lightyear to search investment projects; use hike-knowledge for investment MEMO/investment decision MEMO standards.
Make every reply use natural Taiwan Traditional Chinese and open with the answer, the completed result, or the genuinely needed next step. Use this skill when replying to any user message, including programming, debugging, explanations, planning, research, and everyday conversation. When the question already provides the cause, answer only that cause and the direct fix, without adding diagnostic checklists or unverified assumptions. Keep code, commands, paths, API names, error messages, and technical terms with no natural translation; remove vague openings, Chinglish, mainland Chinese terms, repeated summaries, polite closings, and instructions that push back onto the user work the agent could do.
A collection of Java development manual conventions, based on the Alibaba Java Development Manual (Songshan edition). Covers 7 dimensions: programming conventions, exception logging, unit testing, security conventions, MySQL databases, engineering structure, and design conventions. Use this skill when users need to: (1) write or review Java code (2) check naming/code conventions (3) handle exceptions and logging (4) write unit tests (5) do secure coding (6) design databases (7) design engineering architecture. Trigger words: Java conventions, Alibaba conventions, code conventions, development manual, programming conventions, exception handling, unit testing, security, MySQL, engineering structure, design patterns.
Create a visual Jira sprint dashboard from Jira project, space, sprint, board, filter, JQL, work item keys, or Jira URL data. Use when the user asks for a Jira sprint dashboard, standup dashboard, sprint review, delivery review, engineering manager dashboard, WIP review, planning view, closeout view, or a visual snapshot of Jira work that is more useful than a flat report. Use the richest dashboard format supported by the current agent, such as Cursor Canvas, an interactive artifact, HTML, or Markdown.
JUnit5 + Mockito testing framework skill. Covers JUnit5 @ExtendWith replacing @RunWith, Mockito @Mock/@InjectMocks rules, test isolation principles (FIRST), when to use and not use @SpringBootTest (@WebMvcTest/@DataJpaTest slice tests), BDDMockito given/willReturn style, ArgumentCaptor parameter capture, verify behavior verification, and @ParameterizedTest parameterized tests. Needed when users write Java unit tests/integration tests or mock external dependencies.
Unified GPU kernel operator generation and optimization skill. Automatically detects the target repository type (FlagGems, vLLM, or general Python/Triton) and dispatches to the appropriate specialized sub-skill. Includes operator generation, MCP-based iterative optimization, and feedback submission sub-skills. Use this skill when the user wants to generate or optimize a GPU kernel operator, create a Triton kernel, or says things like "generate an operator", "create a kernel for X", "optimize triton kernel", or "/kernelgen-flagos".
Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, CTA button, hero image, landing page layout, SaaS landing page, product page design, conversion rate, landing page best practices
Make a launch video for your startup or product with Pexo. Describe your product (or paste your landing-page URL or a screenshot) and Pexo writes the script, generates every shot, picks the models, and returns a finished, publish-ready launch video with music — built for Product Hunt, your landing page, or launch-day socials. Use for product and startup launches: "launch video", "product launch video", "make a launch video", "launch day video". NOT for ongoing ad campaigns (use the video-ad skill).
Use when creating, editing, formatting, or extracting LibreOffice Impress (.odp) presentations via UNO, including session-based slide edits, structured targets, lists, tables, charts, media, notes, master pages, patch workflows, and snapshots.
Comprehensive LinkedIn personal branding analysis, profile optimization, and visibility improvement skill using Claude for Chrome browser tools. Use when users request LinkedIn profile analysis, personal branding audit, profile optimization recommendations, LinkedIn visibility improvement, headline optimization, About section review, content strategy guidance, engagement analysis, or Social Selling Index improvement. Works with Claude for Chrome to analyze profile photos, banners, headlines, About sections, experience, skills, recommendations, featured content, activity/posts, and network engagement directly from the user's browser.
Reframe a landscape video into a 9:16 vertical cut for social and mobile - recompose every scene around the action area and turn captions on for sound-off viewing. Use when the user says "make a vertical version", "reframe this for Reels/Shorts/TikTok", "9:16 cut of this video", "make this portrait for LinkedIn", or "turn this into a mobile-friendly cut".
Schedules meetings with internal and external stakeholders by parsing natural language requests, resolving time zones, checking calendar availability, proposing optimal slots, and managing invitations and RSVPs. Use when the user requests meeting scheduler or provides relevant inputs for this workflow.
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.
