5.3K skills · sorted by relevance
Automate supported Appointo tasks through Rube MCP and Composio. The skill finds available tools, checks the service connection, and follows current input requirements to execute requested operations, including batches of supported tasks.
Automate supported Appointo tasks through Rube MCP and Composio. The skill finds available tools, checks the service connection, and follows current input requirements to execute requested operations, including batches of supported tasks.
Configuring Salesforce opportunity management: sales stages, sales processes, opportunity record types, Path configuration, opportunity teams, opportunity splits, and forecasting categories. Use when setting up or restructuring the opportunity lifecycle for Sales Cloud. NOT for forecast types, rollup methods, quotas or manager adjustments — use admin/collaborative-forecasts. NOT for agreeing what the stages and exit criteria should be before any build — use admin/sales-process-mapping. NOT for CPQ pricing or product configuration. Keywords: BusinessProcess, sales process, OpportunityStage, ForecastCategoryName, PathAssistant, OpportunitySplit, OpportunitySplitType, OpportunityTeamMember, Opportunity.settings, enableOpportunityTeam, IsClosed, IsWon, IsPrivate.
The English summary is being prepared. Showing the original description.
Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.
Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.
Set up reinforcement learning, which trains models using rewards, with verl. Follow workflows for preparing data, configuring GRPO or PPO training, scaling across GPUs, and addressing memory errors or unstable training.
Guides LLM training with verl using rewards to improve model responses. Covers data preparation, reward functions, GRPO and PPO configuration, distributed GPU training, and troubleshooting memory shortages or unstable training.
Personal App-in-Skill customer-support desk (help desk) that triages incoming support tickets from email, WhatsApp, web chat, contact forms, and WeChat, drafts KB-grounded replies, and proposes actions, then holds every send behind a human approval queue with a pre-send quality gate (support-qa) that outputs SHIP/FIX/BLOCK, plus SLA and CSAT tracking. Use when the user invokes $kelly-support or /kelly-support, mentions 客服 / 工单 / 支持台, a support desk, help desk, customer service, support tickets, ticket triage, a knowledge base or canned macros, SLA / first-response time, CSAT, escalations, or refund requests, wants incoming tickets triaged into a needs_review → approved → done pipeline, agent-drafted replies grounded in a knowledge base and reviewed before sending, refunds and commitments gated behind human approval, or breaching-SLA tickets surfaced. This is the OPERATOR desk (agent + human), distinct from a visitor-facing chat bubble.
The English summary is being prepared. Showing the original description.
Organize customer support emails, turn requests into tasks, and record ticket updates in a tracking spreadsheet. Escalate urgent issues through Google Chat and schedule follow-up calls with customers in Google Calendar.
Manage KubeSphere’s network extension, from installation and upgrades to Calico IP address pools and traffic restrictions. Inspect live cluster resources and bundled references to configure namespace bindings, plan pool migrations, and verify changes.
Helps implement shared browser support with Zoom Cobrowse SDK. Covers customer and support agent integration, PIN connections, drawing tools, sensitive field masking, and consent-based page scrolling, with references for authentication and connection troubleshooting.
Identify evidence-backed opportunities to sell more to existing customers. Compare purchases with unmet needs across products, teams, regions, and contract levels, then rank potential deals and outline whom to approach and how.
Build an Opportunity Solution Tree, a structured map linking one measurable product outcome to customer needs, possible solutions, and experiments. Use research findings to prioritize problems and define hypotheses, metrics, and success thresholds for testing ideas.
Write support playbook -- response templates, issue-type runbooks, tone guide, and common resolution paths. Use when asked to "write support templates", "build a support playbook", "train our support agents", or "standardize our support responses".
The English summary is being prepared. Showing the original description.
Support operations reconnaissance -- audit current ticket volume, SLA compliance, knowledge base coverage, escalation paths, and CSAT to understand where support is the constraint. Use when asked to "audit our support", "why is our response time bad", "how healthy is our support operation", or "before designing a support system".
The English summary is being prepared. Showing the original description.
Design support metrics dashboard -- CSAT, FRT, TTR, ticket deflection rate, volume trends, and agent efficiency. Use when asked to "what metrics should support track", "build our support dashboard", "measure support quality", or "audit our support performance".
The English summary is being prepared. Showing the original description.
Expert support operations guidance for customer service excellence. Use when designing ticket management systems, creating SLA policies, building support tier structures (L1/L2/L3), optimizing knowledge bases, defining severity levels and escalation procedures, implementing support metrics (CSAT, FRT, TTR, FCR), configuring support tool stacks, or building support-to-CS feedback loops. Covers Zendesk, Intercom, Freshdesk, and help desk best practices.
The English summary is being prepared. Showing the original description.
Conduct a Marty-Cagan-style opportunity assessment interview and produce a ~2-page Opportunity Brief in Confluence. Covers business objective, customer, problem, success metric, current alternatives, assumptions/risks, and what we don't know yet. Triggers on "opportunity brief", "opportunity assessment", "discovery brief", "who is this for", "why are we building this", "validate this idea", "product discovery", or any request to frame a feature before implementation. One question at a time. Records accepted research gaps as structured Confluence Decision pages with bidirectional links.
The English summary is being prepared. Showing the original description.
Review support requests, rank urgency by impact and timing, and identify the responsible internal team. Record evidence, next actions, and response deadlines, then prepare customer reply drafts and an escalation summary organized by urgency.
Manage customer and sales records in Microsoft Dynamics 365 through Rube MCP. Create contacts, accounts, leads, invoices, and support cases, update opportunities and sales orders, and retrieve or filter lead records.
Review help links, chat controls, phone numbers, and FAQ entry points across related pages. Compare their relative positions and order under matching layout conditions, then identify changes that make support easier to find throughout a task.
Work with HighLevel contacts, sales opportunities, appointments, and messages. Identify the correct sub-account, check available operations and permissions, then read or update records with request previews and approval steps for changes that require them.
Review quarterly updates and financials across portfolio companies to identify practical AI opportunities. Rank them by estimated profit impact, speed, and feasibility, then outline first steps and approaches that other companies can reuse.
Analyze LLM serving traces to identify GPU time usage, opportunities to run operations concurrently, and known patterns for combining operations. Produce three consistent tables from saved traces or live captures on supported servers.