Install any skill in seconds. Free to start, no credit card required.
Get Started Free →See what a skill changes, then add it to the agent you already have.
Weekdays, conditional browser lane. Selects from the ticket ledger hardest first, meaning by severity and then by age within severity, and writes each customer a reply into a dated queue file the member reads, edits, and sends by hand. Where the right answer is a refund, a credit, a plan change, or a cancellation, it names the remedy, the exact amount, and the exact screen, and leaves the granting to the member. It sends only where you released the channel, never posts, never resolves a ticket,
Triage one inbound support ticket end to end: classify it, draft a reply, run an escalation check, then send or escalate. Use when the user wants a structured, multi-step process to triage a single support ticket from raw inbound to a sent reply or a clean escalation. Do NOT use for a one-line canned answer or a quick classification that one atomic skill can answer.
Write a clear, fair returns, refunds & exchanges policy for an online store. Use when asked to write a return policy, refund/exchange policy, or store returns page. Produces a customer-friendly policy — window, conditions, process, refund method/timing, exceptions, and shipping — in plain language that reduces support tickets and builds trust. Not legal advice.
Use when a live support ticket needs triage (intent, P1–P4 priority, SLA clock), an on-voice reply, not a raw template, de-escalation of an angry or churn-risk customer, or escalation with a handoff packet. NOT the help-center article it links to (that is `technical-writing`), a win-back program (`retention`), or the auto-answer bot (`chatbot`).
Use when a customer contests a charge and wants it reversed — classify the charge type (proration, renewal, overage, duplicate, authorization-hold) and verify the billing record BEFORE crediting, so a legitimate charge is explained and only a verified duplicate or error is refunded. Do NOT use for deciding refund windows, routing/escalating a ticket, or setting the tone of an upset reply.
Write reusable support macros / canned responses that sound human, not robotic. Use when asked to write a support macro, a canned response, a saved reply, or a template for a common customer ticket. Produces a macro — an empathetic opener, the clear answer/steps, placeholders for personalisation, and a warm close — plus variants (resolved / need-more-info / escalating), tuned to keep it human.
Build an FAQ from the questions people actually ask — mined from tickets, chats, and repeated explanations, answered once and well, organized by the asker's words, and maintained by a capture loop instead of annual archaeology. Use when asked create an FAQ for this product/process/team, I answer the same questions weekly, turn our support threads into docs, or why does nobody find our answers. Produces the mined question list with frequencies, the answers in ask-language, the structure, and the
Build a reusable support macro library from recurring ticket patterns: identify the patterns, draft reply templates with personalization slots, then organize them into a category index. Use when the user wants a structured, multi-step process to turn a sample of recurring tickets into a complete macro library with templates and a lookup index. Do NOT use for a single canned reply or one template that one atomic skill can answer.
Use when replying inside a real-time chat channel — a live chat widget or an ongoing chat session where the customer is present and waiting — so the message uses the chat register (short turns, one question at a time, progressive back-and-forth) instead of a long email-style structured answer. Do NOT use for drafting an email reply, summarizing a chat for a human handoff, or routing a ticket to a queue.
Triage an order or account that tripped a risk check into one of hold, verify, release, or block, then pick the lowest-friction verification step and word any customer message so it never accuses them of fraud. Use when a suspected-fraud order needs a disposition and a customer-facing verification message. Do NOT use for routing a normal support ticket, writing a refund policy, or scoring risk from scratch.
Use when deciding whether and how much discretionary account credit to grant a customer over a complaint — attributes fault (our-fault / goodwill / no-credit), sizes the credit within the account's tier cap, keeps it one-time unless a persistent our-fault issue justifies a capped recurring credit, and words the offer as a goodwill gesture that does not admit liability. Do NOT use for policy-mandated refunds/returns, for pure tone/empathy rewrites, or for routing a ticket.
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches "we would have to see it".
Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
Write a help-center / knowledge-base article that actually resolves the issue and deflects tickets. Use when asked to write a help doc, KB article, FAQ entry, how-to, or support documentation. Produces a findable, skimmable article — task-based title, the answer up front, numbered steps, screenshots-to-add markers, troubleshooting, and related links — written so users self-serve instead of contacting support.
How the Risk Manager writes the desk's risk limits with the user, sizes every proposed trade from live account state and Hyperliquid's real constraints, checks the book, and issues a PASS or REJECT with exact ticket fields. Use for setting up or changing limits, sizing any trade, and answering "how's the book".
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a summary deck for a director, or a required PDF form filled from real device and ticket data.
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Humans own the checkpoints where there is no unique answer or the error cost is severe; agents continuously run everything repeatable and acceptable-by-evidence.
The user wants to share or hand off what was found in a video — "send this analysis to my team", "make a page I can share", "export the findings", "give me something I can attach to the ticket". Use this to render a self-contained offline HTML viewer page with the frames, transcript, and every cached answer with its evidence.