Top Agent Skills

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

Scaffold a new mobile page/screen using the StyleSeed layout patterns

Secure-by-default environment variable management for Claude Code sessions.

Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

BlockRun works with Claude Code and Google Antigravity.

Use when creating test scenarios for a skill, setting up a tests/ directory for a plugin or package, running skill tests against a subagent, or verifying whether a SKILL.md changes agent behavior

Use when working with Textual TUI widgets — looking up available components, reactive attributes, constructor parameters, or messages emitted

Use when writing Textual TUI CSS styles or checking valid CSS properties

Use when designing or implementing tests for TypeScript behavior, public types, compiler failures, filesystem or process boundaries, or package-consumer compatibility.

Use when facing multiple implementation tasks that could benefit from parallelization or when deciding between solo, parallel agent, sequential subagent, or agent team approaches

Use when tightening annotations in existing TypeScript, removing avoidable any or assertions, improving changed-file types, or reducing compiler errors without broad refactoring.

Use when configuring or maintaining a TypeScript repository, package manager, tsconfig files, linting, formatting, testing, builds, workspaces, CI, or publishing automation.

Use to find cancellation, downgrade and switching intent in support conversations, and to be honest about how much of your churn support can actually see. Trigger for "which customers are at risk of leaving", "find cancellation intent", "customers asking how to export their data", "top reasons customers asked to close their account", competitor mentions, or building a churn early-warning signal from support data.

Use to get access to Rulebase and connect an AI client to it — signing up, finding your data region, installing the Rulebase MCP server in Claude Code, Claude Desktop or Cursor, and creating an API key for the REST API. Trigger for "connect Claude to Rulebase", "install the Rulebase MCP", "set up the Rulebase connector", "create a Rulebase API key", "how do I sign up for Rulebase", "Rulebase returns 401", "no token provided", or when Rulebase tools are missing from a session.

Use when support or CS is being asked to claim a share of net revenue retention, expansion or churn reduction, to work out what can honestly be attributed and what cannot. Trigger for "how much NRR can support claim", "prove support's revenue impact", "attribute retention to CS", support ROI for a board deck, or two teams claiming the same expansion.

Use to find upgrade, seat-growth and new-use-case signals that customers give support and nobody routes anywhere. Trigger for "find upsell opportunities in support", "customers hitting plan limits", "which accounts are asking about enterprise features", expansion signals from tickets, or support-sourced pipeline.

Use to design and audit how customers are told they are interacting with AI, or that AI was involved in a decision about them, and to evidence that it happened. Trigger for "do we tell customers it's a bot", "AI disclosure requirements", "should the bot say it's not human", "customer asked if they were talking to a person", AI transparency obligations, or evidencing that an AI-assisted decision was explained.

Use to reconstruct what actually happened to one customer across every conversation, channel and handoff, for an escalation, complaint, post-mortem or goodwill decision. Trigger for "build a timeline for this customer", "what happened on this case", "summarize the back-and-forth before I decide", "when were they first told", escalation summaries, complaint investigations, or a case spanning several tickets.

Use to audit canned responses, macros, templates and saved replies for staleness, contradictions, overuse and gaps. Trigger for "audit our macros", "are our canned responses up to date", "which templates do agents actually use", macro sprawl, template cleanup, conflicting saved replies, or before migrating macros to a new helpdesk.

Use to find where support can drive adoption, referral and retention without turning into a sales channel, and to measure whether it worked. Trigger for "can support drive growth", "support-led growth programme", "should agents mention other features", advocacy and referral from support, adoption nudges in support conversations, or a support team being given a revenue target.

Use to push back-office work into Rulebase over the REST API so it can be evaluated like a conversation, with a dry-run plan, idempotent external ids and an audit log. Trigger for "send our back-office work to Rulebase", "push work items", "QA our operations team", "get case work into Rulebase", disputes or KYC queues with no customer on the line, or duplicate work items appearing after a re-run.

Use to audit how payment disputes, chargebacks and unrecognised-transaction claims are handled against scheme deadlines and evidence standards. Trigger for "audit our dispute handling", "chargeback quality review", "are we meeting scheme deadlines", unrecognised transaction claims, provisional credit decisions, or a customer complaining their dispute was rejected unfairly.

Use to measure customer effort from behavioural signals instead of CES surveys, and to audit whether a composite effort score is honest. Trigger for "customer effort score", "behavioural CES", effort without survey, repeat contacts and channel switches, transfers and reopens, or "our CES doesn't match operational data".

Use to design support queues and the skill taxonomy routing rules depend on — not as an org chart mirror, but as staffable combinations of skill, priority and channel. Trigger for "how should we structure our queues", "too many queues", "queue design", "routing taxonomy", "catch-all queue growing", overflow rules, or redesigning queue structure before changing routing rules.

Use to build an account's cumulative support record ahead of a renewal or QBR, so the review reflects the whole relationship rather than the most recent ticket. Trigger for "prepare for this renewal", "what has this account's support experience been", "which accounts are at risk before renewal", QBR preparation, account health review, or an account that renewed badly with no warning.

Use to map where support conversation data actually goes — systems, vendors, countries, AI providers — and compare it against what the privacy notice and records say. Trigger for "where does our support data go", "map our data flows", "which vendors process our conversations", cross-border transfer review, ROPA accuracy for support, or a new tool that was connected without a review.

Use to check that required disclosures, consents and notices were actually given in support conversations — the right wording, at the right point, through a channel the customer could act on. Trigger for "did we give the required disclosure", "are we capturing consent properly", "recording notification audit", "check our mandatory notices", disclosure compliance, or a complaint that a customer was not told something.

Use to find where support routing is failing — misrouted contacts, reassignment chains, unassigned work, and queues nobody owns. Trigger for "why do tickets bounce between teams", "are we routing correctly", "tickets sitting unassigned", "how many tickets get reassigned", ticket ping-pong, or reviewing routing rules and queue design.

Maps support capabilities, plans cross-training, and sizes multi-skilling against real proficiency and routing cost.

Use to design or fix a customer support survey — CSAT, NPS, or CES — and to diagnose response bias. Trigger for "design a CSAT survey", "our CSAT doesn't match reality", "should we use NPS", survey response rate, non-response bias, survey timing or scale choice, comparing satisfaction across teams or channels, or interpreting a satisfaction trend.

Use to analyse a support backlog and find the conversations actually at risk — never-touched tickets, work stalled on your side, customers stranded with a bot, and unassigned open work. Trigger for "report on our open tickets", "daily outstanding tickets report", "how many tickets have we not responded to", "find tickets waiting on us", "customers stuck with a bot and no human", aging backlog, or a backlog that keeps growing.

Use to design support career progression with IC and lead tracks, skill gates instead of tenure alone, and paths that do not treat leaving the phones as the only promotion. Trigger for "career pathing", "progression framework for support", "IC track", "how do agents get promoted", "support ladder", "team lead vs senior agent", or fixing promotion bottlenecks and title inflation.

Use to design or audit the support contribution to a customer health score, so the score predicts something instead of averaging weakly-related signals into a colour. Trigger for "build a customer health score", "add support signal to health scoring", "our health scores don't predict churn", red/amber/green account scoring, or a health score nobody trusts.

Use to extract competitor mentions, switching language and feature-gap evidence from support conversations as an input to win/loss and product strategy. Trigger for "what competitors do customers mention", "why do customers switch away", "find feature gaps customers ask about", competitive intelligence from support, or win/loss analysis that only samples deals sales remembers.

Use when querying a Rulebase workspace with SQL through the MCP server's query tool — writing queries that finish inside the statement timeout, and avoiding the join fan-outs that silently inflate QA evaluation counts. Trigger for "query my Rulebase data", "the query timed out", "statement timeout", "canceling statement due to statement timeout", counts that don't reconcile between two Rulebase queries, criterion counts exceeding team counts, or any multi-step analysis over Rulebase conversations and evaluations.

Use to map support contacts onto the product lifecycle, interpret contact as a lifecycle signal, and avoid journey-map theatre. Trigger for "customer journey map support", "contact by lifecycle stage", onboarding support drivers, churn and support overlap, stage-specific contact reasons, or when journey mapping is worth doing.

Use to measure how long new support agents take to reach proficiency and where their ramp stalls, so training and nesting can be targeted. Trigger for "how long until new hires are productive", "time to proficiency", "how is the new cohort doing", nesting or ramp design, comparing training cohorts, or a new hire being assessed before they have had time to ramp.

Use to design VIP or tiered support programmes and to test whether higher tiers actually deliver better outcomes. Trigger for "VIP support programme", "service tiering", queue priority for premium customers, entitlement vs priority, tier inflation, or "does our enterprise tier get faster support".

Use to check whether a conversation export, dataset or AI pipeline is leaking personal data that should have been redacted, and to measure how well the redaction actually works. Trigger for "is this export safe to share", "check our redaction", "can we use support transcripts for training", sending transcripts to a vendor or model, "is there PII in this dataset", or before opening support data to a wider audience.

Use to sign off a QA period for audit or governance — stating what is being attested to, on what evidence, and with which limitations. Trigger for "sign off the QA period", "attest to our quality results", "monthly QA governance pack", "certify the quality figures", or being asked to confirm quality was assured for a period.

Use to audit whether similar customers with similar failures received similar redress, and to find variation that could not be defended. Trigger for "are our refunds consistent", "do we compensate similar cases the same way", "audit our goodwill decisions", redress fairness review, customers who escalate getting more, or a complaint that someone else was treated better.

Use to design support incentives that improve behaviour without destroying the metric — pairing pay with guardrails, naming gaming modes, and choosing measures that survive Goodhart pressure. Trigger for "incentive plan", "agent bonus scheme", "SPIFF design", "pay for QA score", "what metric should we bonus", CSAT incentives, or reviewing whether a comp change is driving gaming.

Use to find the causes behind a complaint population and track whether remediation actually stopped them recurring. Trigger for "root cause analysis on our complaints", "why do we keep getting the same complaints", "complaint themes and remediation", recurring complaint categories, complaint reduction programmes, or a remediation that was signed off and did not work.

Use to design and measure proactive outbound support that prevents inbound contacts without creating new ones. Trigger for "proactive support", "prevent tickets with outbound", outage notifications, shipment alerts, eligibility and suppression rules, measuring prevented contacts, or proactive messaging opt-out.

Use to surface fraud, scam and financial-crime signals that customers describe to support before detection systems see them, and to check whether agents recognised and routed them. Trigger for "are customers reporting scams", "new scam pattern targeting our customers", "did we spot the fraud signals", authorised push payment scams, "customer was coached by someone on the phone", or fraud reports arriving through support.

Use to turn a one-off support search into a standing monitor or alert that stays useful instead of being muted within a fortnight. Trigger for "alert me when a customer mentions X", "notify the team when complaints spike", "keep watching for this", "set up a daily monitor for", turning an ad-hoc sweep into something recurring, or an existing alert nobody reads any more.

Use to plan and run peak-season support — what to freeze, pre-stage and measure daily so volume spikes do not become quality and attrition crises. Trigger for "peak season readiness", "holiday staffing plan", "Black Friday prep", freeze policy or KB changes before peak, pre-hire and ramp for surge, daily war room metrics, peak post-mortem, or when last year's peak broke SLA and attrition.

Use to audit QA coverage and scorecard health in a Rulebase workspace via the Rulebase MCP server. Trigger for "audit our QA coverage", "which agents or channels aren't being evaluated", "are our QA scores meaningful", "is our scorecard working", QA blind spots, score distribution or ceiling effects, and checking whether QA scores relate to SLA or complaint outcomes.

Use to compare a support data retention policy against what is actually still stored, and find both over-retention and premature deletion. Trigger for "are we deleting support data on time", "retention audit", "how long do we keep transcripts", "we still have data from 2018", conflicting retention obligations, or preparing for a data protection review.

Use to fulfil a subject access request from support data — finding everything about the person, and deciding what must be redacted before disclosure. Trigger for "handle this SAR", "subject access request", "customer wants all their data", DSAR fulfilment from support systems, "a customer asked for their call recordings", or an employee requesting their own QA records.

Use to analyse why support contacts escalate, how long escalations take, and which escalation paths are broken or missing. Trigger for "why are escalations increasing", "how long do escalations take", "which issues get escalated most", tier 2 volume, back-office handoffs, escalations with no defined path, or designing an escalation process.

Use to distil a CX dashboard into the three numbers a board or exec actually needs — volume/demand health, quality/outcome, and cost/efficiency — with commentary that drives decisions instead of forty tiles nobody acts on. Trigger for "board pack", "exec summary for support", "what should leadership see", "too many metrics on the dashboard", "three KPIs for the board", quarterly business review CX section, or when a leadership deck is mostly charts with no story.

Use to recover a day in real time when volume, handle time or availability diverge from plan — reforecasting decisions, break moves, overtime, callbacks and skill flex without burning tomorrow. Trigger for "intraday management", "real-time reforecast", "we are underwater at 11am", move breaks or lunches, call people back in, flex agents between queues, ride out the spike, or when the WFM plan is wrong before close of business.

Use to export CSAT or satisfaction survey responses from a support platform into one canonical shape. Trigger for "export our CSAT data", "pull satisfaction ratings", "get survey responses out of Zendesk/Freshdesk/Gorgias/HubSpot", joining CSAT to tickets, or when a conversation export left the csat field null.

Use to analyse the help-centre funnel from search through article view to contact, find actionable drop-off, and align KB content to contact drivers. Trigger for "self-service funnel", "contact after viewing an article", "why doesn't the help centre deflect", KB deflection rate, search-to-contact conversion, or article effectiveness.

Use to analyse billing and pricing complaints, separating genuine pricing objections from billing defects and unclear communication. Trigger for "customers complaining about price", "billing complaint analysis", "why do customers dispute their invoice", "is our pricing a problem", unexpected-charge complaints, or a pricing decision that needs evidence from support.

Use to monitor support conversations for conduct risk — pressure, mis-selling, unfair outcomes, obstruction and misleading statements — as distinct from whether the answer matched policy. Trigger for "monitor for mis-selling", "conduct risk in our support conversations", "are agents pressuring customers", "customers being obstructed from cancelling", conduct surveillance, or a conduct finding raised by second line.

Use to identify signals of customer vulnerability in support conversations and audit whether they were recognised and acted on. Trigger for "identify vulnerable customers", "did we spot the vulnerability signals", "customers in financial difficulty", bereavement or health disclosures in support, vulnerable customer handling audits, or designing vulnerability recognition for a support team.

Analyzes chat and call abandonment, queue patience, and what a high FCR may be hiding when abandoned contacts never become tickets.