Каталог навыков агентов

Use when support or CS is being asked to claim a share of net revenue retention, expansion or churn reduction, to work o...

Use this skill when the user asks to "set up monitoring", "configure observability", "onboard new service", "create save...

This skill should be used when the user asks to "chat with AI", "ask Olly", "ask the agent", "send message to AI", "cont...

Use to find the activation blockers visible in support contacts from new customers, before they show up in retention num...

Use to measure how long new support agents take to reach proficiency and where their ramp stalls, so training and nestin...

Use to compare BPO sites, vendors or partner teams fairly, adjusting for the work mix each is given before concluding an...

Use to check whether a conversation export, dataset or AI pipeline is leaking personal data that should have been redact...

Use this skill when the user asks "who has access", "audit permissions", "check user roles", "list API keys", "review ac...

Use to analyse billing and pricing complaints, separating genuine pricing objections from billing defects and unclear co...

Use to design and measure proactive outbound support that prevents inbound contacts without creating new ones. Trigger f...

Query Coralogix continuous-profiling data with the `cx profiling` CLI — find which services use the most CPU or memory,...

Use to design or audit a QA dispute and appeal workflow with timeboxes, adjudication standards, and second-level consist...

Use to sign off a QA period for audit or governance — stating what is being attested to, on what evidence, and with whic...

Use to design support queues and the skill taxonomy routing rules depend on — not as an org chart mirror, but as staffab...

Use to compare a support data retention policy against what is actually still stored, and find both over-retention and p...

Use to turn an ad-hoc CX reporting request into a versioned spec that can be re-run each period and actually compared ac...

Use to audit whether similar customers with similar failures received similar redress, and to find variation that could...

Use to design a refund, credit and goodwill framework that agents can apply consistently without escalating everything,...

Use to assemble a pack of support evidence for a regulator, auditor or supervisory request, at the standard of reproduci...

Use to build an account's cumulative support record ahead of a renewal or QBR, so the review reflects the whole relation...

Use to quantify the revenue exposed by unresolved support failures, complaints and escalations without inflating the num...

Use to design a safe pipeline that writes derived attributes back into a helpdesk — risk scores, segments, health flags...

Use to staff and schedule QA reviewers for sustainable throughput without grading quality collapsing — fatigue, drift, a...

Use to find where support routing is failing — misrouted contacts, reassignment chains, unassigned work, and queues nobo...

Use this skill when the user asks to "add RUM", "set up RUM", "install the RUM SDK", "add Coralogix RUM to my app", "cre...

Use to export CSAT or satisfaction survey responses from a support platform into one canonical shape. Trigger for "expor...

This skill should be used when the user asks to "find a dashboard", "search dashboards", "does a dashboard exist for X",...

Use to plan and run peak-season support — what to freeze, pre-stage and measure daily so volume spikes do not become qua...

Use to analyse the help-centre funnel from search through article view to contact, find actionable drop-off, and align K...

Query Coralogix's Service Catalog (APM v2 entities) with the `cx service-catalog` CLI — discover entity types, list know...

Use to design VIP or tiered support programmes and to test whether higher tiers actually deliver better outcomes. Trigge...

Use to map support capabilities, plan cross-training, and size multi-skilling against real proficiency and routing cost...

Manage Coralogix SLO (Service Level Objective) definitions with the `cx slos` CLI — list and inspect SLOs, check whether...

Use to fulfil a subject access request from support data — finding everything about the person, and deciding what must b...

Use to find where support can drive adoption, referral and retention without turning into a sales channel, and to measur...

Use to design the process that gets a revenue signal out of support and to the account owner without turning agents into...

Use to design or fix a customer support survey — CSAT, NPS, or CES — and to diagnose response bias. Trigger for "design...

Use to clean up sprawling helpdesk tags, categories and custom fields so reporting built on them means something. Trigge...

Use to decide how to split a growing support organisation — by product, segment, channel, or complexity — and when pods...

Use this skill for any question involving telemetry data: "investigate an issue", "debug a problem", "find out why somet...

Use to review how an outsourcer, BPO or vendor handles your customer data and meets your conduct obligations, using evid...

Use to assess whether support conversations can be used to train, fine-tune or evaluate a model, and to build a filtered...

Use to define handoff standards for support transfers and to measure whether context survives the handoff — cold vs warm...

Use to keep localised help centre content current when the source language changes, detect stale translations, and preve...

Use to set up or fix quality assurance for voice/phone support, including transcript-based and AI-graded call QA. Trigge...

Use to forecast support contact volume and calculate staffing requirements for voice, chat, or async channels. Trigger f...

Use to identify signals of customer vulnerability in support conversations and audit whether they were recognised and ac...

Use to extract competitor mentions, switching language and feature-gap evidence from support conversations as an input t...

Use to set concurrency and work-in-progress limits for support teams — chat concurrency, personal WIP on async work, and...

Use ast-grep (sg) for AST-aware code search and rewrite across 25 languages. Trigger for structural code matching or det...

MUST USE for coding, PR creation/review/merge, dependent branches, scaffolding, and QA. Classify C0-C5, preserve safety...

MUST USE for module boundary work, circular dependency detection, coupling review, barrel or re-export changes, and vali...

MUST USE for backend, API, server, or database work — API design, architecture, database optimization, security hardenin...

MUST USE for code review and review-readiness — review process, quality thresholds, antipattern detection, review verdic...

MUST USE for data engineering and analysis work — pipelines, ETL/ELT, data quality, SQL optimization, schema evolution,...

Use for debugging and system comprehension. Triggers: debug this, root cause, how does X work, reverse engineer, 왜 안 돼,...

MUST USE for DevOps, infrastructure, or delivery work — container builds, deploy pipelines, stacked-PR CI diagnosis, Kub...

DEPRECATED — renamed to cxc-dev-visualizer. Use $cxc-dev-visualizer for visual documents, diagrams, HTML/SVG explainers...

MUST USE for any frontend, web UI, or visual implementation work — building, styling, or redesigning pages/components, r...

MUST USE for project setup, feature scaffolding, structural audits, or documentation scaffolding — applies feature-based...

MUST USE for security guidance covering XSS, CSRF, SQL injection, JWT, OAuth, secrets, OWASP, auth hardening, supply cha...

MUST USE for testing, QA, regression protection, and release verification — unit, integration, API, contract, Playwright...

MUST USE for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout v...

Create well-composed visual documents, HTML reports, SVG diagrams, charts, interactive explainers and PDF deliverables....

DEPRECATED — merged into cxc-loop. Use $cxc-loop for durable goalplans.

Use for Codexclaw Interview mode: persistent IPABCD I-phase requirements discovery, contradiction hunting, focused user...

MUST USE for Korean prose polishing (윤문) — revising existing Korean text to read like a person wrote it: removing transl...

Use for scoped PABCD completion loops. Bare cxc-loop means HOTL; explicit explanation, interview, plan-only, read-only,...

Codexclaw Luna search lane: cheap parallel public-web discovery via hardcoded gpt-5.6-luna explorer subagents, then hand...

DEPRECATED — merged into cxc-pabcd. Use $cxc-pabcd for phase control.

Use for class-scaled Plan-Audit-Build-Check-Done work. Explicit explanation, interview, plan-only, and read-only limits...

MUST USE after building or changing any user-facing surface (web UI, TUI, CLI, HTTP API, native desktop GUI) before clai...

MUST USE for past-session recall — when a term from prior work is unfamiliar, context feels lost after a compact/restart...

MUST USE for messenger-bridge remote setup and channel onboarding — connecting Telegram or Discord to codexclaw, pairing...

Use RepoMap for codebase overview, structure maps, symbol overview, and architecture map exploration. Triggers: repo map...

MUST USE for external, current, real-time, or public-web lookups — latest releases/versions, news, prices, docs, status,...

DEPRECATED: capability routing now lives in cxc-dev.

MUST USE when working inside or renaming Codex-app managed worktrees — hash-named dirs under ~/.codex/worktrees, detache...

Lead customer experience with journey mapping, voice of customer programs, service design, and experience metrics.

Use to package concise executive updates, decks, and decision logs for enterprise pursuits.

Challenge vision alignment, value, cost, risk and operating ownership at material scope or release decisions.

Creates a Product Requirements Document through interactive brainstorming with parallel codebase and web research. Use w...

Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase explor...

Creates a Technical Specification by translating PRD business requirements into implementation designs through interacti...

Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. U...

Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Us...

Executes provider-agnostic PR review remediation using existing review round files under .compozy/tasks/<name>/reviews-N...

Cyprus non-domicile (non-dom) status for individuals, tax year 2026, under the Special Defence Contribution (SDC) Law 11...

Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files com...

Maintains workflow-scoped task memory for Compozy runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt...

Run read-only exposure checks for security advisories and write a structured local audit report.

Expert UK Cyber Essentials and Cyber Essentials Plus advisor — the NCSC-owned, IASME-delivered baseline certification. C...

Sofortmassnahmen bei aktivem Cyber-Vorfall Ransomware Datenexfiltration oder Insider-Threat. Anwendungsfall Cyberangriff...

Use when legacy prompts or older framework flows reference `cyber-intel` and you need the modern runtime to resolve that...

Build incident response timelines and report packs from event logs. Use for detection-to-recovery reporting, phase track...

Prioritize vulnerability remediation using KEV-style exploitation context plus asset criticality. Use for CVE triage, pa...