В каталоге 185 367 навыков в 14 категориях.
Structured incident response. Use when user reports an outage, production error, or says 'incident', 'something is down'...
Incident response mode — diagnose a production issue, write a postmortem, add follow-up tasks to TODO.md. Use when user...
Analyze production incidents and generate prioritized triage checklists
Respond to a production outage: assess severity, mitigate first (roll back/flip a flag/scale), investigate safely, commu...
Emergency response workflow for production issues
IR playbook execution, evidence collection, forensic timeline analysis, memory forensics, and post-incident reporting fo...
Use when writing an internal or stakeholder incident update, especially when recovery is not yet confirmed.
This skill empowers Claude to guide you through the security incident response process, ensuring a structured and effect...
Use when a request requires investigating an incident, separating evidence from hypotheses, or choosing the next diagnos...
Sets up incident alerting workflows with smart routing, escalation policies, and noise reduction. Configures alert group...
Use when analysing production logs, investigating incidents, writing postmortems, or reviewing error patterns from struc...
Analyze and resolve production incidents using systematic investigation, root cause analysis, and autonomous remediation
A runbook written in a wiki decays silently: the dashboard is renamed, the
Guides IT incident response from declaration to post-mortem: assigns P1 to P4 severity with a decision sequence, sets up...
Production incident response protocol, blameless post-mortem authoring, root-cause triage, and mitigation runbooks.
Incident Commander Skill
Advance one declared incident through a fixed roster, approval-bound communications planning, and receipt-backed resolut...
Comprehensive incident response framework from detection through resolution and post-incident review. Battle-tested SRE/...
Writes the public status page updates for a Heron Press incident. Use when asked to "post a status update", "write the i...
From incident to fix to prevention
Composite skill — runs the postmortem chain after any production incident (`/hotfix`, rollback, or prod outage acknowled...
Look up 80 coded AI-agent security incidents from 2023 to 2026 (prompt injection, tool poisoning, exfiltration and more)...
Use this skill when managing production incidents, designing on-call rotations, writing runbooks, conducting post-mortem...
Implement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews...
Runs an operational incident from detection to closed action — declaring it and naming a commander, separating the peopl...
<!-- Copyright (c) 2026 defconxt. All rights reserved. -->
Handle production incidents effectively. Use when responding to outages, conducting post-mortems, or improving reliabili...
Use when building runbooks, responding to incidents, handling on-call handoffs, or writing postmortems.
Manage ServiceNow incidents — creation with impact/urgency priority calc, auto-assignment by category, reassignment trac...
Triage a production incident with safe, minimal changes and rollback guidance.
Writes the incident note for an Orchard storefront outage or rollback from the release thread and the deploy log. Use wh...
Incident management platform integration for PagerDuty, Opsgenie, and related tools
Create post-incident timeline and actions.
Close the learning loop after a rescue or incident — reconstruct the timeline from action_log, run root-cause analysis (...
Write a structured incident postmortem or post-incident review. Use when asked to write a postmortem, incident report, P...
Draft an incident postmortem with timeline, RCA, and action items. Use when a senior developer needs a structured post-i...
Write blameless incident postmortems with timeline reconstruction, root cause analysis, action items, and preventive mea...
Manage incident postmortem template operations. Auto-activating skill for Technical Documentation. Triggers on: incident...
Build a blameless, cited postmortem timeline and document skeleton from a saved incident issue export, ordering label ch...
Write a single clear, honest public statement about an incident. Use when asked to draft a public statement, a press sta...
インシデント調査で根本原因を特定するためのなぜなぜ分析ファシリテーションツールです。推測を避け、ユーザーの発言を記録し、リアルタイムでマインドツリーを作成して全体を可視化します。複合要因を分割し、最低1つの根本原因を特定します。
Generates professional incident reports using customizable templates. Supports outage, security, performance, and data-l...
Construction safety incident reporting and analysis. Capture incidents, conduct investigations, track corrective actions...
Guided incident response workflow for security incidents
Manage production incidents with structured response, debugging, and post-mortem documentation
Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive inciden...
Runbook skill for failures: cron error, PA failure, cascade, gateway disconnect, semantic DB stale. Walks: detect → clas...
Production incident response automation. Reads logs, checks recent deploys, identifies root cause, suggests fixes, draft...
Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident...
Step-by-step incident response for OpenClaw security breaches. Guides you through containment, investigation, credential...
Expert incident responder specializing in security and operational incident management. Masters evidence collection, for...
Handle production incidents — triage, mitigate, communicate, and write postmortems.
Use when a security incident has been detected or declared and needs classification, triage, escalation path determinati...
Incident response is a systematic approach to handling security breaches and incidents to minimize damage, reduce recove...
Production incident handling covering triage, evidence gathering, mitigation, communication, and post-mortem practices.
Handle security incidents with IR playbooks and procedures. Implement detection, containment, eradication, and recovery...
I provide the technical expertise to handle production incidents effectively. I focus on rapid diagnosis, swift mitigati...
Runs a security incident from detection to closure — triage, containment, investigation, communication, and the review a...
Incident response procedures — triage, communication, investigation, mitigation, and post-incident review. Use when hand...
Use when detecting, responding to, or recovering from system failures, outages, security breaches, or critical errors. T...
线上问题的现场处置,核心是止血优先于根因定位。当用户报障或描述线上故障时使用:线上出问题了、服务不可用、大面积报错、用户反馈打不开、接口全 500、比赛/大促/活动期间现场崩了、要立刻恢复服务、要写故障复盘或 postmortem、要定严重...
Calm, systematic crisis handling — from detection through post-mortem to prevention
Run a structured response to a suspected web or server compromise. Follows SANS PICERL — Preparation, Identification, Co...
Incident response and analysis via Harness MCP. Correlate incidents with recent deployments, assess blast radius and dow...
Manage and respond to production incidents effectively. Establish on-call rotations, runbooks, and post-mortem processes...
IR playbook execution — evidence collection, timeline analysis, memory forensics, disk forensics, containment strategies...
Handles live production incidents and postmortems. Use when production is down, degraded, or on fire; when coordinating...
Contain an incident, verify recovery and preserve a factual postmortem. Triggers on "incident", "事故响应".
Use when triaging a production alert, writing a postmortem, creating or updating a runbook, classifying incident severit...
5-step incident response playbook. Use when a service is down, degraded, or experiencing errors.
How to work a production incident remediation task. Use when the task title starts with "Incident:" or its description c...
IR playbook — contain/eradicate/recover. Defense-only Security OS skill. Use for ASSESS-ONLY gap/control work.
Guide defensive security incident handling on systems the user owns or is authorized to investigate: triage and scoping,...
Incident triage, cascade prevention, and postmortem methodology. Use when handling production incidents, designing resil...
Use during and after a production incident. Covers triage, mitigation before diagnosis, communication, and blameless pos...
When something breaks in production: triage the severity, gather evidence, identify root cause, deploy a fix or mitigati...
Run a structured incident response. Use when the user says "we have an incident", "production is down", "service is degr...
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured...
Runbooks para respuesta a incidentes. Diagnóstico, mitigación y documentación de incidents en producción.
This skill should be used when the user mentions "postmortem", "incident", "root cause analysis", "blameless", "severity...
Incident response methodology, containment, and investigation.
Coordinates an active production incident by establishing command, reducing blast radius, preserving evidence, communica...
Provides incident response best practices covering severity classification, on-call rotation, war room protocols, runboo...
Incident management, on-call procedures, and runbook execution.
Use when triaging active infrastructure outages, alerts or credential incidents. Otherwise, skip: route telemetry design...
Triage and manage production incidents. Trigger with "we have an incident", "production is down", "something is broken",...
Support a blue-team investigation of a suspected security incident by analyzing logs, alerts, and code the user provides...
Use when defining severity levels and on-call procedures, when creating a runbook for a critical service, when an incide...
Guides teams through IT outages and security incidents, providing structured workflows for detection, containment, eradi...
Use when working with incident response incident response
Production incident response patterns: severity classification (SEV1-4), incident roles, SLO/SLI framework, error budget...
Use this skill when a company has no incident response plan, has one copied from a template that names teams it does not...
Incident Response Planner - Auto-activating skill for Security Advanced.Triggers on: incident response planner, incident...
Incident response playbook design for mid-2026 — NIST 800-61r3, ISO 27035, ATT&CK-driven detection, PICERL phases, AI-cl...
Creates detailed incident response playbooks tailored to your cloud environment and team structure. Covers detection, co...
Run and document production incidents — severity classification, incident commander role, communication cadence, triage...
[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assiste...