737 skills · sorted by relevance
Deploy decoy files and monitor changes, renames, and deletions for early signs of ransomware. This skill guides Python monitoring, email, Slack, and syslog alerts, plus simulated file operations to verify that the detection and notification pipeline works.
Monitor public Certificate Transparency logs, which record TLS certificates, to spot unexpected issuance and discover subdomains. Use crt.sh data to maintain a certificate inventory, check domain findings against DNS, and configure alerts for suspicious activity.
Define service reliability targets, choose measurements that reflect user experience, and calculate error budgets—the failures a target allows. Generate alert thresholds and review existing definitions for unrealistic targets, unclear metrics, and missing response policies.
Manages security incident cases in Google SecOps, from reviewing queues and related alerts to updating priorities, assignments, and investigation notes. It supports closing cases with documented causes, with available actions depending on the connected MCP tools.
Record and query iii engine logs, traces that show how calls flow, and operational metrics. Set up reactions to incoming errors, inspect alerts, and review metrics aggregated over time windows.
Set up application monitoring with structured logs, performance metrics, and traces that follow requests across services. Build dashboards and alerts, run load tests, investigate CPU and memory bottlenecks, and estimate future infrastructure capacity.
Set up Telegram alerts for a colony, a group of AI agents, so users can respond when work stalls. The skill creates or reuses a bot, stores its token, connects the destination chat, and tests notifications.
Set up Slack alerts for a colony, a group of AI agents, so users can reply when work stalls. The skill prepares the Slack app, stores sending and receiving tokens, connects a channel, and tests notifications.
Build a single-page operations guide for engineers on call, the people assigned to respond to service issues. Organize service dependencies, alert thresholds, dashboard links, copyable commands, duty rotations, and an incident response checklist.
Process SARIF files, a standard format for static analysis results, to filter alerts, remove duplicates, combine findings from multiple tools, and produce reports. It also supports comparing runs and integrating result checks into CI/CD pipelines.
Design notification routing that sends agent messages to channels by topic, such as security, releases, or daily digests. Use shared configuration and message tags to keep important alerts visible among routine updates.
Collect open Dependabot alerts, group them by dependency files, and propose fixes suited to each package manager. After approval, update dependency versions or override settings and verify that patched versions are installed without introducing new audit issues.
Generates a standalone YOLO26 detection and tracking service scaffold for VSS Search and Alerts. Includes DeepStream configuration, Docker files, and tests, with Kafka integration guidance and clear limits on validation before model assets are available.
Read the user's local TradingView desktop app through opencli: quotes, options chains with greeks and per-strike IV, options expiries, screener results across stocks, crypto, forex, futures, and bonds, gainers and losers, news headlines and full stories, alerts (active, fired, offline fires), watchlists including colored flag lists, symbol search, chart state, and chart screenshots. Use this skill whenever the user asks for any of these from TradingView ("TV") — for example an options chain, puts, or IV skew for a ticker, an oversold-stock screen, their red flag list, which alerts fired, or a screenshot of their chart. For plain quotes, TA readouts, scans, or futures without the desktop app, prefer tradingview-mcp. Read-only: it never places trades or edits watchlists, alerts, or layouts.
The English summary is being prepared. Showing the original description.
Design observability strategies: SLI/SLO frameworks, alerting, and dashboards. Use when instrumenting a production service, tuning alert rules, designing Grafana dashboards, defining SLOs and error budgets, or reducing alert fatigue.
The English summary is being prepared. Showing the original description.
Configure competitor alerts: change thresholds per competitor, urgency routing, digests. "set up competitor alerts"
The English summary is being prepared. Showing the original description.
Adjudicates whether a hit generated by sanctions, PEP, or adverse-media screening is a true positive, false positive, or requires human escalation. Use whenever a user presents a screening alert, a name match against a watchlist (OFAC SDN, EU consolidated list, UK OFSI, UN list, PEP list, adverse media hit, etc.), or asks to clear a screening hit / reduce false positives / determine whether a flagged name is actually the listed party. Use even when the user describes the task casually — "is this person actually on the sanctions list", "did we get a real match", "clear this alert", "I have a hit on X" — these are all screening-adjudication tasks. Produces a deterministic determination with full audit trail (structured JSON + human-readable narrative). Designed for use by compliance analysts and screening systems.
The English summary is being prepared. Showing the original description.
Send Telegram messages, files, and alerts via bot API; read replies; ask questions with inline buttons and wait for the answer (approve-from-phone). Supports multiple bots and named chat targets. Use when the user wants to send a Telegram message or alert, get notified on Telegram when a task finishes or needs input, ask for approval via Telegram, or wire Telegram notifications into hooks, cron jobs, or CI. Triggers: 'telegram', 'send me a telegram', 'alert me on telegram', 'ask me on telegram', 'notify me when done'.
The English summary is being prepared. Showing the original description.
AlertOps integration. Manage data, records, and automate workflows. Use when the user wants to interact with AlertOps data.
The English summary is being prepared. Showing the original description.
Alert Logic integration. Manage data, records, and automate workflows. Use when the user wants to interact with Alert Logic data.
The English summary is being prepared. Showing the original description.
Fix "Requested backend named 'X' does not exist" or TLS alert errors in Fastly Compute@Edge. Use when: (1) Backend works locally but fails in production with "backend does not exist", (2) TLS alert received (alert_id=0) errors when calling external APIs from Fastly, (3) Backends defined in fastly.toml aren't available after deployment. The fastly.toml [[backends]] section only applies during initial service creation - existing services require backends to be added via CLI or API with proper SSL/SNI configuration.
The English summary is being prepared. Showing the original description.
Site reliability specialist for Prometheus metrics, distributed tracing, alerting strategies, and SLO designUse when "observability, monitoring, prometheus, grafana, alerting, slo, sli, metrics, tracing, logging, on-call, incident, observability, prometheus, grafana, tracing, jaeger, alerting, slo, sli, metrics, logging, sre, ml-memory" mentioned.
The English summary is being prepared. Showing the original description.
Automatic init the first time Claude acts in an incident or alerts channel — one named like #inc-…, #incident-…, #sev0-…/#sev1-…, or whose recent messages are pages or alerts from PagerDuty, Opsgenie, incident.io, Datadog, Sentry or Grafana, or relayed by people (talk about being paged is not an alert) — that isn't already a team's oncall / monitoring channel. Run once per channel, on first contact (just invited, first @-mention, channel just created), before doing what was asked: load the oncall memory oncall setup wrote to shared workspace memory, pick the owning team's section, work out which monitoring / paging / code tools Claude can reach and which are missing, post one short zero-context message, note findings in this channel's memory, then hand off to `incident-investigate` if something was asked — or immediately, unasked, when the channel was plainly opened for a live outage. Works with no oncall memory (offers setup once). Also on "load the oncall setup here" / "init this incident".
The English summary is being prepared. Showing the original description.
Monitor product availability and get restock alerts for Shopify stores. This skill should be used when checking if a product is in stock, watching for restocks, setting up back-in-stock alerts, or tracking product availability. Supports SMS, Slack, and terminal notifications on status transitions. Keywords: out of stock, sold out, back in stock, restock alert, notify when available, watch product.
The English summary is being prepared. Showing the original description.