监控
日志、指标与可观测性
analyzing-experiment-precompute-canary
PostHog
Analyze the experiment precompute result-consistency canary across prod-US and prod-EU, deep-dive any issues, and produce an actionable report. Sweeps the canary's Prometheus health gauges in both regions, and when anything is unhealthy pulls the structured divergence/failure logs from Loki to reconstruct exactly which (team, experiment, metric) went wrong, by how much, and which class of divergence it is (stability vs correctness, and for correctness whether exposure counts or only values differ). Mechanism-level root cause needs ClickHouse and is out of scope — the skill hands off with precise drill-down steps. Use when the user asks to check / analyze / verify the experiment precompute canary, investigate a canary divergence or alert, or confirm precomputed experiment results are consistent in production. All data comes through the Grafana MCP (Prometheus + Loki) — no payload decryption, no ClickHouse.
log-error-digest
zebbern
"Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats."
agent-improve
langwatch
Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that capture production signals, and experiments that settle open questions. Use when you want to know what to do next to improve your agent.
add-tracing
metabase
Add OpenTelemetry tracing spans to Clojure code following Metabase tracing conventions. Use when instrumenting backend code with trace coverage.
cpu-profile
ClickHouse
Profile a ClickHouse query using the sampling query profiler and system.trace_log. Use when the user wants to find CPU hotspots, analyze where time is spent in a query, or investigate performance bottlenecks.
instrumenting-first-party-metrics
PostHog
"How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same way customers do. Use when adding application metrics in this monorepo (web, Celery, Temporal), when asked to push or ship metrics into posthog metrics, or when unsure whether the SDK in this environment supports posthog.metrics yet. Covers the environment decision (SDK-first per the public docs, OTel fallback when the SDK path is not available), the exact version gates per SDK, what is already wired internally, and how to validate metrics actually arrive."
debugging-local-task-agent-runs
PostHog
'Debug the output of local PostHog task runs — the wizard cloud-run path that executes inside a Docker sandbox under the local Temporal process-task workflow (the wizard that integrates PostHog, then the coding agent that commits and opens the PR). Use when a local run looks stuck, failed, or silent, or when you need to read the wizard or agent logs. Covers the .env.local keys + ai_features intent required for cloud runs locally, finding the task UUID (docker ps, temporal CLI, Temporal UI at localhost:8081), tailing live logs inside the sandbox container (/tmp/posthog-wizard.log, /tmp/agent-server.log), and reading the durable per-run console log from object storage after the sandbox is torn down. Trigger terms: task-sandbox, run_wizard, agent-server, process-task, SANDBOX_PROVIDER, LLM_GATEWAY, cloud_run, posthog-wizard.log.'
exploring-ai-failures
PostHog
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
analyzing-experiment-query-performance
PostHog
Pull and interpret production experiment query-performance data from the staff-only /api/debug_ch_queries endpoints backing the /experiments/staff scene: slowest experiment queries, precompute read/build health, and preaggregation cache footprint. Covers prod-US and prod-EU via a query_performance:read personal API key, all query params, and response field semantics (exception codes, exposure paths, precompute skip reasons, job states). Use when investigating slow or failing experiment queries, precompute regressions, 307/159/241 errors, preaggregation table growth, or when asked how experiment query performance or the precompute rollout is doing in production.
monitoring-capture-service
PostHog
Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka backpressure, Redis issues, rate limiting, Envoy proxy issues, or any capture health question. Covers prod-us and prod-eu environments.
understanding-billing-usage
PostHog
Explains PostHog billing usage and spend from the customer's visible Billing MCP tools. Use when the user asks why usage or spend is high, which product or project is driving usage, what a usage type means, how to reduce usage, what changed over time, why they got a usage change alert, or whether a spike/drop alert was real or noisy. Also use before product-specific analytics skills when the user names a billable PostHog product metric such as events, recordings, feature flag requests, exceptions, survey responses, synced rows, logs, AI events, AI credits, or Inbox credits. Starts from Billing usage/spend tools, then routes to customer-visible product MCP surfaces for deeper investigation.
hogli
PostHog
PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to run/build/test/lint, or any dev environment commands.
perf-report
ClickHouse
Analyze CI performance comparison reports for a ClickHouse PR. Lists all regressions and improvements, cross-references with master history to distinguish real changes from flaky tests.
1k-sentry
OneKeyHQ
Configure OneKey Sentry and filter events across desktop, mobile, web, and extension.
1k-startup-profile
OneKeyHQ
"Deep startup profiling for OneKey mobile — per-module JS factory timings, HBC I/O/parse breakdown, per-segment timings. Gated behind the single env var ONEKEY_STARTUP_PROFILE=1. Zero overhead when disabled (default). Use when diagnosing cold-start regressions, sizing main.bundle parse cost, finding slow modules, measuring segment load, or auditing what a 1.7s require('./App') actually contains. Triggers on: startup profile, 启动性能分析, module timing, HBC parse time, segment timing, require cost, StartupProfile, ONEKEY_STARTUP_PROFILE, __d patcher, inline-requires."
sentry
openai
"Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require SENTRY_AUTH_TOKEN."
backend-conventions
getsentry
Sentry backend conventions for logging, tracing/spans, metrics tags, and the options system. Use when adding or editing Python in src/ that logs (logger.info/exception), records metrics (metrics.incr/timing with tags), instruments spans/transactions, or reads registered options with options.get(). Trigger on "add logging", "log an error", "add a metric", "add a span", "instrument tracing", "read an option", "LOG005", "LOG011", or metrics tag cardinality questions.
sentry-backend-bugs
getsentry
'Review Sentry Python and Django changes for bug patterns drawn from real production issues. Use when reviewing a backend diff or PR, checking Warden findings, auditing the current branch, reviewing production-error patterns, or looking for common regressions in src/ and tests/.'
evals-write-spec
elastic
Write LLM evaluation spec files with datasets, tasks, and evaluators using the @kbn/evals Playwright fixture. Use when authoring new eval specs, adding datasets or evaluators, or debugging evaluation test failures.
x-lsof
x-cmd
Enhanced lsof (List Open Files) with interactive UI and structured output. View open files, network connections, and processes. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
aws-collector-tool
xuiltul
AWS infrastructure collector. Fetches ECS status, CloudWatch logs, and metrics. Use when: checking ECS health, inspecting CloudWatch error logs, pulling infra metrics, or monitoring AWS resources.
appinsights-instrumentation
microsoft
Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. USE FOR: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices. DO NOT USE FOR: adding App Insights to my app (use azure-prepare), add telemetry to my project (use azure-prepare), add monitoring (use azure-prepare). This skill provides guidance—azure-prepare orchestrates component changes.
azure-compliance
microsoft
Comprehensive Azure compliance and security auditing capabilities including best practices assessment, Key Vault expiration monitoring, and resource configuration validation. USE FOR: compliance scan, security audit, azqr, Azure best practices, Key Vault expiration check, compliance assessment, resource review, configuration validation, expired certificates, expiring secrets, orphaned resources, policy compliance, security posture evaluation. DO NOT USE FOR: deploying resources (use azure-deploy), cost analysis alone (use azure-cost-optimization), active security hardening (use azure-security-hardening), general Azure Advisor queries (use azure-observability).
azure-observability
microsoft
Azure Observability Services including Azure Monitor, Application Insights, Log Analytics, Alerts, and Workbooks. Provides metrics, APM, distributed tracing, KQL queries, and interactive reports.