调试
定位并修复问题，分析错误
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.
debugging-table-access-denied
PostHog
Debugs a TableAccessDeniedError from an error tracking issue, Slack alert, or user report. Use when investigating why HogQL denied a system or warehouse table and whether the occurrence is a real bug or expected behavior. Trigger terms include TableAccessDeniedError, table_access_denied, and "You don't have access to table".
triaging-warehouse-sync-tickets
PostHog
Debug a customer's data warehouse source, schema, or table from a support ticket, using PostHog's own production data. Use when a ticket says a warehouse table is stale, empty, stuck, duplicated, missing rows, or failing to sync, and you need the real state of the sync rather than the customer's description. The customer is on a team your MCP session cannot reach, so every answer comes from execute-sql with a connectionId set to a direct-connect source over PostHog's live production databases, which hold all customers' data. Covers region detection (US vs EU), the Production Postgres connection (externaldatasource / externaldataschema / externaldatajob / datawarehousetable), the Production ClickHouse connection (log_entries, app_metrics2), cross-region access through posthog-connection-call, why the external-data-* product tools silently answer from your own project instead, and how to end with one recommended action plus who can run it. Internal only: every query returns another customer's data.
feature-usage-feed
PostHog
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits $ai_generation and $ai_evaluation events with $session_id linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).
debugging-ci-failures
PostHog
Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?"). Use when the user asks why CI is red, asks for the current CI or master status, or mentions a failing check, GitHub Actions run, Depot runner, workflow, job, shard, merge queue kick, flaky test, lint failure, typecheck failure, snapshot diff, migration check, generated types drift, or skills build failure. Start with the hogli ci:insights digest (cross-run CI history from engineering analytics), then guides read-only inspection, failure classification, smallest local reproduction with hogli, and safe reporting without rerunning CI or posting to GitHub. Running unattended as the "Master-red diagnosis" workflow: see references/master-red-incident.md.
triaging-web-analytics-support
PostHog
Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two numbers don't match", traffic count drop, tracker not loading / undercounting vs a competitor, ad-platform integration error, channel type misclassification), run the matching playbook, and produce reply drafts plus fix PRs where warranted. Use when asked to triage the web analytics support channel, investigate a web analytics Zendesk or conversations ticket, or explain metric discrepancies a customer reported. Internal-only: queries cross-customer support and usage data; never copy customer names or their traffic numbers into public artifacts (PRs, issues, commits).
workflows:compound
brycewang-stanford
Document a recently solved research problem to compound methodological knowledge
workflows:plan
brycewang-stanford
Transform research descriptions into well-structured implementation plans following project conventions
deep-audit
brycewang-stanford
Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies. Then fixes all issues and loops until clean. Use when: after making broad changes, before releases, or when user says "audit", "find inconsistencies", "check everything".
docker-management
NousResearch
Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.
cmux-diagnostics
manaflow-ai
"Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary."
cmux-shared-behavior
manaflow-ai
"Shared behavior and mutation-path rules for cmux. Use when a behavior is exposed through multiple entrypoints such as keyboard shortcuts, command palette, context menu, CLI, settings, debug menu, optimistic UI, or tests that previously missed a bug."
cmux-debugging
manaflow-ai
"Debug logging, Debug menu, runtime pitfalls, typing-latency-sensitive paths, SwiftUI list snapshot boundaries, OS-version repros, and local visual iteration for cmux. Use when adding debug probes, diagnosing UI/runtime issues, touching terminal rendering, tab/sidebar list views, drag/drop UTTypes, or using the Debug menu."
n8n:create-instance-ai-eval
n8n-io
Authors a new Instance AI workflow eval case — written locally as JSON, calibrated against a real build, then pushed to the LangTracer suite CI runs — build cases, behaviour/process cases, credential cases, and seeded (mid-conversation) cases — with intent-driven expectations. Use when adding or changing an Instance AI workflow eval, or debugging why one is flaky.
n8n:reproduce-bug
n8n-io
Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.
debugging-executions
n8n-io
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
linear-bug-triage
langfuse
Use this skill after a bug or regression candidate has measured evidence to document them within linear.
datadog-query-recipes
langfuse
Research Langfuse production telemetry with reusable Datadog queries. Use for tenant or project activity, API usage, queue behavior, spans, logs, metrics, or ad hoc measurements across production regions; pair with debug-issue-with-datadog for root-cause analysis.
debug-issue-with-datadog
langfuse
Establish root cause by combining Datadog telemetry with the Langfuse repo. Use when investigating or triaging a user report, Linear or GitHub issue, incident, or pasted production error.
browser-testing-with-devtools
addyosmani
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
debugging-and-error-recovery
addyosmani
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
systematic-debugging
open-metadata
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
understand-issue
mastra-ai
Collaboratively investigate a GitHub issue or bug — trace history, understand architecture, diagnose root cause