菜单
Use Datadog MCP tools to investigate logs, metrics, traces, and incidents for the Gram project. Activate when the user asks about errors, performance issues, incidents, latency, or wants to search telemetry data.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Rules when working with ClickHouse database in Gram for analytics and telemetry features, including editing the ClickHouse schema (server/clickhouse/schema.sql) and creating or fixing ClickHouse migrations
Rules and best practices when working on the dashboard and elements React frontend codebases
Concepts, external interfaces, and conventions for Gram's audit logging subsystem — the internal Go API for recording actor/action/subject events and the `/rpc/auditlogs.*` management API that exposes them. Activate whenever the task involves recording or exposing audit events (adding or changing audit coverage on a service, introducing a new audited subject or action, writing tests that assert an event was recorded, changing how entries are displayed or filtered).
Concepts, external interfaces, and conventions for Gram's management API — the Goa-designed HTTP-RPC surface under `/rpc/<service>.<method>` that powers the dashboard, CLI, and public SDK. Activate whenever the task involves designing, implementing, or modifying a management endpoint (new service, new method, payload/result changes, OpenAPI/SDK surface changes, CLI changes, wiring a new service into the server).
Concepts, external interfaces, and conventions for Gram's role-based access control (RBAC) subsystem — scopes, grants, principals, system roles, and the `authz.Engine.Require` enforcement path used inside handlers. Activate whenever the task involves authorization (adding or modifying a scope or resource type, declaring a new role or grant, gating a handler, changing scope inheritance, exposing RBAC state through the dashboard).
Use the Playwright MCP browser to capture a demo (screenshots or a GIF recording) of a user-visible frontend change and post it as a PR comment
| name | datadog |
| description | Use Datadog MCP tools to investigate logs, metrics, traces, and incidents for the Gram project. Activate when the user asks about errors, performance issues, incidents, latency, or wants to search telemetry data. |
Always filter by the relevant service(s) when querying Datadog:
| Service | Description |
|---|---|
gram | Dashboard frontend (RUM) |
gram-dashboard | Dashboard backend |
gram-server | Main backend API server |
gram-worker | Temporal worker |
fly | Fly.io — where Gram Functions logs are collected |
Use only the following Datadog MCP tools unless the user explicitly asks for others:
mcp__datadog-mcp__search_datadog_logs — Search and filter log eventsmcp__datadog-mcp__analyze_datadog_logs — Analyze log patterns and aggregate statsmcp__datadog-mcp__get_datadog_metric — Get a specific metric's time-series datamcp__datadog-mcp__get_datadog_metric_context — Get context and metadata for a metricmcp__datadog-mcp__search_datadog_metrics — Search available metrics by namemcp__datadog-mcp__get_datadog_trace — Get a specific trace by IDmcp__datadog-mcp__search_datadog_spans — Search spans (useful for latency investigation)mcp__datadog-mcp__search_datadog_incidents — Search active/recent incidentsmcp__datadog-mcp__get_datadog_incident — Get details for a specific incidentmcp__datadog-mcp__search_datadog_monitors — Find monitors and their current statemcp__datadog-mcp__search_datadog_rum_events — Search Real User Monitoring events (frontend errors, sessions)mcp__datadog-mcp__search_datadog_events — Search Datadog events streammcp__datadog-mcp__search_datadog_services — Discover services in APMmcp__datadog-mcp__search_datadog_service_dependencies — View service dependency mapsearch_datadog_logs, filter by status:error, then follow trace IDs with get_datadog_trace.search_datadog_spans with service:<name> and sort by duration.search_datadog_rum_events for gram.search_datadog_incidents first before deep-diving into logs.