grafana

Use when the user wants to performance-test, load-test, or stress-test a public website end-to-end with k6. Produces a hybrid (protocol + browser) test suite, SLO-backed thresholds, a load-generator monitor sidecar, and a Grafana-side investigation playbook…

Write or review k6 documentation across the three k6 repositories - k6-DefinitelyTyped (TypeScript types), k6-docs (user documentation), and k6 (release notes / changelog). Applies k6 doc style conventions, generates TypeScript type definitions, drafts…

Investigates CPU, memory, and contention problems with Grafana Pyroscope profiles via the gcx CLI. Compares affected and baseline workloads, locates changed application stacks, and tests root-cause hypotheses against symptom and change evidence. Use when a…

Author Grafana Cloud Synthetic Monitoring checks, with deep coverage of k6 scripted and browser checks: SM's single-VU/single-iteration execution model, assertions that actually fail probe_success (expect() and fail() vs bare check()), secrets, deterministic…

Diagnoses a Grafana Frontend Observability (RUM) session: whether it is healthy, what went wrong, ranked problems with timestamps and evidence, likely cause, how to fix it. Optional follow-up: zoom in on the top error, impact across sessions, Session Replay,…

Generate, validate, and review k6 test scripts — load, stress, spike, soak, smoke, breakpoint, functional, and protocol. Covers HTTP, WebSocket, gRPC, browser, all executors, thresholds, checks, custom metrics, the k6-testing library, k6 Cloud execution, and…

Maintain and improve existing k6 test scripts. Covers threshold tightening based on trend data, version migration between k6 releases, auto-fixing tests when the underlying service changes, refactoring for cleanliness, and auditing scripts against current…

Generate a working k6 browser test (k6/browser) from a plain-language description of a user journey — no CSS selectors or technical detail needed. Explores the LIVE target site with a throwaway k6/browser session to discover real, verified selectors…

Prototype single-reviewer, concern-aware PR review for explicitly requested trials and evaluations. Use only when the user names review-lite; ordinary PR reviews use /review.

Prototype single-reviewer, concern-aware PR review for explicitly requested trials and evaluations. Use only when the user names review-lite; ordinary PR reviews use /review.

Draft a structured PR description from the current diff using `docs/design/CONCERNS.md` routing. Interviews the author for motivation first, then outputs Summary, What to look at, Why, How to verify, Breaking changes, and Reversibility for human review. Pair…

Routed PR review orchestrator for grafana-pathfinder-app. Use for `/review` or any review of a PR in this repo, instead of grafana-engineering:review, grafana-engineering:pr-review, or code-review.

Set up, review, or retire an A/B experiment in Grafana Pathfinder end to end: MTFF flag, variant validation, enrollment seam, exposure analytics, QA overrides, tests, docs, and a retirement plan. Use for `/create-experiment` or any request to add an…

Principal engineer level architecture design review and critique. Use when the user asks for design review, architecture feedback, design partnership, risk analysis of a design doc, or wants to drive ambiguity out of a plan. Never writes code; operates as a…

Set up, review, or retire an A/B experiment in Grafana Pathfinder end to end: MTFF flag, variant validation, enrollment seam, exposure analytics, QA overrides, tests, docs, and a retirement plan. Use for `/create-experiment` or any request to add an…

Reduce Grafana app plugin bundle size with React.lazy, Suspense, and webpack code splitting. Use when module.js is too large, the plugin loads slowly, or the user asks to code split, lazy load plugin pages, or cut the initial JS payload.

Creates, updates, pulls, pushes, and deletes Synthetic Monitoring checks from YAML via gcx. Use also when the user gives a URL or hostname to monitor. For check health use synth-check-status. For a failing check use synth-investigate-check.

Inspects and manages Grafana Agent Observability resources via gcx: conversations, generations, experiments, evaluators, rules, scores, templates. Use to search or export conversations, debug an LLM conversation, or manage evaluators. For guided production…

Review someone else's gcx pull request, produce a ranked report with a verdict, and optionally post it to GitHub as line-anchored inline comments. Covers what to report, in what order, when to stop, how to rank over-engineering findings, how to judge whether…

Prepare a contribution to the gcx repository: report or fix a bug, update documentation, or propose and implement a code change. Use inside a gcx checkout for contribution routing, planning, implementation and self-review; operating a Grafana instance uses…

Investigates application problems and incidents with Grafana metrics, logs, and traces via gcx: errors, latency, regressions, blast radius, trace comparison with baselines. Accepts alert payloads, dashboard links, and trace IDs. For alert rule semantics use…

(Experimental) Runs an end-to-end observability rollout for an application on Grafana Cloud via gcx: instrumentation, SLOs, alerts, synthetic checks, k6, IRM, dashboards, cost, GitOps. Use to set up monitoring for a service from scratch. For LLM apps use…

Instruments a developer's own LLM app or repairs missing generations and empty Performance charts in Grafana Agent Observability. Applies confirmed changes and verifies generation ingest, traces, and metrics. Excludes coding-agent telemetry plugins. For…

Sets up production evaluation for a deployed AI agent in Agent Observability: online eval rules and guards (redact PII, block tools), based on its code and live traffic. Applies via gcx after confirmation. Not for pre-ship tests (use agento11y-test-starter).

Skill for the Bookmarks area of metrics-drilldown. 14 symbols across 11 files.

Skill for the Components area of metrics-drilldown. 25 symbols across 15 files.

Skill for the AppDataTrail area of metrics-drilldown. 28 symbols across 17 files.

Skill for the App area of metrics-drilldown. 24 symbols across 16 files.

Skill for the Breakdown area of metrics-drilldown. 15 symbols across 9 files.

Skill for the Extensions area of metrics-drilldown. 17 symbols across 8 files.

Skill for the Fetchers area of metrics-drilldown. 11 symbols across 3 files.

Skill for the Labels area of metrics-drilldown. 12 symbols across 4 files.

Audit grafana/tempo CI for flaky jobs and slow jobs using gh and action logs and data, then fix what the evidence supports (flaky test, matrix split) and flag what it doesn't (runner capacity, alreay fixed issues, etc).

Review Grafana Tempo pull requests for correctness, data integrity, performance, API and config design, and testing. Use for Copilot code reviews and re-reviews, reporting actionable findings without approval or merge recommendations.

Review documentation changes for style, accuracy, and completeness. Use when docs have been written or updated and need a quality check before submission, when the user asks to review docs, proofread, check style compliance, or verify technical accuracy of…

Assess documentation status for PRs — classify gaps, identify existing docs that need updating, and flag UI changes that may affect screenshots. Use when the user asks to check docs coverage for PRs, triage documentation needs, audit PRs for missing docs,…

Write or update product documentation for user-facing PR changes. Use when the user asks to write docs for a PR, document a PR, update existing docs based on a code change, process PRs flagged by docs-pr-check, or provides PR numbers or links and wants the…

Reformat prose using Semantic Line Breaks (SemBr) from https://sembr.org while preserving rendered output and meaning. Use when asked to reflow plain text or compatible markup (Markdown, AsciiDoc, reStructuredText, LaTeX, Org, MediaWiki) into semantic…

End-to-end workflow for PR documentation — check, write, review, and optionally validate screenshots. Use when the user wants to document one or more PRs from start to finish, run the full docs pipeline, or asks for a complete documentation pass on PRs.

Use this skill to assess whether documentation content fits its intended audience. Identifies the target persona (Learner, Practitioner, Expert, Operator), use case, and entry state, then flags mismatches between the content and what that audience needs. Use…

Review an ai-sdk diff, feature, bug or package against its upstream parity contract. Find behavioral mismatches, unsupported assumptions, scope drift and gaps in regression evidence.

Upgrade the pinned upstream AI SDK reference, assess the current Go implementation against it, and register parity work for independent implementation afterward.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".

Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".

Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in a project that uses OpenSpec. Use when the user wants to think through something before or during an OpenSpec change. Also use when…

Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation. Also use when the user says…

Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. Also use when the user says "openspec sync" or "opsx sync".

Verify implementation matches OpenSpec change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. Also use when the user says "openspec verify" or "opsx verify".

Maintain and improve existing k6 test scripts. Covers threshold tightening based on trend data, version migration between k6 releases, auto-fixing tests when the underlying service changes, refactoring for cleanliness, and auditing scripts against current…

Look up official k6 documentation with `k6 x docs` when writing, debugging, or configuring a k6 test, or reaching for any k6 API, option, executor, or CLI flag. k6 syntax changes between versions, so consult it instead of recalling k6 from memory or searching…

Use when the user wants to performance-test, load-test, or stress-test a public website end-to-end with k6. Produces a hybrid (protocol + browser) test suite, SLO-backed thresholds, a load-generator monitor sidecar, and a Grafana-side investigation playbook…

Use this skill when the user wants to write a k6 browser test that interacts with a web page using a real browser (Chromium). Covers navigation, clicks, form fills, assertions, and web-vitals thresholds via the k6/browser module. Trigger on "browser test",…

Use this skill when the user says "write a k6 script", "generate a k6 load test", or "create performance tests with k6." Handles load, performance, stress, soak, and spike tests for APIs, services, and applications, leveraging k6 MCP tools for script…

Use this skill when a user provides a Playwright script and needs a faithful conversion into a production-ready k6/browser test while following Grafana's migration guidance and MCP workflows.

Use this skill when the user wants a quick k6 smoke test to verify basic functionality under minimal load. Smoke tests run 1–5 VUs for a short duration and assert that endpoints respond correctly. Trigger on "smoke test", "sanity check", or "quick health…

Use this skill to plan k6 test suites from natural-language requirements. It analyses the system under test, identifies the right test types (load, stress, soak, spike, smoke, browser), and produces a structured test plan that other k6 skills can execute.…

Generate interactive guide content.json files from Grafana dashboard JSON. Analyzes dashboard panels, variables, rows, and data sources to produce a Pathfinder guide that tours or explains a dashboard. Use when the user provides dashboard JSON (file, pasted,…

Generate interactive guide content.json files from source code. Analyzes React/TypeScript UI components to extract structure, selectors, field metadata, and conditional logic, then produces a Pathfinder guide JSON. Use when the user provides GitHub links to…

Migrate a standalone guide or learning path to the Pathfinder package format by generating manifest.json (and path-level content.json for LJs). Reads content.json, index.json, recommender rules, and optionally website markdown to derive all manifest fields.…

Guide a human reviewer through a learning path PR in interactive-tutorials — five phases from checkout through Block Editor smoke testing and GitHub submit. AI assists; the reviewer tests and approves comments. Use when the user runs /review-learning-path-pr.

Guide a learning path author through pre-PR self-review in interactive-tutorials. Mirrors /review-learning-path-pr (shared static checklists, shared claim-check, Playwright DOM, readiness) from the author side, then optional package fixes and optional…

Comprehensive read-only audit of an existing Pathfinder guide. Combines structural (lint), semantic (check + best-practices decision trees + the 21 critical rules), and adversarial (attack) analysis into one phased workflow that produces a single prioritised…

Modify an existing Pathfinder guide based on a change request. Plans the edit, applies it surgically, runs a review pass against critical rules, and validates with the Pathfinder CLI. Preserves all blocks outside the planned change. Use when the user wants to…

Set up Grafana Agent observability for a coding agent (Claude Code, Codex, Copilot CLI, Cursor, OpenCode, pi, Vibe, or experimental Kiro CLI) with the agento11y binary: install it, save credentials, wire the agent, verify a session reaches Grafana Cloud, and…

Optional credential-free Hermes integration checks using an explicit loopback model provider and local telemetry receivers. Inspect the scripts before running them; their defaults are not safe evidence of a local-only run.

Help choose, configure, and test local agento11y guard packs for coding-agent tool calls. Use when the user asks to enable safety packs, protect .env files, block dangerous commands, redact tool arguments, create custom local rules, or diagnose local guards.…

Run any Python LLM agent as an Agent Observability experiment using the public agento11y.experiments package: define a test suite, run an existing agent through typed trials, bind or record generation I/O, grade outputs, and publish scores, including from…

Draft a commit message when the user describes a code change and asks for a commit message. Not for general questions or explanations.

Use early in an AI-agent project — before ship, before real traffic — to decide which evaluations to set up and to scaffold a starter experiment. Reads the agent's own code (system prompt, tools, task), recommends specific evaluators with reasons that cite…

Add reliable @grafana/e2e-selectors to interactive elements and key containers in the Grafana frontend. Use when adding e2e selectors, data-testid attributes, or test selectors to React components, when a file or component lacks selectors for testing, or when…

Write and run unit and E2E tests for Grafana frontend code (React/TypeScript, any package or feature area) to the conventions this repo expects. Use when running Playwright E2E tests; when adding, backfilling, or reviewing frontend tests; when a test only…

Write unit and E2E tests for Grafana visualization panels and viz utilities to the conventions this repo expects. Use when adding, backfilling, or reviewing tests for panels (barchart, timeseries, table, xychart, heatmap, canvas, etc.), grafana-ui viz…

Expert at writing migrations and additions for the create-plugin codemod system in packages/create-plugin/src/codemods/. Use this skill whenever the user wants to create, modify, or debug a codemod, migration, or addition in the plugin-tools repo — including…

Diagnose a failing nightly E2E run by identifying which grafana/grafana commit likely introduced an incompatibility with @grafana/plugin-e2e. Use whenever the user wants to triage a playwright-nightly failure, asks "what broke the nightly", "which grafana…

Use when bumping the @grafana/plugin-e2e version in the create-plugin template. Fetches the latest npm version, updates _package.json, commits, and opens a draft PR.

Connect to and use the Grafana Cloud MCP server effectively, including natural-language Grafana Assistant questions and observability investigations. Covers setup, OAuth authorization, tool categories, read/write access scopes, and best practices for context…

Use the grafana-assistant CLI to interact with Grafana Assistant via A2A API. Covers installation, configuration, prompting, keeping conversation context, and practical patterns for ops investigations. Use when the user mentions grafana-assistant, Grafana…

Install, configure, and use the Grafana MCP server effectively. Covers setup via Docker or binary, environment variables, tool categories, RBAC, and best practices for context window management. Use when the user wants to set up mcp-grafana, configure Grafana…