elastic
- 163 skills
- 0 followers
- 210 repo stars
- yesterday last updated
- ▌ Debug Build · elasticDiagnose failing Buildkite builds in the golang-crossbuild pipeline. Fetches recent failures, reads logs, and traces root causes in Dockerfiles and apt sources lists. Use when builds on main (or another branch) start failing.
- ▌ Debug Updatecli · elasticDiagnose failing updatecli GitHub Actions workflows in apm-server (bump-elastic-stack-snapshot, bump-golang, update-beats, update-compose). Fetches failed runs, reads job logs, classifies root causes and checks whether they recur. Use when an updatecli automation workflow fails.
- ▌ Elasticsearch Onboarding · elasticPrimary guided playbook for Elasticsearch search in Kibana Agent Builder: intent → data → mapping → Dev Tools API snippets (SENSE), with one question at a time. Load this skill whenever the user wants to learn Elasticsearch search, get started, begin building, take first steps, onboard, follow a walkthrough or tutorial, go from zero to a working query, or get structured help setting up indices and search — including casual openers like hi, help, getting started, new to Elasticsearch, how do I build search, or I want to try search. Use when they need end-to-end onboarding, not a single narrow API answer. If they only ask what they can build with Elastic (exploration without the full playbook), prefer invoking /use-case-library first; you can still load this skill afterward for the guided build.
- ▌ RAG Chatbot · elasticGuide for building RAG (retrieval-augmented generation) chatbots and Q&A systems with Elasticsearch. Use when a developer wants to build a chatbot, Q&A system, or AI assistant that answers questions from their own data.
- ▌ Keyword Search · elasticGuide for building keyword/full-text search with Elasticsearch. Use when a developer wants text matching, filters, faceted search, autocomplete, or traditional search functionality.
- ▌ Use Case Library · elasticElasticsearch use case library — the full map of what you can build, with industry examples and technologies. Use when a developer asks "what can Elastic do?", "what can I build?", "what use cases does Elasticsearch support?", or needs help choosing what to build.
- ▌ Catalog Ecommerce · elasticGuide for building catalog and e-commerce search with Elasticsearch. Use when a developer wants product search, faceted navigation, autocomplete, "did you mean" suggestions, or shopping-oriented search experiences.
- ▌ Vector Hybrid Search · elasticGuide for building vector search, hybrid search, and using Elasticsearch as a vector database. Covers semantic_text, dense_vector, embedding strategies, hybrid BM25+kNN via RRF, reranking, and production optimization. Use when a developer wants semantic search, hybrid search, kNN, embeddings, or Elasticsearch as a vector store.
- ▌ Elasticsearch Tutorial · elasticTopic-driven, hands-on Elasticsearch tutorial flow that runs in Kibana Dev Console. Use whenever the user says "walk me through", "give me a tutorial for", "teach me", "show me how X works", "tutorial on", or similar topical learning intent — and they are NOT asking you to build their real, specific use case. Topics are open-ended: any Elasticsearch / Kibana search concept the user names (e.g. mappings, analyzers, bool queries, semantic_text, kNN, RRF, aggregations, ingest pipelines, reranking, data streams, ES|QL). Tutorials use sample data on isolated resources, present every step as a SENSE snippet to run in Dev Tools, and end with cleanup plus pointers to docs and the onboarding / pattern skills.
- ▌ Revert Migration 2 · elasticUse when the user wants to "undo the migration", "delete the dashboards I just uploaded", "remove the migrated alert rules", "roll back", "clean up Kibana", or "start over" — removes some or all of the Kibana assets a migration created (uploaded dashboards and/or migrated alerting rules). Operates only on the TARGET (Kibana); it never deletes anything from the source Grafana/Datadog.
- ▌ Install Obs Migrate 2 · elasticUse when obs-migrate is missing, doctor fails, the user asks how to install/set up the CLI, uvx/pip fails, Python is too old, extras are missing, or any other migration skill cannot run because the tool is not Ready — owns getting elastic-observability-migration installed and verified before connect/migrate skills proceed. Not for Grafana/Datadog/Elastic credentials (use connect-to-o11y-source).
- ▌ Scan O11y Environment 2 · elasticUse when the user wants to scan, inventory, list, or take stock of their source environment, asks "what do I have / how many dashboards / what datasources / what panel types", or wants an overview before committing to a migration — produces an inventory of what exists in a connected Grafana or Datadog environment (dashboard/asset counts, panel/widget types, datasource distribution including non-migratable datasources, and folder organization). For a migrate/no-migrate verdict per asset, use assess-migration-readiness instead.
- ▌ Validate Side By Side 2 · elasticUse when the user asks to "validate the migration", "compare side by side", "did my panels translate correctly", "verify the numbers match", or "check parity" — checks whether a migrated Kibana dashboard matches the original Grafana/Datadog source panel-by-panel, numerically where Elasticsearch's native PROMQL oracle applies and structural-only otherwise. Runs read-only queries against the target cluster and writes nothing to the source. For an overall coverage summary use report-migration-coverage; to understand panels that failed use explain-migration-gaps.
- ▌ Connect To O11y Source 2 · elasticUse when the user wants to connect, authenticate, point the tool at, or verify connectivity/credentials to their Grafana or Datadog instance, or asks "can the tool reach my Grafana/Datadog" / "how do I set up access" — connects the obs-migrate tool to a source observability vendor (Grafana or Datadog) and proves it can actually reach it before any migration.
- ▌ Explain Migration Gaps 2 · elasticUse when the user asks "why didn't this panel migrate", "what does not_feasible mean here", "how do I fix the panels that need manual work", "explain the warnings", or "how do I rebuild this in Kibana" — explains WHY panels and widgets did NOT migrate cleanly, in plain language, with step-by-step guidance to rebuild them in Kibana. Read-only; reads migration artifacts already on disk. For an overall coverage summary use report-migration-coverage; to numerically verify the panels that DID migrate use validate-side-by-side.
- ▌ Migrate Selected Assets 2 · elasticUse when the user wants to migrate "these specific dashboards", "only my critical alerts", "just the monitors matching X", "this folder/team's dashboards", or otherwise scope a real migration to a selection — migrates a chosen SUBSET of a user's Grafana/Datadog dashboards and/or alerting rules into Kibana, not just one (that is try-one-source-dashboard) and not everything (that is migrate-all-supported-assets). Routes by the engine's selectors — uniform `--select-folder/-tag/-datasource/-team/-updated-after/-before/-starred` metadata flags, plus Datadog ids/query — and is honest about which dimensions a given source/asset cannot supply.
- ▌ Prepare Target Telemetry 2 · elasticUse when, before or while running an obs-migrate Grafana/Prometheus or Datadog migration, the user needs to prepare the Elastic target so migrated dashboards show data instead of being empty — deciding how to get Prometheus/Datadog telemetry into Elastic, which target layout or --field-profile that produces, when data must exist relative to migrating, and how to verify target fields. For pre-migration target/ingest readiness, not post-upload panel debugging.
- ▌ Try One Source Dashboard 2 · elasticUse when the user wants to "try one of my dashboards", "migrate just one", "do a single dashboard end-to-end", "prove it on one real dashboard first", or wants one real proof-of-value before committing — fully migrates ONE of the user's own Grafana/Datadog dashboards into Kibana end-to-end for a side-by-side comparison before bulk migration. For a count/type inventory use scan-o11y-environment; for a migrate/no-migrate verdict use assess-migration-readiness; for diagnosing a single broken uploaded panel use debug-uploaded-kibana-dashboard.
- ▌ Understand Source Schema 2 · elasticUse when the user asks how their schema/fields/metric names/labels map or translate to Elastic, why migrated panels can't find data, what fields they need, or how to customize/override the field mapping (rule pack / field profile) — explains how a source observability schema (Prometheus metric/label names, Datadog dotted metrics/tags) maps to Kibana/Elastic field names, shows the concrete source-to-target field mapping for the user's own dashboards, and what to change so migrated dashboards find data.
- ▌ Evaluate O11y Permissions 2 · elasticUse when the user asks whether their credentials/API key has the right permissions, roles, or privileges to export from their source or to import dashboards / create alert rules into Kibana, or wants to check access before committing to a migration — verifies the credentials have what an obs-migrate migration needs end-to-end — read/export on the source (Grafana/Datadog) and write on the Elastic/Kibana target.
- ▌ Report Migration Coverage 2 · elasticUse when the user asks for "a migration report", "coverage summary", "how much migrated", "what's left", or "a summary I can send my manager" — produces a shareable migration coverage report (counts, % migrated cleanly, what needs review or is blocked, plus a rough manual-effort estimate) from the artifacts a completed obs-migrate run already wrote. Read-only; reads existing artifacts and does not re-run a migration or touch any cluster. For per-panel "why didn't this migrate / how do I rebuild it" use explain-migration-gaps; to prove panels are numerically correct use validate-side-by-side.
- ▌ Assess Migration Readiness 2 · elasticUse when the user wants a readiness assessment, feasibility verdict, "what will/won't migrate", how much manual effort is required, a go/no-go before committing, or to know how confident they can be in the result — assesses how much of a connected Grafana/Datadog environment will migrate cleanly versus need manual rework, and how trustworthy that assessment is. For a plain count/type inventory (no verdict), use scan-o11y-environment instead.
- ▌ Prepare Production Cutover 2 · elasticUse when the user asks whether an obs-migrate Grafana/Datadog migration is ready for production cutover, wants a final go/no-go, needs a board/customer-ready cutover checklist, or asks what must be validated before switching users from the source observability stack to Kibana.
- ▌ Migrate All Supported Assets 2 · elasticUse when the user has decided to fully switch and wants to "migrate everything", "do the whole environment", "migrate all my dashboards and alerts", or a complete cutover — bulk-migrates EVERY supported dashboard and/or alerting rule from a connected Grafana or Datadog environment into Kibana in one sweep, and reports exactly which assets could not migrate. For a chosen subset use migrate-selected-assets; for a single proof dashboard use try-one-source-dashboard.
- ▌ Remediate Field Mapping Gaps 2 · elasticUse when migrated Kibana panels are empty, show missing/unknown fields, query the wrong index or data view, or the user needs to fix Prometheus label / Datadog tag / metric-name mapping gaps after an obs-migrate run.
- ▌ Debug Uploaded Kibana Dashboard 3 · elasticUse when an operator reports a migrated Kibana panel empty / "No results found" / "Migration Required" / wrong values after obs-migrate upload, or asks why a panel is broken — diagnoses uploaded dashboards with package CLIs (grafana-validate-uploaded, artifacts, /_query) and plain Kibana UI checks. Not for repo test harnesses or translator development.
- ▌ Review And Enable Migrated Alerts 2 · elasticUse when obs-migrate created Kibana alerting rules and the user asks whether they can enable them, verify them, review connectors/actions, audit migrated rules, or safely roll alert rules into production.
- ▌ Openspec New Change · elasticStart a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
- ▌ Debug Uploaded Kibana Dashboard 2 · elasticUse when the user reports a panel rendering empty / "No results found" / "Migration Required" / wrong-shape values after running parity-rig/upload-all.sh or obs-migrate upload, or hands over a Kibana dashboard URL and asks "why is this panel broken" — diagnoses a Kibana dashboard that mig-to-kbn uploaded to the Serverless cluster by driving Chrome via the chrome-devtools MCP server, capturing the per-panel ES|QL the Kibana UI is actually running, the /_query network response, browser console errors, and a screenshot of the failing panel.
- ▌ Test Duplicate 2 · elasticSecond skill with a duplicate name that should be caught by the duplicate name lint validation check.
- ▌ Test My Skill 2 · elastic bundleA test skill with cross-references to other skills for validating reference extraction and detection of external path dependencies.
- ▌ My Skill 2 · elasticThis skill has an invalid name that is not kebab-case and contains spaces and special characters which violates the naming convention.
- ▌
- ▌ Integration Test Review · elastic bundleReview elastic-agent integration test changes (testing/integration/**) for flakiness risks before merge. Use when reviewing a PR, diff, or commit that adds or modifies integration tests, or when asked whether an integration test will be stable in CI.
- ▌ Review Pr · elastic bundleReview a package-spec pull request or branch for completeness and correctness. Use when the user asks to review a PR, check their branch is ready to merge, verify they have not missed required changes, or wants a pre-submission checklist. Accepts a PR number, a branch name, or no argument (current branch vs main).
- ▌ Open Pull Request · elasticDrafts or opens a GitHub pull request body that matches this repository’s .github/PULL_REQUEST_TEMPLATE.md, keeps What/Why concise, and fills Related issues with links to issues, PRs, or other repos. Use when the user asks to open a PR, create a pull request, write PR description, or prepare gh pr create.
- ▌ Package Spec Release · elastic bundlePrepares a package-spec release branch from elastic/main, finalizes spec/changelog.yml, updates compliance CI matrix, reviews Go toolchain (prompts whether to adopt a newer Go minor when stable releases are ahead, otherwise patch-only .go-version), updates AGENTS.md, commits by topic, pushes to the contributor fork, and opens a PR to elastic/main. If git remotes do not clearly identify the user's fork, lists remotes and asks which remote to use. Use when the user asks to release package-spec, prepare a release, or run the release workflow.
- ▌ Alert Triage · elastic bundleTriage Elastic Security alerts — fetch, investigate, classify threats, create cases, and acknowledge. Use when triaging alerts, performing SOC analysis, investigating detections, reviewing security incidents, or when the user mentions ransomware, malware, lateral movement, credential theft, DLL injection, suspicious processes, or any specific threat. Also trigger for "show me alerts", "what's happening on host X", "any critical alerts", or any security operations question.
- ▌ Case Management · elasticCreate, search, update, and manage SOC cases for Elastic Security. ALWAYS use this skill when the user mentions cases, incidents, investigations, or asks to see, show, list, open, create, update, or search cases. Trigger for: "show me my cases", "open cases", "list cases", "any open cases", "create a case", "case for this alert", "show me case 42", "incident tracking", "investigation status", or any case-related question.
- ▌ Generate Sample Data · elasticGenerate sample security events, attack scenarios, and synthetic alerts for Elastic Security. Use when demoing, populating dashboards, testing detection rules, setting up a POC, or when the user asks for test data, demo data, or sample alerts.
- ▌ Attack Discovery Triage · elastic bundleTriage Elastic Security Attack Discovery findings — fetch correlated attack narratives, assess confidence with entity risk and rule frequency signals, and present an interactive triage dashboard for approval, case creation, and acknowledgment. Use when triaging attack discoveries, reviewing correlated attacks, assessing EASE output, or when the user mentions "attack discovery", "AD findings", "triage attacks", "correlated alerts", or asks to process attack discovery results. Also trigger for "what attacks were discovered", "triage my discoveries", or "any attack discoveries".
- ▌ Detection Rule Management · elasticCreate, tune, and manage Elastic Security detection rules. Use for false positive tuning, adding exceptions, creating new detection coverage, finding noisy rules, enabling/disabling rules, or any detection engineering task. Also trigger for "detection rules", "noisy rules", "false positives", "add exception", "create rule", or "tune rule".
- ▌ Observe · elasticThe agent's Elastic-access primitive. Four modes: wait for an ML anomaly to fire, poll an ES|QL metric (live-sample or wait for a threshold), read a single-instance scalar value, or return a full ES|QL table. Use when the user says "tell me when...", "let me know if...", "wait until X drops below Y", "watch for anything unusual", "monitor for the next N minutes", "poll until stable", "what is X right now", "list …", "which … are …", or wants transient (session-scoped) monitoring or ad-hoc querying without creating a persistent Kibana rule. Also trigger for "keep an eye on" and post-remediation validation.
- ▌ Ml Anomalies · elasticQuery Elastic ML anomaly detection results to understand what's behaving unusually, why, and how badly. Use when the user asks "what's anomalous", "is anything unusual happening", "why is X slow/spiking", "show me the weirdness", or mentions memory growth, CPU spikes, restart patterns, unusual latency, unexpected error rates, or drift from typical behavior. Also trigger for "ML anomalies", "anomaly detection", "Elastic ML", "what does ML think", or when the user wants to understand behavior that deviates from baseline. The tool opens an inline explainer view with a severity gauge, plain-English narrative, and per-entity deviation breakdown — so the agent should USE the visualization, not just dump JSON.
- ▌ Manage Alerts · elasticCRUD for Kibana alerting rules — create, list, get, or delete custom-threshold rules. Use when the user says "alert me when", "create a rule for", "page me if", "set up an alert", "show me my rules", "what alerts do I have", "delete that alert", "remove the rule". Backend-agnostic — works on any metric field in any index pattern (metrics-*, logs-*, traces-apm*, custom). For transient session-scoped monitoring use `observe` instead. Requires Kibana with the Alerting feature enabled — the tool is auto-disabled when no Kibana URL is configured.
- ▌ K8S Blast Radius · elasticAssess the impact of a Kubernetes node going offline — which deployments lose all replicas (full outage), which lose partial capacity (degraded), which are unaffected, and whether the cluster has enough spare capacity to reschedule the lost pods. Use when the user asks "what happens if node X goes down", "what's the blast radius of draining this node", "can I safely maintain node Y", "what's running on this node", "if I evict this node what breaks", or is planning node maintenance, a cluster upgrade, or investigating an actual node failure. Requires Kubernetes (kubeletstats metrics) and Elastic APM for downstream service impact — do not trigger for non-K8s deployments.
- ▌ Apm Health Summary · elasticGet a cluster-level rollup of service health from APM telemetry — the "how's my environment right now?" entry point for observability investigations. Use whenever the user asks about HEALTH, STATUS, or general wellbeing of an environment / cluster / namespace ("how's my cluster", "status of the X env", "what's broken", "any issues", "show me the health of …", "give me a status report", "what should I look at", "things feel slow"). This applies regardless of any time qualifier — "show me the health of X over the past hour" still routes here (with lookback="1h"), NOT to observe. observe is for raw-metric queries; this tool is for the rollup. Gracefully degrades: layers in Kubernetes pod data and ML anomaly context when those backends are present, but still returns useful APM-only output if they aren't. Do not use for log-only or metrics-only customers — this tool requires Elastic APM.
- ▌ Apm Service Dependencies · elasticMap the application topology from APM telemetry — which services call which, over what protocols, with what call volume and latency. Use when the user asks "what calls X", "what depends on X", "show me the topology", "what are the upstream/downstream services", "where does this service fit", or is doing root-cause investigation and needs to trace how a problem propagates through the call graph. Also trigger for "service map", "dependency graph", "blast radius of service X", or "who's the dependency of Y". Requires Elastic APM — do not trigger for log-only or metrics-only customers.
- ▌ Pr · elasticCreate a GitHub pull request for the current branch with a focused why/what body and exactly one release-drafter label. Use when the user asks to open a PR, create a pull request, or ship a branch.
- ▌ Lint · elasticAuto-fix all formatting issues in the docs-builder repo — runs dotnet format for C# and npm fmt:write for TypeScript/JS. Use when the user asks to fix formatting, lint the code, or when a pre-commit hook fails due to formatting.
- ▌ Test · elasticRun the relevant tests for what changed — detects whether to run C# unit tests, specific test projects, integration tests, or JS/TS tests based on changed files. Use when the user asks to run tests, verify changes, or check if something is broken.
- ▌ Issue · elasticFile a well-formed bug report or feature request. Use when the user asks to open an issue, report a bug, or request a feature in the docs-builder repo.
- ▌ Commit · elasticStage relevant files and create a well-formed git commit for the docs-builder repo. Use this when the user asks to commit changes, save work, or create a commit.
- ▌ MCP Search · elasticSearch, analyze, and author Elastic documentation using the remote MCP server. Use this when the user asks about Elastic product documentation, features, or APIs; wants to find, read, or verify existing docs pages; is writing or editing documentation; mentions cross-links between repos; asks about documentation structure, coherence, or consistency; wants to generate templates following Elastic content type guidelines; or references elastic.co/docs URLs or Elastic product names.
- ▌ Feature Flag · elasticRegisters a feature flag as additive-only and verifies the flag-off path still matches the previous default. Use whenever adding or extending a feature flag, editing FeatureFlags.cs, changing feature_flags in assembler.yml, gating a code path behind a FEATURE_* environment variable, or enabling a flag in an environment. Do not skip this skill for flag work even if the user does not name it.
- ▌ Style Review · elasticReview changed or staged C# code against the docs-builder coding standards and flag violations. Use when the user asks to review code style, check for standards violations, or audit a diff before committing.
- ▌ Install Obs Migrate · elasticUse when obs-migrate is missing, doctor fails, the user asks how to install/set up the CLI, uvx/pip fails, Python is too old, extras are missing, or any other migration skill cannot run because the tool is not Ready — owns getting elastic-observability-migration installed and verified before connect/migrate skills proceed. Not for Grafana/Datadog/Elastic credentials (use connect-to-o11y-source).
- ▌ Schema Coverage · elastic bundleAnalyzes a Terraform resource schema and compares it to attributes used in the acceptance test suite (configs + assertions). Produces a prioritized report of missing and poor coverage (set-only assertions, single-value coverage, missing unset/empty cases, missing update coverage). Use when the user asks about schema coverage, test coverage gaps, or improving Terraform acceptance tests for a resource.
- ▌ Openspec Explore · elasticEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
- ▌ Openspec Propose · elasticPropose a new 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.
- ▌ Openspec Plus Tdd · elasticMANDATORY skill that activates whenever code is written to implement an OpenSpec change task. Triggers: openspec-plus-apply is active, /opsx-apply is running, the user is implementing tasks from an OpenSpec change, an implementer subagent dispatched by openspec-plus-apply is starting work, or the user invokes phrases like 'TDD for the change', 'implementing change tasks', or 'writing tests for spec scenarios'. Load before any production code is written for an OpenSpec change. Enforces strict RED-GREEN-REFACTOR per test (any test — acceptance, unit, edge case, helper). Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST. Gherkin scenarios in spec.md are the canonical source for acceptance tests (every scenario MUST become at least one test); additional unit, edge-case, and helper tests are encouraged and follow the same per-test cycle.
- ▌ Flaky Test Catcher · elasticDetects broken and flaky acceptance tests from recent CI failures on main and opens structured GitHub issues for automated remediation. Follow this skill strictly when analyzing CI failures.
- ▌ Openspec Plus Spec · elasticMANDATORY skill that activates whenever the OpenSpec specification phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; `openspec instructions spec` or `openspec instructions specs` is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec specification.
- ▌ Pr Monitoring Loop · elastic bundleMonitor GitHub pull requests through a subagent-based loop that watches CI checks, review comments, PR comments, review state, merge conflicts, and branch freshness. Use when a workflow reaches PR monitoring, CI polling, review feedback handling, or asks to keep a PR merge-ready.
- ▌ Openspec Plus Apply · elastic bundleMANDATORY skill that activates whenever the OpenSpec apply phase begins. Triggers: /opsx-apply runs, the openspec-apply-change vanilla skill is referenced or active, `openspec instructions apply` is invoked, or the user asks to implement, apply, execute, or build out an OpenSpec change ('implement the change', 'apply tasks', 'execute change', 'build out the change'). Takes over only vanilla step 6 (implementation loop) and emulates step 7 output (final status).
- ▌ Openspec Plus Tasks · elasticMANDATORY skill that activates whenever the OpenSpec tasks phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; `openspec instructions tasks` is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec tasks.md file.
- ▌ Openspec Sync Specs · elasticSync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
- ▌ Openspec Plus Design · elasticMANDATORY skill that activates whenever the OpenSpec design phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; `openspec instructions design` is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec design document.
- ▌ Openspec Apply Change · elasticImplement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
- ▌ Openspec Plus Proposal · elasticMANDATORY skill that activates whenever the OpenSpec proposal phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; `openspec instructions proposal` is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec proposal.
- ▌ Openspec Verify Change · elasticVerify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
- ▌ New Entity Requirements · elastic bundleGathers initial requirements for a new Terraform resource or data source by examining API clients (go-elasticsearch, generated kbapi), Elastic API docs (Elastic docs MCP server and/or web), then interviewing the user for gaps. Produces an OpenSpec proposal (change with proposal, design, tasks, and delta specs)—not a hand-written spec under openspec/specs/ alone. Use when designing a new entity, drafting requirements from an API, or before implementing a new resource/data source.
- ▌ Openspec Archive Change · elasticArchive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
- ▌ Openspec Continue Change · elasticContinue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
- ▌ Requirements Verification · elastic bundleAnalyzes an OpenSpec requirements spec for internal consistency, implementation compliance, and test opportunities; when a shell is available, run openspec validate first for structural checks. Use when reviewing specs, verifying implementation against requirements, or identifying test gaps.
- ▌ Existing Entity Requirements · elastic bundleExamines an existing Terraform resource or data source implementation and produces an OpenSpec requirements document under openspec/specs/. Use when the user asks to document requirements for a Terraform entity, capture behavior from code, or write a requirements doc for a resource/data source.
- ▌ Openspec Implementation Loop · elasticOrchestrates an end-to-end implementation loop for a single OpenSpec change: select a change, ask commit-only vs PR delivery, triage the change to determine an execution strategy (inline, single-implementor, or per-task) based on change size and complexity, implement tasks using the chosen strategy, run review and validation, feed findings back for fixes, push to origin, then either watch GitHub Actions on the branch (commit mode) or create a PR and delegate PR monitoring to the pr-monitoring-loop skill (PR mode). Use when the user wants to implement an approved OpenSpec proposal/change with iterative review and CI feedback.
- ▌ Workshop Grafana To Elastic · elasticWorkshop skill for metrics adoption on Elastic Observability Serverless (existing customers): bulk-convert Grafana/PromQL metric dashboard JSON into Kibana dashboards and rules via grafana-migrate; pair with Elastic Agent Skills for refinement.
- ▌ Revert Migration · elasticUse when the user wants to "undo the migration", "delete the dashboards I just uploaded", "remove the migrated alert rules", "roll back", "clean up Kibana", or "start over" — removes some or all of the Kibana assets a migration created (uploaded dashboards and/or migrated alerting rules). Operates only on the TARGET (Kibana); it never deletes anything from the source Grafana/Datadog.
- ▌ Workshop Datadog To Elastic Alerts · elasticWorkshop skill for metrics adoption on Elastic Observability Serverless (existing customers): convert Datadog-style monitor JSON into Kibana alerting rule drafts; complements Elastic Agent Skills for alerting APIs.
- ▌ Scan O11y Environment · elasticUse when the user wants to scan, inventory, list, or take stock of their source environment, asks "what do I have / how many dashboards / what datasources / what panel types", or wants an overview before committing to a migration — produces an inventory of what exists in a connected Grafana or Datadog environment (dashboard/asset counts, panel/widget types, datasource distribution including non-migratable datasources, and folder organization). For a migrate/no-migrate verdict per asset, use assess-migration-readiness instead.
- ▌ Validate Side By Side · elasticUse when the user asks to "validate the migration", "compare side by side", "did my panels translate correctly", "verify the numbers match", or "check parity" — checks whether a migrated Kibana dashboard matches the original Grafana/Datadog source panel-by-panel, numerically where Elasticsearch's native PROMQL oracle applies and structural-only otherwise. Runs read-only queries against the target cluster and writes nothing to the source. For an overall coverage summary use report-migration-coverage; to understand panels that failed use explain-migration-gaps.
- ▌ Connect To O11y Source · elasticUse when the user wants to connect, authenticate, point the tool at, or verify connectivity/credentials to their Grafana or Datadog instance, or asks "can the tool reach my Grafana/Datadog" / "how do I set up access" — connects the obs-migrate / mig-to-kbn tool to a source observability vendor (Grafana or Datadog) and proves it can actually reach it before any migration.
- ▌ Explain Migration Gaps · elasticUse when the user asks "why didn't this panel migrate", "what does not_feasible mean here", "how do I fix the panels that need manual work", "explain the warnings", or "how do I rebuild this in Kibana" — explains WHY panels and widgets did NOT migrate cleanly, in plain language, with step-by-step guidance to rebuild them in Kibana. Read-only; reads migration artifacts already on disk. For an overall coverage summary use report-migration-coverage; to numerically verify the panels that DID migrate use validate-side-by-side.
- ▌ Migrate Selected Assets · elasticUse when the user wants to migrate "these specific dashboards", "only my critical alerts", "just the monitors matching X", "this folder/team's dashboards", or otherwise scope a real migration to a selection — migrates a chosen SUBSET of a user's Grafana/Datadog dashboards and/or alerting rules into Kibana, not just one (that is try-one-source-dashboard) and not everything (that is migrate-all-supported-assets). Routes by the engine's selectors — uniform `--select-folder/-tag/-datasource/-team/-updated-after/-before/-starred` metadata flags, plus Datadog ids/query — and is honest about which dimensions a given source/asset cannot supply.
- ▌ Prepare Target Telemetry · elasticUse when, before or while running an obs-migrate Grafana/Prometheus or Datadog migration, the user needs to prepare the Elastic target so migrated dashboards show data instead of being empty — deciding how to get Prometheus/Datadog telemetry into Elastic, which target layout or --field-profile that produces, when data must exist relative to migrating, and how to verify target fields. For pre-migration target/ingest readiness, not post-upload panel debugging.
- ▌ Try One Source Dashboard · elasticUse when the user wants to "try one of my dashboards", "migrate just one", "do a single dashboard end-to-end", "prove it on one real dashboard first", or wants one real proof-of-value before committing — fully migrates ONE of the user's own Grafana/Datadog dashboards into Kibana end-to-end for a side-by-side comparison before bulk migration. For a count/type inventory use scan-o11y-environment; for a migrate/no-migrate verdict use assess-migration-readiness; for diagnosing a single broken uploaded panel use debug-uploaded-kibana-dashboard.
- ▌ Understand Source Schema · elasticUse when the user asks how their schema/fields/metric names/labels map or translate to Elastic, why migrated panels can't find data, what fields they need, or how to customize/override the field mapping (rule pack / field profile) — explains how a source observability schema (Prometheus metric/label names, Datadog dotted metrics/tags) maps to Kibana/Elastic field names, shows the concrete source-to-target field mapping for the user's own dashboards, and what to change so migrated dashboards find data.
- ▌ Workshop Datadog Dashboards To Elastic · elasticWorkshop skill for metrics adoption on Elastic Observability Serverless (existing customers): bulk-convert Datadog-style metric dashboard JSON into Kibana via datadog-migrate; pair with kibana-dashboards Agent Skill and Cursor for query rewriting.
- ▌ Evaluate O11y Permissions · elasticUse when the user asks whether their credentials/API key has the right permissions, roles, or privileges to export from their source or to import dashboards / create alert rules into Kibana, or wants to check access before committing to a migration — verifies the credentials have what an obs-migrate / mig-to-kbn migration needs end-to-end — read/export on the source (Grafana/Datadog) and write on the Elastic/Kibana target.
- ▌ Report Migration Coverage · elasticUse when the user asks for "a migration report", "coverage summary", "how much migrated", "what's left", or "a summary I can send my manager" — produces a shareable migration coverage report (counts, % migrated cleanly, what needs review or is blocked, plus a rough manual-effort estimate) from the artifacts a completed obs-migrate run already wrote. Read-only; reads existing artifacts and does not re-run a migration or touch any cluster. For per-panel "why didn't this migrate / how do I rebuild it" use explain-migration-gaps; to prove panels are numerically correct use validate-side-by-side.
- ▌ Assess Migration Readiness · elasticUse when the user wants a readiness assessment, feasibility verdict, "what will/won't migrate", how much manual effort is required, a go/no-go before committing, or to know how confident they can be in the result — assesses how much of a connected Grafana/Datadog environment will migrate cleanly versus need manual rework, and how trustworthy that assessment is. For a plain count/type inventory (no verdict), use scan-o11y-environment instead.
- ▌ Prepare Production Cutover · elasticUse when the user asks whether an obs-migrate Grafana/Datadog migration is ready for production cutover, wants a final go/no-go, needs a board/customer-ready cutover checklist, or asks what must be validated before switching users from the source observability stack to Kibana.
- ▌ Migrate All Supported Assets · elasticUse when the user has decided to fully switch and wants to "migrate everything", "do the whole environment", "migrate all my dashboards and alerts", or a complete cutover — bulk-migrates EVERY supported dashboard and/or alerting rule from a connected Grafana or Datadog environment into Kibana in one sweep, and reports exactly which assets could not migrate. For a chosen subset use migrate-selected-assets; for a single proof dashboard use try-one-source-dashboard.
- ▌ Remediate Field Mapping Gaps · elasticUse when migrated Kibana panels are empty, show missing/unknown fields, query the wrong index or data view, or the user needs to fix Prometheus label / Datadog tag / metric-name mapping gaps after an obs-migrate run.
- ▌ Debug Uploaded Kibana Dashboard · elasticUse when the user reports a panel rendering empty / "No results found" / "Migration Required" / wrong-shape values after running parity-rig/upload-all.sh or obs-migrate upload, or hands over a Kibana dashboard URL and asks "why is this panel broken" — diagnoses a Kibana dashboard that mig-to-kbn uploaded to the Serverless cluster by driving Chrome via the chrome-devtools MCP server, capturing the per-panel ES|QL the Kibana UI is actually running, the /_query network response, browser console errors, and a screenshot of the failing panel.
- ▌ Review And Enable Migrated Alerts · elasticUse when obs-migrate created Kibana alerting rules and the user asks whether they can enable them, verify them, review connectors/actions, audit migrated rules, or safely roll alert rules into production.
- ▌ Docs Skill Review · elastic bundleReview an Elastic agent skill against official documentation for accuracy, completeness, and coverage gaps. Use when a writer wants to review, audit, or validate a skill from a repository of agent skills.
- ▌ Create Skill · elastic bundleInteractively create a new Claude Code skill and add it to the elastic-docs-skills catalog. Use when the user wants to generate a new skill, scaffold a slash command, or build automation for docs tasks.
- ▌ Docs Lens Chart Page · elastic bundleCreate or update a Lens chart documentation page following Elastic docs conventions. Use when writing a new chart type page (pie, bar, metric, gauge, heat map, etc.) or updating an existing one in explore-analyze/visualize/charts/. Relies on lens-chart-settings for verifying UI labels against source code.