pulse

Step-by-step workflow for adding a new sub-agent or tool to the Pulse AI system. Use when creating a new ADK agent, tool, or extending the AI pipeline in pulse_ai/.

Cross-cutting workflow for adding a new alert metric spanning DB, backend, cron, frontend, and AI agent. Only invoke explicitly when adding a new metric type.

Step-by-step workflow for adding a new REST API endpoint to pulse-server. Use when creating a new backend endpoint, route, resource, or API in backend/server/.

Step-by-step workflow for adding a new reusable component to pulse-ui. Use when creating a shared component in pulse-ui/src/components/ (not a full screen/page).

Step-by-step workflow for adding a new screen/page to pulse-ui. Use when creating a new UI screen, page, dashboard view, or route in pulse-ui/.

Workflow for ClickHouse schema changes — adding columns, tables, or modifying the OTEL analytics schema. Use when making changes to ClickHouse tables in the otel database.

Workflow for building and deploying Pulse services locally via Docker. Use when building Docker images, starting/stopping services, or managing the local development environment.

Fatal Five — triages large-scale production failures by grounding hypotheses in repository code, ranking the top five failure modes by likelihood (P×I×E) with evidence and disconfirmers. Use when production is degraded at scale, SEV/incident response, post-incident review, outage, spike, or widespread regression; also when the user says Fatal Five or fatal-five.

Integrate @dreamhorizonorg/pulse-web into a host app (vanilla JS, React SPA, React Router, Next.js App/Pages Router). Use when adding Pulse Web RUM/OTEL to a new or existing frontend, wiring PulseProvider, trackEvent, setUserId, verifying integration success, or debugging OTLP export failures.

Workflow for reviewing pull requests via GitHub MCP or GitHub CLI (gh) and team coding standards. Use when reviewing PRs, checking code quality, or providing structured review feedback.

Use this skill when the user wants to draft a new Pulse PRD from a feature brief, idea, or scoping conversation. Walks the user through locating the work in the execution-framework progress matrix, anchoring persona and execution layer, building a hypothesis using glossary metrics, and producing a draft PRD saved to product/prds/. Triggers on phrases like "write a PRD", "draft a PRD for X", "scope feature Y for Pulse", "create PRD for", "let's PRD this".

Use this skill when the user wants to review or validate an existing Pulse PRD against the execution framework, glossary, and folder conventions. Produces a structured findings report covering persona/layer correctness, metric reuse, hypothesis quality, dependency coverage, missing sections, front-matter compliance, and renderer-contract conformance. Triggers on phrases like "review this PRD", "validate this PRD", "audit PRD against framework", "does this PRD comply", "check PRD".

Index skill for the SPEC audit orchestrator — load the agent definition for full persona, Task invocation, and iteration loop. Use when the user @mentions the orchestrator skill or asks for multi-pass SPEC vs implementation sweeps for pulse-web-otel.

Audits pulse-web-otel docs/instrumentations/*/SPEC.md against src for format compliance (including mandatory Mermaid HLD, LD, and edge-case flow diagrams) and spec–code parity with a positive/negative/edge test matrix. Uses audit-index.json for dimension checklist and path mapping. Use when editing pulse-web-otel SPECs or instrumentations, after queue hooks fire, or when the user asks for SPEC vs implementation alignment.

Reads pulse-web-otel instrumentation DESIGN.md (and plan folder) to produce a comprehensive E2E test matrix—positive, negative, edge, gate-off, consent—and grill/revalidate coverage gaps; also audits existing Playwright specs and upgrades assertions to the same bar. Use when adding or reviewing E2E for a Web SDK instrumentation, or when the user asks for exhaustive e2e cases from design docs.

New or resumed instrumentation in pulse-web-otel—research, touchpoints matrix, ADR/PLAN-B, implementation, testing. Uses web-sdk-e2e-matrix for DESIGN→E2E matrix; web-sdk-ship for ship-ready gates; optional pulse-web-sdk staged flow (instrumentation + stage 0–8).

Ship-ready workflow for pulse-web-otel — scope, contract, safe implementation, test ladder, regression checklist, pre-merge diff audit (P0/P1/P2), test-run-log, doc sync. (Legacy folder names: pulse-web-sdk-sanity, web-sdk-merge.)