Claude Skills by nodesource

Trigger: detect stack, detect project, update config. Inspects project files to detect tech stack, test runner, linter, type checker, build system and testing capabilities. Updates openspec/config.yaml context and rules with the detected information. Run after init or when project tooling changes.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Enter 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.

Propose 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.

Performs an advanced N|Solid memory leak hunt comparing baseline vs peak heap evidence to isolate retained constructors, closures, and retainer paths. Use when the user reports recurring/staircase memory growth, elusive leaks, retained objects, closures holding references, or a standard heap sample/snapshot analysis was inconclusive. Prefer supplied baseline/peak assets; capture new samples only when needed.

Analyzes an existing N|Solid diagnostic asset by asset ID or local asset path using asset-summary. Use when the user asks to inspect, review, summarize, or interpret an already-captured CPU profile, heap profile, heap sample, or heap snapshot, including assets just produced by ns-generate-asset. Do not use to capture new profiles/snapshots.

Investigates an existing N|Solid event payload and correlates relevant MCP evidence. Use when the user provides or references an event such as process-blocked, new-vulnerability-found, agent-exit, uncaught exception, stack trace, span data. Routes follow-up to CPU, memory, vulnerability, or tracing workflows when needed.

Analyzes N|Solid/OpenTelemetry tracing evidence for request latency, HTTP errors, and service dependencies. Use when the user asks about slow endpoints, API timeouts, distributed traces/spans, N+1 queries, await chains, microservice latency, cascading failures, or trace IDs. Query N|Solid only when no trace data was provided. Do not assume full waterfall details unless supplied.

Analyzes live runtime vulnerabilities loaded by connected N|Solid Node.js processes. Use when the user wants to know which CVEs are actually present in running apps, active exploitable/live vulnerabilities, zero-day exposure, supply-chain risk in production, or production package risk. For static npm-audit-style project dependency scans, use ns-audit-dependencies instead.

Audits a local Node.js project dependency tree with NCM vulnerability data. Use when the user asks for an npm audit-style security review, package CVEs, direct/transitive vulnerability report, dependency risk assessment, or remediation plan before upgrading. For vulnerabilities actually loaded in running N|Solid processes, use ns-analyze-vulnerabilities instead.

Benchmarks one Node.js function and reports throughput/statistics. Use when the user asks to benchmark or time a single function, measure ops/sec, compare input sizes, or answer "how fast is this code?" Use ns-validate-optimization instead when original and optimized versions need an A/B proof.

Diagnoses high CPU or slow execution in a Node.js app using supplied evidence or N|Solid CPU metrics/profiles. Use when the user reports CPU spike, high CPU percent, slow endpoint/function, event loop blocking, flamegraph/profile analysis, hot loop, or asks why an app is slow. Prefer existing asset IDs, summaries, trace data, or local profiles before capturing a new profile.

Downloads a raw N|Solid diagnostic asset (heap snapshot, CPU profile, or heap profile) to local disk by asset ID. Use when the user asks to download, save, export, or pull an asset file locally, or needs the raw file for external tools such as snapshot-parser, Chrome DevTools, or diffing. Do not use for analyzing assets — ns-analyze-asset covers that.

Captures a new N|Solid diagnostic asset for a connected Node.js app. Use when the user explicitly asks to collect, capture, or generate a CPU profile, flamegraph, heap sample, heap snapshot, or heap tracking asset and wants it saved or handed off for analysis. For existing assets, use ns-analyze-asset instead.

Generates a Software Bill of Materials (SBOM) for a connected or registered N|Solid Node.js app. Use when the user asks for SBOM, software bill of materials, compliance evidence, SOC2/vendor review, license inventory, dependency inventory, or transitive package report for a running application.

Diagnoses memory growth, heap spikes, RSS increases, OOMs, and suspected leaks in Node.js apps using supplied heap evidence or N|Solid heap sampling/snapshots. Use when the user reports memory leak, heap growing, high RSS, out-of-memory, heap snapshot/profile analysis, or wants memory root-cause triage.

Plans a Node.js runtime upgrade for a project. Use when the user asks which Node version to use, upgrade/migrate Node.js, address LTS/EOL, update .nvmrc or engines, or move between Node versions. Produces version detection, LTS/EOL rationale, dependency compatibility checks, upgrade steps, and rollback guidance.

Optimizes a specific local Node.js function selected by the user. Use when the user points to code and asks to make it faster, improve throughput, reduce CPU/memory cost, or fix a slow function. Requires workspace source; analyzes blast radius, proposes a behavior-preserving rewrite, and hands off to benchmark validation. Not for live N|Solid diagnostics alone.

Finds and evaluates alternatives to an npm package. Use when the user wants to replace, drop, or swap a dependency, migrate away from a deprecated/abandoned/risky package, or asks "what can I use instead of X?" Compares candidates with NCM data and provides migration/API-diff guidance. Use ns-upgrade-package for staying on the same package.

Switches which NodeSource organization nsolid-plugin is authenticated against. Use when the user is a member of multiple NodeSource orgs and wants to switch orgs, sign in to a different org, or asks why MCP data is showing the wrong organization.

Plans an upgrade for a specific npm package already used by a Node.js project. Use when the user wants to bump/update one dependency, assess semver or breaking changes, resolve peer dependency risk, move to a target version, or get exact package-manager commands. Use ns-replace-package when switching to a different library.

Validates a proposed optimization with controlled A/B benchmarks. Use when original and optimized versions of the same Node.js function need statistical proof, ops/sec comparison, p-value/significance, or a performance regression check. Also fits after ns-optimize-function or diagnostics produce a candidate fix. Use ns-benchmark-run for single-version timing only.