Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Apply Strunk's writing rules to prose—documentation, commits, error messages, UI text. Clearer, stronger, more professional. Also handles sharpening and tightening drafts by subtraction.

Expert in graph database design and development with deep knowledge of graph modeling, traversals, query optimization, and relationship patterns. Specializes in SurrealDB but applies generic graph database concepts. Use when designing graph schemas, optimizing graph queries, implementing complex relationships, or building graph-based applications.

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Helps fix security vulnerabilities identified by DryRunSecurity. Activates when the user shares a DryRunSecurity comment (from a GitHub PR or GitLab MR) or asks for help fixing any security finding including SQL injection, XSS, CSRF, SSRF, path traversal, command injection, authentication bypass, authorization flaws, and prompt injection. Researches authoritative sources and applies fixes grounded in the user's specific codebase context.

Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.

Diagnose where new users fail to activate, identify the aha moment, measure time-to-value, and build a sized plan to move activation rate. Use when a PM needs to understand why signups don't convert to active users, find the aha moment, reduce time-to-value, or improve onboarding.

Set up measurement and tracking for product launches, run post-launch retros with data, and build a launch analytics system. Use this skill whenever someone asks to track a launch, set up UTM parameters, measure launch performance, run a launch retro, analyze launch results, or build a dashboard for a product release. Also trigger for "how do we know if the launch worked," "what should we track for this launch," "set up UTMs for the announcement," or any request about measuring or evaluating a product launch. Covers pre-launch tracking setup, UTM conventions, per-tier KPIs, benchmark expectations, and retro frameworks.

Implement Customer.io webhook and reporting event handling. Use when processing email delivery events, click/open tracking, bounce handling, or streaming to a data warehouse. Trigger: "customer.io webhook", "customer.io events", "customer.io delivery status", "customer.io bounces", "customer.io open tracking".

Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.

Configure SAML 2.0 and OIDC SSO for Cursor with Okta, Microsoft Entra ID, and Google Workspace. Triggers on "cursor sso", "cursor saml", "cursor oauth", "enterprise cursor auth", "cursor okta", "cursor entra", "cursor scim".

Configure Cursor privacy mode, data handling, telemetry, and sensitive file exclusion. Triggers on "cursor privacy", "cursor data", "cursor security", "privacy mode", "cursor telemetry", "cursor data retention".

Integrate VS Code extensions with Cursor IDE: compatibility, Open VSX registry, VSIX installation, conflict resolution, and essential extensions. Triggers on "cursor extensions", "cursor vscode extensions", "cursor plugins", "cursor marketplace", "open vsx", "vsix install".

Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync. Use when architecting new Clay integrations, reviewing data flow design, or establishing enrichment pipeline standards. Trigger with phrases like "clay architecture", "clay best practices", "clay pipeline design", "clay reference", "clay data flow".

Execute use when generating infrastructure as code configurations. Trigger with phrases like "create Terraform config", "generate CloudFormation template", "write Pulumi code", or "IaC for AWS/GCP/Azure". Produces production-ready code for Terraform, CloudFormation, Pulumi, ARM templates, and CDK across multiple cloud providers.

Derives a working definition of Agents as a Service specific to a user's business. Starts from user-provided context only (website, docs, description). Identifies the business category, researches agentic solutions (NVIDIA, complementary vendors, open source), proposes three user stories (human, agent, hybrid), then derives a custom AaaS definition. Enforces logic checks, uncertainty mapping, and source quality throughout. Produces MD and JSON output. Use when exploring what AaaS could mean for a specific business, preparing an AaaS strategy, or evaluating agent-based service opportunities. Invoke with /aaas-definition.

Express Spec-Driven Development. Use only when the user explicitly asks for ESDD, references an ESDD command or artifact, or wants to continue an existing ESDD change. Do not use for ordinary coding, debugging, refactoring, or small code changes.

This skill should be used when the user says "shipping", "arness shipping", "ship it", "ship", "create PR", "open pull request", "push and PR", "commit and push", "wrap up", "ship the feature", "ship the fix", "ready to ship", "push changes", "finalize", "finish up", "done", "arn-shipping", or wants to commit, push, and optionally create a pull request. Handles branching, staging, committing, pushing, and PR creation as a single guided flow. Chains from arn-implementing at completion.

This skill should be used when the user says "concept review", "review concept", "update product concept", "synthesize stress tests", "stress test review", "apply stress test findings", "review stress test results", "concept update", "merge stress test recommendations", or wants to synthesize findings from completed stress tests into a reviewed and updated product concept document. Scans for stress test reports, consolidates recommendations, resolves conflicts using product pillars, presents the full changeset for user approval, and produces an updated product-concept.md alongside a concept-review-report.md.