Design reproducible build, image, and deployment pipelines for Kotlin plus Spring applications, including CI verification, layered containers, rollout safety, and deployment-time migration coordination. Use when creating or improving Dockerfiles, CI workflows, image hardening, Kubernetes manifests, release gates, or deployment strategies for Spring Boot services, especially where build reproducibility and operational safety matter.

Scope management for legal matters — baseline capture, in-flight change control, OOS documentation, and scope retrospective. Use when asked to review scoping assumptions, assess whether work is in or out of scope, draft a scope change notice, track scope changes, prepare an OOS justification, run an OOS report, prepare a scope call agenda, or review what changed on a matter. Trigger on: 'scope change', 'out of scope', 'OOS', 'scope creep', 'is this in scope', 'the client wants us to also', 'additional work', 'scope review', 'what changed from the original scope', 'we need to revisit the quote', 'the budget assumed', 'OOS report', 'scope call with the client', 'run a scope report'.

Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. Use when starting a new plugin or adding a plugin to a multi-plugin repository.

Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.

Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.

Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.

Azure Resource Manager SDK for Fabric in .NET. Use for MANAGEMENT PLANE operations: provisioning, scaling, suspending/resuming Microsoft Fabric capacities, checking name availability, and listing SKUs via Azure Resource Manager. Triggers: "Fabric capacity", "create capacity", "suspend capacity", "resume capacity", "Fabric SKU", "provision Fabric", "ARM Fabric", "FabricCapacityResource".

Build distinctive, high-quality frontend interfaces. Use when users request web components, pages, landing pages, portfolios, or creative applications. Generates production-ready code with creative typography, layered color systems, fluid motion choreography, and inventive layouts. Eliminates generic AI aesthetics. Say "Prime" for maximum quality.

Generate Harness Agent Template files for AI-powered automation agents. Produces metadata.json, pipeline.yaml (v1 syntax), and wiki.MD files. Agents automate tasks like code review, security scanning, test generation, and documentation. This is a YAML generation skill. Use when asked to create an agent template, build an AI agent, create an automation agent, generate agent pipeline files, or set up a Harness agent. Trigger phrases: create agent template, agent template, AI agent, automation agent, build agent, code review agent, security scanner agent, Harness agent.

Generate Harness Infrastructure Definition YAML for deployment targets and create via MCP. Use when user says "create infrastructure", "infrastructure definition", "k8s cluster config", "deployment target", or wants to configure where workloads run.

Remove and tighten unnecessary LLM-generated comments — including narration disguised as "why", restated constraints, and why-comments a named symbol or the code structure already conveys. Use while editing, and as the final narration-comment pass before opening an MR or pushing, to strip the LLM narration the model left behind.

Craft comprehensive JIRA tickets (summary, context, requirements, deliverables, definition of done) from a title plus repo/user inputs. Trigger when the user asks for help drafting or refining a JIRA card, ticket, or story and expects structured markdown saved to disk.

Find the most active users in Amplitude, check your Google Calendar for open slots, and create personalised Gmail drafts inviting them to a research interview. Never sends — always saves as drafts for your review. Use when planning a user research sprint.

Launch Loki Mode autonomous SDLC agent. Handles PRD-to-deployment with minimal human intervention. Invoke for multi-phase development tasks, bug fixing campaigns, or full product builds.

Plan and operate project-agnostic parallel feature work using atomic file-owned packets, dependency waves, handoff prompts, and repair packets. Use when Codex needs to split any feature, migration, refactor, or platform change into independent subagent tasks, define packet contracts, decide which packets can run in parallel, generate handoff prompts, review completed packets, or create narrow follow-up repair packets.

The Jobs-to-be-Done framework as applied product methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity (discovery, prioritization, positioning) and where it becomes performative ritual (job-statement workshops that do not drive decisions, persona-theater disguised as JTBD). Triggers on jobs-to-be-done, JTBD, job statements, struggling moments, hire criteria, fire criteria, switch triggers, functional emotional social jobs, outcome-driven innovation. Also triggers when a team is over-relying on feature-request lists or persona archetypes that do not drive product decisions, when a positioning conversation needs the framing JTBD provides, or when discovery is producing outputs that do not connect to product strategy.

Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.

Set up and run rank tracking using Ahrefs MCP: pick the right keywords to track, segment them by purpose, set baselines, and define alert thresholds. Use this skill when starting a new tracking project, baselining for a campaign, choosing what to monitor, or building a rank reporting cadence. Triggers on rank tracking, keyword tracking, monitor rankings, track positions, what should we track, ranking dashboard, baseline rankings, alert thresholds. Also triggers when a stakeholder wants weekly or monthly ranking visibility.

Performs comprehensive documentation review including build validation, Diataxis analysis, structure audit, accuracy verification, and style compliance. Use when reviewing documentation changes or auditing documentation quality.