Generate comprehensive admin documentation for AEM Edge Delivery Services project handover. Use when handing over admin responsibilities, onboarding a new site administrator, or documenting admin procedures — e.g., "admin guide", "admin documentation", "admin handover".

Audit images across AEM Edge Delivery Services pages for SEO and performance. Checks alt text quality, missing dimensions, lazy loading on LCP images, fetch priority, file naming, and decorative image handling. Generates a per-page report with specific fix instructions for alt text (in the source document) and performance attributes (in block code or scripts). Use when optimizing Core Web Vitals, improving image accessibility, or auditing image SEO.

Use this when the page-import pipeline needs to produce structured HTML from authoring analysis for AEM Edge Delivery Services. Covers building section structure, applying block tables, handling metadata, and managing the images folder. Do not invoke directly — called by page-import as a pipeline step.

Generate project handover documentation for AEM Edge Delivery Services projects. Creates comprehensive guides for content authors, developers, and administrators. Use for "handover docs", "project documentation", "generate handover", "create guides".

Provide advisory guidance for the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEM 6.5 / AMS workflows only, with public-doc citations and AMS-specific MCP verification plans. Use for conceptual questions such as `statfileslevel`, filter rules, URL decomposition, cache invalidation behavior, rewrite behavior, and security headers.

Publish, deactivate, and delete AEM content programmatically via the Cloud Service Replication API (com.day.cq.replication). Covers single-path and bulk activation, preview-tier targeting with AgentFilter, synchronous/async options, ReplicationStatus checks, permission validation, workflow process steps, and replication event handling. Use when the user needs to publish pages, activate or deactivate content, check replication status, build workflow steps that replicate content, listen to replication events, query batch publication state, or work with Replicator, ReplicationOptions, or ReplicationStatusProvider in AEM Cloud Service.

Provide advisory guidance for the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEMaaCS cloud workflows only, with public-doc citations and cloud-specific MCP verification plans. Use for conceptual questions such as `statfileslevel`, filter rules, URL decomposition, cache invalidation behavior, rewrite behavior, and security headers.

Compares the performance of two or more audience segments across key metrics side by side. Use this skill when someone wants to compare audiences, cohorts, or groups — for example, "how do mobile users compare to desktop users on conversion," "compare new vs. returning visitors," "show me the difference between these two segments," "compare these audiences on our KPIs," or "which segment performs better." Also trigger for "segment comparison," "audience comparison," or "cohort comparison."

Compares the performance of two or more audience segments across key metrics side by side. Use this skill when someone wants to compare audiences or visitor groups — for example, "how do mobile visitors compare to desktop on conversion," "compare new vs. returning visitors," "show me the difference between these two segments," "compare these audiences on our KPIs," or "which segment performs better." Also trigger for "segment comparison" or "audience comparison."

Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

Run mutation testing with cargo-mutants on the Rust workspace. Use when asked to run mutation tests, check test quality, or find untested code paths.

Orchestrate work using ns2 — start issues, monitor progress token-efficiently, navigate work branches, and manage multi-issue workflows. Use whenever you're about to create ns2 issues or manage ongoing agent sessions.

Use when a draft (not-yet-final) Design mockup + bundle arrives and needs evaluating against Alethical's real data, backend capability, and UX before anyone builds it. Pressure-tests every element for buildability + honesty (grounded-answers), applies the design-audit accessibility/interaction rubric to everything a static design can reveal, and routes prioritized feedback to Design, the current coding agent, or the maintainer. Pre-build. First in the design- skill set: design-review → design-intake → design-build → design-audit.

Finds the work that eats the owner's time and repeats most, and proposes the first jobs AI could take on. Use when Andrew or the owner asks where the time goes, what to automate or hand to AI first, or to diagnose the business.

Test-Driven Development (TDD) and Incremental Implementation discipline. Use when implementing any feature or fixing bugs to enforce Red-Green-Refactor, vertical slicing, and atomic commits.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Load before you build any new kept workflow or Agent. It decides which one to build, or what to ask first. Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embeds_other (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an agent tool). Must be used whenever the current turn requires choosing or reconsidering the intent of an automation request, including compound requests, independent automations introduced mid-build, one-off questions or reports that need external systems you cannot query directly, and requests that need clarification before an anchor can be chosen. An explicit Agent request routes to agent-builder before ask_user. Do not load for routine edits or extensions when the conversation already targets a workflow or Agent.

Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from a node or an external service (for example a 401), before you explain the cause to the user.

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory