
Execute a single task end-to-end — either a new story or a fix from validation findings. Reads the task context and architecture, then produces working output that meets all acceptance criteria. Adapts to project type: writes code for code projects, writes deliverables for non-code projects.
Execute a version end-to-end with a coordinated agent team. Cycles through architect-version → DoD gate → build-stories → execute → validate until the version ships. A version is shipped when the human signs off.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Execute a Linear spec end-to-end with a coordinated agent team. Cycles through architect-version → build-stories → execute-task → validate-execution until the spec ships. Accepts a Linear identifier or text to search. A spec is shipped when the human signs off.
Manage Cloudflare DNS zones and records via Terraform in nexaedge/infrastructure. Auto-invoke when configuring a new domain, subdomain, DNS record, or zone. TRIGGER when: user mentions "DNS", "domain", "subdomain", "A record", "CNAME", "MX record", "TXT record", "SPF", "DKIM", "DMARC", "nameserver", "zone", "cloudflare", or needs to point a domain/subdomain to a service, IP, or Pages project. DO NOT TRIGGER when: user is asking about DNS concepts without wanting to make changes, or when working on non-NexaEdge infrastructure.
Deep-dive architecture for a single spec. Reads the Linear spec issue, the deliverable's Architecture document, and adjacent spec issues, then writes the spec body to the issue description and creates a `Spec vX.Y — Architecture` Project Document. Use before /build-stories.
Execute a single story sub-issue end-to-end — either a new story or a fix from validation findings. Reads the sub-issue, parent spec, and architecture, then produces working output that meets all acceptance criteria. Code goes through worktrees; execution logs and state changes go to Linear.
Create the project-level implementation approach as a Linear Project Document. For code projects: technology stack, schemas, API contracts, system design. For non-code projects: delivery approach, document structure, resource plan. Adapts based on the project spec. Use after /ideate.
Build a comprehensive project specification through conversational refinement. Adapts to any project type — code, business, research, consulting. Reads workspace context to understand where it is and what kind of project this is. Use at the very start of a new project or major initiative.
Post-spec retrospective that captures lessons learned, fixes documentation drift, and proposes skill improvements. Reads the Linear spec, story sub-issues with comments, and the Validation Report. Writes retrospective to the knowledge base on disk and posts a back-link comment on the spec issue.
Design an evolutionary delivery roadmap by creating a Linear initiative (where applicable), deliverable projects, and one issue per spec. Adapts to project type — code releases, consulting milestones, research phases. Use after /ideate and /architect.
Validate a Linear spec's implementation against its Definition of Done. For code projects: runs automated tests against the live application. For non-code projects: reviews deliverables against acceptance criteria. Writes a `Spec vX.Y — Validation Report` Project Document and comments the link on the spec issue. Runs incrementally on re-runs.
Deep-dive architecture for a single version. Reads the version spec, overall architecture, roadmap, and related versions, then produces a comprehensive architecture document with specific implementation choices. Adapts to project type. Use before /build-stories.
Break down a single version into executable story files. Reads the version spec, architecture, and roadmap, then creates ordered stories. Adapts to project type — code stories for engineers, deliverable stories for any project type. Use after /architect-version.
Create the implementation approach for a project. For code projects: technology stack, schemas, API contracts, system design. For non-code projects: delivery approach, document structure, resource plan. Adapts based on the project spec. Use after /ideate.
Build a comprehensive project specification through conversational refinement. Adapts to any project type — code, business, research, consulting. Reads workspace context to understand where it is and what kind of project this is. Use at the very start of a new project or major initiative.
Design an evolutionary delivery roadmap through conversational refinement. Defines version progression where each version delivers tangible value. Adapts to project type — code releases, consulting milestones, research phases. Use after /ideate and /architect.
Post-version retrospective that captures lessons learned, fixes documentation drift, and proposes skill improvements. Analyzes PROGRESS.md, story logs, QA results, and commit/change history to identify struggle patterns and knowledge worth preserving. Run after a version is shipped.
Validate a version's implementation against its Definition of Done. For code projects: runs automated tests against the live application. For non-code projects: reviews deliverables against acceptance criteria. Runs incrementally on re-runs. Ends with human validation guidance.
Break down a single Linear spec issue into executable story sub-issues. Reads the spec body, the spec architecture document, and the deliverable architecture, then creates one ordered sub-issue per story under the spec issue. Adapts to project type. Use after /architect-version.
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).