OS-level and system performance work for org run linus requests. Use when asked about infra, workers, performance, or low-level operational concerns.

Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.

Break down PM story into organized tasks in a single file following UI DEVELOPMENT order: Setup → Static UI → Dynamic Logic → Interactions → Testing. UNIQUE VALUE: Creates single task file (story-{name}.md) containing all tasks for a story. Tasks are ordered by UI development layers. Use this skill when: - Running /frontend.tasks command - User asks to "break down story", "create frontend tasks", "split into tasks" - Have story at docs/reference/pm/stories/ and need organized task breakdown - Need tasks ordered by UI development layers (not random order) - Starting frontend work and want organized task list Task order is CRITICAL: Setup → Static UI → Dynamic → Interactions → Tests Output: Create single file docs/reference/frontend/tasks/story-{name}.md with all tasks

Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.

When working with Streamlit web apps, data dashboards, ML/AI app UIs, interactive Python visualizations, or building data science applications with Python

2026-01-16 16:07 [agent=codex] [model=unknown] Created item

Break down PM story into organized tasks in a single file following LAYERED ARCHITECTURE order: Types → Database → Repository → Service → API → Tests. UNIQUE VALUE: Creates single task file (story-{name}.md) containing all tasks for a story. Tasks are ordered by backend architecture layers. Use this skill when: - Running /backend.tasks command - User asks to "break down story", "create backend tasks", "split into tasks" - Have story at docs/reference/pm/stories/ and need organized task breakdown - Need tasks ordered by backend architecture layers (not random order) - Starting backend work and want organized task list Task order is CRITICAL: Types → Database → Repository → Service → API → Tests Output: Create single file docs/reference/backend/tasks/story-{name}.md with all tasks

Verify and close stories after frontend/backend tasks are completed. Check ALL related task files, update story acceptance criteria checkboxes. UNIQUE VALUE: Ensures BOTH frontend AND backend tasks are verified before closing story. Prevents premature story closure. Use this skill when: - Frontend or backend notifies "task completed, please verify" - User asks to "verify story", "accept story", "close story", "mark story done" - Need to check if a story can be marked as complete - User asks "is story X done?", "can we close story X?" CRITICAL: Must check BOTH frontend tasks (docs/reference/frontend/tasks/) AND backend tasks (docs/reference/backend/tasks/) before closing. Output: Update story file checkboxes from `- [ ]` to `- [x]`

Execute frontend task implementation with TDD. Read task file, execute steps, verify each, update status. Use this skill when: - User asks to "implement task/plan", "start implementation", "execute plan", or "start coding" - Have task file (story-* or standalone-*) ready to execute - User asks to "use TDD", "write test first", or "test-driven" - User asks to "write tests", "add tests", "create tests" - Fixing UI bugs (write failing test first) TDD Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST TDD Cycle: RED (failing test) → Verify fails → GREEN (minimal code) → Verify passes → REFACTOR Prerequisites: - Task file in docs/reference/frontend/tasks/ (story-* or standalone-*) - Read design-system.md, constraints.md, design spec before coding Flow: Read Task → Read Constraints → Execute Steps → Verify → Test → Update Status

**Model**: Claude Sonnet 4.5

Complete implementation of **Prompt 2.2: Create Gamma AI Skill** with comprehensive requirements gathering, content generation, prompt engineering, theme selection, and error handling.

Initialize a Dataverse workspace on a new machine or new repo. USE WHEN: ".env is missing", "setting up on a new machine", "starting a new project", "initialize workspace", "new repo", "first time setup", "configure MCP server", "MCP not connected", "load demo data", "sample data", "create a new environment", "select environment", "which environment". DO NOT USE WHEN: installing tools (use dataverse-setup).

DEPRECATED: Use component-builder instead for M3-compliant, production-grade components.

Measure quality effectively with actionable metrics. Use when establishing quality dashboards, defining KPIs, or evaluating test effectiveness.

Resolve requirement ambiguities through STRUCTURED questioning: one question at a time, with recommended options and reasoning. UNIQUE VALUE: Prevents overwhelming users with multiple questions. Provides expert recommendations for each decision. Use this skill when: - Running /pm.clarify command - User says "unclear", "not sure what this means", "confused about" - User asks "what does X mean?", "how should X work?", "can you clarify?" - Requirements have conflicting or inconsistent details - Stories are missing acceptance criteria or have gaps - Need to fill information gaps BEFORE development can proceed Process: Ask ONE question at a time (max 5 per session), provide recommended option with reasoning. DO NOT ask multiple questions at once - this overwhelms users.

Autonomous multi-session feature development framework. Use when the user wants to systematically implement features from a specification, track progress across sessions, and ensure all tests pass before marking features complete. Activated by the /lynyx-agent-kit:auto-coder command or when working with feature_list.json files in an .auto-coder directory.

Browse, analyze, and contribute to the team's SharePoint solution library. Uses agent teams for intelligent tagging and pattern extraction.

Generates personalized outreach messages by pulling context from Dataverse records. Creates tailored emails for new prospects, re-engagement, follow-ups, or cross-sell. Use when user says "draft an email to [contact]", "write outreach for", "help me reach out to", "compose email", "re-engage this contact", "follow-up email", "prospecting email", or "outreach message for".

Generate reports from brief.json on demand — without running a build. Four report types for different audiences: brief (design state), build (status + deviations), customer (simplified, zero jargon), deployment (checklists + env mapping).

Reviews opportunities in the sales pipeline to identify stuck deals, missing next steps, weak qualification, and unbalanced stages. Use when user asks "how is my pipeline looking", "analyze pipeline health", "which deals are stuck", "pipeline review", "find at-risk deals", "identify stalled opportunities", or "audit my open deals".