WinAppProfiles

Use when the user wants to merge dev into main for a production release — covers rebasing dev from main if behind, automatic semantic versioning from conventional commits, merge commit, release tagging, and syncing dev back onto main.

Use when the user wants to ship current working changes through a feature branch PR into the DEV branch — covers pulling latest, staging, committing, pushing, PR creation, merge, branch cleanup, and syncing DEV locally.

Audit all feature specs in docs/features/ against the current template, CAP-ID standards, open questions, logical gaps, and plan coverage — then request user authorization before making any changes

Universal coding patterns, constraints, TDD workflow, atomic todos

Prevent semantic code duplication with capability index and check-before-write

Mandatory code reviews via /code-review before commits and deploys

Atomic commits, PR size limits, commit thresholds, stacked PRs

Run the full HomeRadar project orchestration loop — picks up the next todo task, spawns the appropriate agent, and iterates until all tasks are complete

Schema awareness - read before coding, type generation, prevent column errors

Analyze existing repositories, maintain structure, setup guardrails and best practices

Audits and removes stale git worktrees and branches (local + remote origin) that have been merged into `dev`. Use this whenever the user wants to clean up branches, prune stale worktrees, remove merged branches, tidy up the repo, or do any kind of branch housekeeping. Also trigger when the user says things like "let's clean up the repo", "what branches can I delete", "remove old branches", or asks about git branch hygiene — even if they don't use the word "stale". Always invoke this skill before manually running git branch -d or git worktree remove commands.

Personal assistant for walking the user step-by-step through any markdown file, manual, guide, runbook, or instruction document. Use this skill whenever the user says things like "walk me through", "run me through", "guide me through", "step me through", or references a .md file, manual, runbook, or guide they want help executing. Also invoke when the user provides a file path to a markdown document and asks for help following it. ALWAYS use AskUserQuestion for every prompt to the user — never just print a question as plain text.

Automated project implementation orchestrator that drives feature-driven development from a single initial prompt through to completed code. Use this skill when the user invokes /continue-tasks, /review-tasks, /update-tasks, /init-features, or /reinit. Also trigger proactively when docs/INITIAL_PROMPT.md exists and the user says anything like "move forward", "keep building", "what's next", "continue the implementation", or "start working on the project". This skill manages the full lifecycle: extracting feature specs via interview, generating phased implementation plans, spawning typed agents to execute tasks, monitoring completion sentinels, recovering from failures, and archiving finished work — all driven by markdown files that act as the shared state between orchestrator and worker agents.

Archive legacy plans and tasks, normalize all feature specs to the current template, then launch the full orchestration loop

Dry-run project status report. Produces a read-only snapshot of all feature specs, plans, and task progress without spawning any agents or modifying any files. Use this when the user invokes /review-tasks or asks for a project status snapshot, completion percentage, or "what's left".

OWASP security patterns, secrets management, security testing

Context preservation, tiered summarization, resumability

Start any type of modern application — web apps, APIs, full-stack projects, Docker-based stacks, microservices, and more. Use this skill whenever the user wants to run, launch, start, execute, or spin up an application or service. Trigger it even when the user says "start the app", "run it", "boot it up", "kick it off", "get it running", "spin it up", or any similar phrase. Also trigger when the user asks how to run the project, which command starts the UI, how to get the dev environment going, or when a prompt includes a technology name alongside a run/start intent (e.g. "start the Next.js app", "run the FastAPI server", "launch the Docker stack").

Sync active task files — checks for completion sentinels and updates plan status without re-running any tasks

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

Multi-repo and monorepo awareness — topology analysis, API contract tracking, cross-repo context