lee-to

Plan implementation for a feature or task. Two modes — fast (single quick plan) or full (richer plan with optional git branch/worktree flow). Use when user says "plan", "new feature", "start feature", "create tasks".

Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions. Use when user says "implement", "start coding", "execute plan", or "continue implementation".

Refine an existing implementation plan with a second iteration. Re-analyzes the codebase for gaps, missing tasks, and wrong dependencies. Use after /aif-plan or to improve an /aif-fix plan. Optional +check flag validates refinements via a fresh-context subagent.

Verify completed implementation against the plan. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met. Use after "/aif-implement" completes, or when user says "verify", "check work", "did we miss anything".

Fix a bug or problem. Supports fix-now or plan-first; no args executes FIX_PLAN.md. When a regression check is needed, reproduce first, then implement and rerun it. Adds logging and suggests extra coverage.

Executes QA test cases created by /aif-qa in human-guided or automated-agent mode. Use when you need to walk through QA one case at a time, record pass/fail results, or have an agent verify cases through browser, CLI, API, automated tests, or file/document checks.

Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".

Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.

Generate contracts, validation specs, and implementation plan from milestone artifacts. Use when the user has added requirements to milestone artifacts/ and wants to formalize them into contracts, or says "generate", "create contracts", or "formalize requirements".

Validate contracts, validation specs, plan, and project map. Runs structural checks and LLM cross-review, then produces a verify report. Use after /hlv-generate or after manual edits to contracts, when the user says "verify", "check", or "validate structure".

Interactive interview to fill artifacts directory. Walks through domain, features, infrastructure, decisions, and unknowns. Use at project start or when adding features.

Execute the implementation plan by assigning agents to tasks, generating code and tests from contracts. Agents work in parallel within stages. Use after /hlv-verify passes, when the user says "implement", "generate code", or "execute plan".

Interactive session to resolve open questions. Walks through each question, gives a recommendation, asks the user, and updates the file. Use after /hlv-generate when open questions exist.

Run all mandatory validation gates (from gates-policy.yaml) and produce a release decision. Use after /hlv-implement completes, when the user says "validate", "run gates", "check gates", or "release check".

Review a GitHub pull request and post a verdict comment. Stateful — if a previous review comment exists, review only the new commits since the last review and track whether prior findings were addressed. Focus on code cleanliness, duplication, and docs sync. Use when user says "review this PR", "check the PR", "leave a review on <PR URL>", or passes a PR URL / number.

Используй этот skill, когда нужно подключить и настроить Nuxt Content v3 в Nuxt-проекте: collections (content.config.ts), schema/frontmatter, запросы queryCollection(), рендер Markdown через <ContentRenderer>, навигация и (опционально) поиск.