iterative-engineering

Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures. Reviews code for breaking contract changes. Spawned by the code-review skill as part of a reviewer ensemble.

Create git worktrees or branches for workspace isolation. Spawned by the iterative:implementing skill during setup phase.

Always-on plan-review persona. Reviews planning documents for internal consistency — contradictions between sections, terminology drift, structural issues, and ambiguity where readers would diverge. Spawned by the plan-review skill as part of a reviewer ensemble.

Always-on code-review persona. Reviews code for logic errors, edge cases, state management bugs, error propagation failures, and intent-vs-implementation mismatches. Spawned by the code-review skill as part of a reviewer ensemble.

Conditional code-review persona, selected when the diff touches migration files, schema changes, data transformations, or backfill scripts. Reviews code for data integrity and migration safety. Spawned by the code-review skill as part of a reviewer ensemble.

Conditional plan-review persona, selected when a tech plan proposes architecture decisions, external system integrations, performance requirements, or migration strategies. Reviews whether the approach will actually work. Spawned by the plan-review skill as part of a reviewer ensemble.

Internal implementation detail of the design-exploration skill. Do not invoke directly — requires a structured variation spec that only the design-exploration orchestrator provides. Writes one self-contained HTML file per variation with embedded metadata.

Always-on code-review persona. Reviews code for premature abstraction, unnecessary indirection, dead code, coupling between unrelated modules, and naming that obscures intent. Spawned by the code-review skill as part of a reviewer ensemble.

Conditional code-review persona, selected when the diff touches database queries, loop-heavy data transforms, caching layers, or I/O-intensive paths. Reviews code for runtime performance and scalability issues. Spawned by the code-review skill as part of a reviewer ensemble.

Create a pull request following repo conventions. Spawned by the implementation-wrapup skill to generate PR title, description, and create via GitHub CLI.

Document-type plan-review persona, selected when the document is a PRD or brainstorm. Reviews as a senior product leader evaluating product document quality. Spawned by the plan-review skill as part of a reviewer ensemble.

Conditional code-review persona, selected when the diff touches error handling, retries, circuit breakers, timeouts, health checks, background jobs, or async handlers. Reviews code for production reliability and failure modes. Spawned by the code-review skill as part of a reviewer ensemble.

Conditional plan-review persona, selected when a PRD has multiple priority levels with potential conflicts, unclear scope boundaries, or goals that don't align with requirements. Reviews scope decisions for internal alignment. Spawned by the plan-review skill as part of a reviewer ensemble.

Conditional code-review persona, selected when the diff touches auth middleware, public endpoints, user input handling, or permission checks. Reviews code for exploitable vulnerabilities. Spawned by the code-review skill as part of a reviewer ensemble.

Conditional plan-review persona, selected when the plan proposes abstractions, multi-layer architecture, plugin systems, generic frameworks, or infrastructure ahead of need. Reviews for unjustified structural complexity. Spawned by the plan-review skill as part of a reviewer ensemble.

Execute a single subtask from a technical plan. Reads plan context, loads referenced patterns, implements with TDD, and commits. Spawned by the iterative:implementing skill.

Document-type plan-review persona, selected when the document is a tech plan or implementation brief. Reviews as an implementer evaluating whether they can code from this plan. Spawned by the plan-review skill as part of a reviewer ensemble.

Always-on code-review persona. Reviews code for test coverage gaps, weak assertions, brittle implementation-coupled tests, and missing edge case coverage. Spawned by the code-review skill as part of a reviewer ensemble.

Browser automation using Vercel's agent-browser CLI. This skill should be used when the user says "browse a website", "fill a form", "take a screenshot", or "test a web page". Uses ref-based element selection.

Scope-first brainstorming with intelligent routing — assesses complexity upfront (Quick/Standard/Full), then adapts depth accordingly. Handles simple bug fixes in ~2 exchanges and complex features with full PRD ceremony. Triggers: "brainstorm", "create a PRD", "write requirements", "explore approaches", "think through options", or starting a new feature with unclear direction.

This skill should be used when the user says "review my code", "check these changes", or wants feedback on code before creating a PR. Also used after completing a task during iterative implementation.

Explore radically different design approaches for any page, component, or feature. Use when the user wants to compare multiple distinct visual directions side by side — not build one specific thing, but see several fundamentally different takes on the same UI. Signals: "explore designs for", "show me different ways to design", "radically different approaches", "what could this look like", "design exploration", "let's see some options before we commit", "different layout approaches", "different visual identities for the same content", wanting to see multiple families or variations before choosing a direction. Also triggers when the user pastes design exploration feedback (starts with "## Design Exploration Feedback") to iterate on a previous round, or pastes a design direction ("## Design Direction") to finalize. Do NOT trigger for building one specific design, visual refreshes, design critiques, brainstorming without visual output, single widget prototypes, or comparing CSS frameworks.

The craft of building design exploration prototypes. Covers file structure, control wiring, styling conventions, and output validation. Preloaded into the html-prototyper agent. Not intended for direct invocation.

Address code review feedback by evaluating validity and fixing issues — supports local agent feedback and GitHub PR threads. Triggers: "fix the review feedback", "address PR comments".

Internal skill for workspace isolation. Detects current git state and offers worktree/branch options. Called by iterative:implementing, not user-invocable.

Complete a feature branch with test verification and PR creation. Triggers: "finish up", "create a PR", "wrap up the feature". Also invoked by iterative:implementing after all tasks are complete.

Execute a tech plan with dependency-aware batching, TDD, code review, and PR creation. Triggers: "implement the plan", "start building", "start implementing", "execute the plan".

Review PRDs, brainstorm docs, tech plans, design docs, specs, or any planning document for issues. This skill should be used whenever the user wants feedback, critique, or a quality check on an existing planning or requirements document — even if they don't use the word "review." Common triggers include: "review the plan", "check the PRD", "critique my tech plan", "what's wrong with this plan", "poke holes in the requirements", "is this plan solid", "take a look at this spec", "give feedback on the brainstorm", or pointing to a doc file and asking if anything is off. Also triggers after writing a PRD or tech plan (to review what was just created), or when invoked by brainstorming or tech-planning skills. Do NOT trigger for code review (PRs, diffs, source files), writing/creating new plans, debugging, or reviewing non-planning documents (READMEs, CLAUDE.md, test coverage).

Investigate open questions through parallel research — prior art, constraints, competitive analysis. Triggers: "research this", "investigate questions", "resolve open questions", "look into this", or when a PRD has unresolved questions.

Turn requirements into a structured implementation plan with subtasks, dependencies, file paths, and test scenarios. Triggers: "create a plan", "tech planning", "write a tech plan", or has requirements ready to formalize.