Command
Post-PRD competitive research — maps similar solutions (anchored on the PRD), then co-curates the result with you to surface differentiation gaps that become candidate features. Sources mandatory.
Command
Defines or refines product metrics across 4 layers, each with baseline, formula, source, and a kill criteria tripwire.
Command
Micro-navigator that answers only "what is the canonical next step?" and flags gaps (work happening ahead of an unmet prerequisite), without running any step commands.
Command
Extracts a structured product persona (role, quantified pain, success criterion, anchor phrase, anti-persona).
Command
Distributes all system features into sequential, time-boxed phases, with Phase 0 as the end-to-end anchor set.
Command
Defines a realistic scope for a roadmap phase using a full MoSCoW breakdown against a fixed time budget.
Command
Wraps superpowers:writing-plans with RENATA guardrails to produce a method-compliant, ADR-respecting execution plan reviewed by the architect.
Command
Generates or refines a one-page Micro PRD for a product or feature in the RENATA standard.
Command
Guides a disciplined, scope-controlled refactor that preserves behavior, stays test-backed, and respects the project's ADRs.
Command
Facilitates a structured, actionable retrospective at the end of a roadmap phase or cycle, ending in an explicit decision.
Command
Consolidates the macro roadmap (Step 9) — explicit, verifiable gates per phase over the fases-overview created in Step 7.5, plus one file per phase.
Command
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
Command
Guides a short, focused technical investigation (spike) to answer a risk question before committing to a direction.
Command
Reports where the project stands in the RENATA flow and points to the next step, gating the current step behind human verification, without running any step commands.
Command
Manages the project's TODO backlog with inline markers in docs reconciled against a central, impact-ordered list, optionally mirrored to a task MCP.
Command
Triages an unprioritized list of bugs, debt, and tasks into a full MoSCoW breakdown with justification and an attack order.
Command
Maps a persona's before/during/after journey with a mermaid diagram, anti-journeys, critical points, and the metrics each journey generates.
Hook
Runs when a session starts on startup and resume, executing method-status-line.sh via bash (2 commands). From AInsteinsBR/renata.
Hook
Runs before the agent uses a tool for Skill and Bash tool calls, executing etapa-gate.sh via bash. From AInsteinsBR/renata.
Skill Claude CodeCodex
Use whenever the urge to "also add X", "while I'm here", "since I'm already touching this" appears, or a capability not foreseen in the feature spec comes up. Compares the proposal against the IN/OUT scope of the active feature and forces a conscious decision before expanding the work.
Skill Claude CodeCodex
Use whenever you finish a task, pause a session, complete a phase, or change the project status. Ensures the living docs (the active plan and CLAUDE.md Section 5) reflect the real state so the next session can resume without loss of context. Auto-activates on "done", "pausing", "completed", "end of phase", "I'm going…
Skill Claude CodeCodex
Use whenever you are about to propose a technical solution, write code, or implement a feature. Ensures the proposal respects the project's accepted ADRs before writing a single line of code. Auto-activates when detecting context like "implement X", "how do I Y", "I'm going to use library Z", or similar.