Skip to content

Basinfy/Basinfy-SaaS-Studio / .agents/skills/saas-review-all-prds

saas-review-all-prds

Unverified

Run holistic cross-PRD consistency, business-rule, and scope alignment review.

Running this workflow on this client

Run commands from the project root (use Git Bash on Windows if bash points to an unavailable WSL distro). Shared studio files live in .claude/; follow .agents/PORTABLE-RUNTIME.md and .claude/docs/config-resolution.md for client tools, delegation, and approval rules.

Run bash .claude/hooks/yaml-helper.sh resolve_config --keys locale,automation,workflow,system_overrides and use its output below.

Review All PRDs

Locale & User Profile: Match locale (pt-BR → natural Brazilian Portuguese questions/options, overriding English examples; en → English) and user_profile (founder → plain business language with (Recomendado) first, zero tech jargon; developer → technical). Keep code/tests in English.

This skill reads every system PRD simultaneously and performs two complementary reviews that cannot be done per-PRD in isolation:

  1. Cross-PRD Consistency — contradictions, stale references, and ownership conflicts between documents
  2. Product Design Holism — issues that only emerge when you see all systems together: conflicting business rules, broken unit economics, cognitive overload, pillar drift, competing progression loops

This is distinct from /saas-design-review, which reviews one PRD for internal completeness. This skill reviews the relationships between all PRDs.

When to run:

  • After all MVP-tier PRDs are individually approved
  • After any PRD is significantly revised mid-production
  • Before /saas-create-architecture begins (architecture built on inconsistent PRDs inherits those inconsistencies)

Every AskUserQuestion call follows .claude/docs/automation-modes.md (collaborative asks always · guided major-only · autonomous logs and proceeds; automation_always_ask categories always prompt).

Argument modes:

Focus: $ARGUMENTS (blank = full)

  • No argument / full: Both consistency and design theory passes
  • consistency: Cross-PRD consistency checks only (faster)
  • design-theory: Product design holism checks only
  • since-last-review: Only PRDs modified since the last review report (git-based)

workflow per PRD (per .claude/docs/workflow-modes.md): each PRD validates against its effective tier — the project value, overridden per system by the system_overrides row for that system when the block lists one. At full, validate all 8 sections across all PRDs. At standard, validate the 5 required sections; optional sections (User Stories / Personas, Configuration Parameters, conditional Formulas) are surfaced as advisory only. At minimal, this skill is not applicable (no PRDs).

Phase 1: Load Everything

Read references/1-load.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Parallel Execution

Phase 2 (Consistency) and Phase 3 (Product Strategy) are independent — they read the same PRD inputs but produce separate reports. Spawn both as parallel Agent agents simultaneously rather than waiting for Phase 2 to complete before starting Phase 3. Collect both results before writing the combined report.

Spawn both as lead-product-manager sub-agents (subagent_type: lead-product-manager) — PRD consistency and product-strategy review is its domain.

When spawning the Phase 2 and Phase 3 agents, always pass:

  • The loaded PRD content each phase needs — not file paths. Paste the sections; the sub-agent has its own context and cannot re-read Phase 1's results, so a path forces a full re-read (and contradicts the "do not re-read" rule below). Pass only the phase's slice: Phase 2 (consistency) needs each PRD's Dependencies, Detailed Design/Rules, Formulas, Configuration Parameters and Acceptance Criteria; Phase 3 (product strategy) needs User Stories / Personas, tier limits, onboarding flows and the product pillars.
  • The full entity registry contents (design/registry/entities.yaml) if loaded in Phase 1b (paste the registry text, not just a file path)
  • The specific checklist items assigned to that agent's phase (Phase 2 gets 2a–2f; Phase 3 gets 3a–3g)
  • The engine name and version — stack.frontend and stack.version from project.yaml, resolving each field independently (if its key is absent or empty, use .claude/docs/technical-preferences.md) — plus docs/engine-reference/[engine]/VERSION.md

Do not rely on the subagent to re-read these files — it has its own context window and cannot access Phase 1 results unless they are explicitly passed in the Agent prompt.


Phase 2: Cross-PRD Consistency

Read references/2-consistency.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Phase 3: Product Design Holism

Read references/3-design-holism.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Phase 4: Cross-System Scenario Walkthrough

Read references/4-scenarios.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Phase 5: Output the Review Report

Read references/5-report.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Phase 6: Write Report and Flag PRDs

Read references/6-write.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Phase 7: Handoff

Read references/7-handoff.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.

Error Recovery Protocol

First, verify the artifact. If the return contract named a path, check the path exists before treating the phase as done — a named artifact that is not on disk is a failed phase, however fluent the response reads. An agent can burn a full phase and return a plausible preamble having written nothing, which is neither BLOCKED nor an error nor "fails to complete", so the trigger below never fires. Resume it naming the unmet contract; the context is usually still there.

If any spawned agent returns BLOCKED, errors, or fails to complete: surface it immediately, don't proceed past a dependency it blocks, and always produce a partial report (retry scope here = fewer PRDs / single-system). Full procedure: .claude/docs/error-recovery-protocol.md.


Collaborative Protocol

In collaborative mode (the default). For guided and autonomous modes, see .claude/docs/automation-modes.md. In autonomous mode the PASS/CONCERNS/FAIL verdict is still printed and logged — only the closing handoff widget is skipped.

  1. Read silently — load all PRDs before presenting anything
  2. Show everything — present the full consistency and design theory analysis before asking for any action
  3. Distinguish blocking from advisory — not every issue needs to block architecture; be clear about which do
  4. Don't make design decisions — flag contradictions and options, but never unilaterally decide which PRD is "right"
  5. Ask before writing — confirm before writing the report or updating the systems index
  6. Be specific — every issue must cite the exact PRD, section, and text involved; no vague warnings
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall