Back to skills
SKILL.md
Saas Content Audit
ASecurityAudit planned SaaS entities against implemented files on disk — routes, UI components, database models, services, and specs. Compare planned vs built.
- 9 stars
- 0 votes
- 0 copies
- 0 views
- Added November 7, 2026
Works with
Security analysis
100/100npx -y skills add Basinfy/Basinfy-SaaS-Studio --skill saas-content-audit --agent claude-codeAre you the author of Saas Content Audit?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/basinfy-saas-content-audit)---
name: saas-content-audit
description: "Audit planned SaaS entities against implemented files on disk — routes, UI components, database models, services, and specs. Compare planned vs built."
argument-hint: "[--engine <stack>] [--system <name>] [--files] [--review full|lean|solo]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write, Agent, Bash(bash "*/.claude/skills/saas-content-audit/../../hooks/yaml-helper.sh" resolve_config *)
model: sonnet
---
!`bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys locale,automation,workflow`
# Content Audit (Planned vs Built Entities)
> **Interaction Localization Rule**:
> When `locale: pt-BR` (or user speaks Portuguese), ALL questions (`AskUserQuestion` / `ask_question`), confirmation prompts, and selectable options MUST be translated and presented in **Brazilian Portuguese (PT-BR)**.
> Any English question text or options in this skill are illustrative examples — NEVER display English questions or options to a Portuguese developer.
> Internal reasoning, code synthesis, tests, and documentation files MUST remain in English.
Audits the completion of planned software entities and architecture resources against actual
files implemented on disk across all SaaS layers.
---
## Phase 1: Read Planned Entities
1. **Entity Registry**:
- Read `design/registry/entities.yaml` if it exists (via `bash .claude/scripts/content-count.sh registry`).
- Extract planned models, API endpoints, UI views, and workers.
2. **PRD Quantities**:
- Grep `design/prd/*.md` for specified entity counts:
- Endpoints / routes
- Pages / screens / modals
- Database tables / schemas
- Background jobs / webhooks
---
## Phase 2: Scan Implemented Resources on Disk
Run `.claude/scripts/content-count.sh found` to discover implemented resources:
- **Routes**: `src/app/api/**`, `api/routes/**`, `src/pages/api/**`
- **Components**: `src/components/**`, `src/ui/**`, `src/views/**`
- **Schemas**: `prisma/schema.prisma`, `src/db/models/**`, `supabase/migrations/**`
- **Services**: `src/services/**`, `src/lib/**`, `src/workers/**`
- **Docs**: `docs/**`, `design/**`, `production/**`
---
## Phase 3: Gap Analysis & Completion Status Bands
Compare specified count ($S$) against found count ($F$):
- $F = 0$: **NOT STARTED**
- $0 < F/S < 50\%$: **EARLY**
- $50\% \le F/S < 100\%$: **IN PROGRESS**
- $F \ge S$: **COMPLETE**
Calculate:
- `total_specified`
- `total_found`
- `total_gap`
- `unbuilt_percentage`
---
## Phase 4: Output Report
Save audit findings to `production/audit/content-audit-[date].md`:
- Summary table by resource category
- Detailed gap table per system
- High-priority missing resources needed for MVP / current milestone.
Attribution
Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.