- Home
- Skills
- Agents & Orchestration
- Brownfield Reverse Specifier
Works with the AI Agents you already use
Brownfield Reverse Specifier
Reverse-engineers undocumented codebases into structured 7-file specification suites and task baselines.
$2
Brownfield Reverse Specifier
Example session with this skill installed
Onboard this Node/Express repo. It has a Postgres DB and React frontend. Reverse-engineer the current state into the specs/ folder and create the TASKS.md baseline.
- Read your context and instructions
- Compiled the brownfield reverse specifier
I have inspected the repository manifests, directory structure, and source code. The project uses Express for the API, Sequelize for Postgres migrations, and a React/Tailwind frontend. I have reverse-engineered the existing capabilities into the 7-file specification suite and generated a baseline task list.
Project Baseline (specs/TASKS.md)
| Phase | Task ID | Description | Status |
|---|---|---|---|
| Phase 0 | ARCH-BSL-1 | Express Server Core & Middleware | [✓] |
| Phase 0 | DB-TBL-1 | Users & Authentication Schema | [✓] |
| Phase 0 | SEC-AUTH-1 | JWT-based Auth Strategy | [✓] |
| Phase 0 | UI-CMP-1 | React Dashboard & Sidebar | [✓] |
| Debt-1 | SEC-GAP-1 | Implement rate limiting on /api/login | [ ] |
| Debt-1 | TST-GAP-1 | Add integration tests for Sequelize models | [ ] |
| Debt-1 | ARCH-HLT-1 | Implement /health health-check endpoint | [ ] |
Onboarding Summary
The following files were created in the specs/ directory:
0-product-requirements-document.md: Mapped existing features toPRD-US-*.1-architecture.md: Documented the Express/Node service layer and RAG setup.2-database-schema.md: Extracted User, Session, and Post models.3-security-design.md: Defined current CORS and JWT middleware logic.4-user-interface-design.md: Documented Tailwind theme and component library.5-testing-plan.md: Identified existing Jest suites and current gaps.6-deployment-config.md: Parsed Dockerfile and environment requirements.
Next steps
- Review
specs/3-security-design.mdfor identified technical debt in the auth flow. - Run
change-and-triage-leadto begin implementing the Debt-1 hardening tasks. - Validate the
ARCH-API-*tags against your API documentation.
Connects securely to your tools. The creator never sees your data.
About this skill
Brownfield codebases often lack the documentation required for reliable agentic development. This skill solves the "cold start" problem for legacy repositories by reverse-engineering existing logic, schemas, and architecture into a structured specification format. It allows you to onboard undocumented code into a spec-driven workflow without manual auditing.
What it does
- Architectural Discovery maps existing directory structures, route controllers, and service layers into a formal architecture document.
- Schema Extraction parses migration files and models to document the current database state and entity relationships.
- UI/UX Auditing identifies Tailwind configurations, component patterns, and design tokens used in the current frontend.
- Security Mapping documents existing auth middleware, RBAC rules, and environment variable requirements.
- Technical Debt Logging flags security vulnerabilities or missing test coverage discovered during the inspection.
How it works
- Inspection of project manifests, directory trees, and configuration files to identify the tech stack.
- Analysis of controllers, middleware, and database schemas to reconstruct the product logic.
- Clarification of any ambiguous modules with focused questions and recommended defaults.
- Generation of the canonical 7-file
specs/folder and aTASKS.mdbaseline reflecting the current state.
Frameworks & tools
Works with any repository containing standard manifests like package.json, pyproject.toml, Dockerfile, or .env.example. It parses SQL migrations, UI components, and API route definitions.
Why this beats prompting it yourself
Writing a complete specification for an existing project is tedious and prone to missing edge cases in auth or database constraints. This skill enforces a consistent tagging system (PRD-US-1, ARCH-API-1) across seven distinct files, ensuring the entire context is synchronized for downstream agent tasks.
Use cases
- Onboarding a legacy codebase into a new agent-led development workflow.
- Documenting a project inherited from another team or contractor.
- Auditing security and test gaps before starting a major refactor.
- Standardizing documentation for multiple microservices into a unified format.
Known limitations
Does not modify application code, migrations, or tests. Relies on existing file visibility to infer logic; highly obfuscated code or missing manifests may reduce accuracy.
Does not modify application code or fix bugs. Requires read access to manifests and schemas. Ambiguous logic requires user confirmation of recommended defaults.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 27 days ago