- Home
- Skills
- Business & Operations
- mise en place
More screenshots
Works with the AI Agents you already use
mise en place
Turn requirements into a traceable project blueprint with EARS specs, ADRs, and agent-specific guardrails.
Free
mise en place
Example session with this skill installed
Run mise-en-place on ./docs/prd.md for a React/Node stack. Target Cursor and Claude Code. Budget is 15 requirements.
- Read your context and instructions
- Compiled the mise en place
I have completed the intake and analysis of ./docs/prd.md. The project is initialized in blueprint/ with a budget of 15 requirements. I have identified 3 core capabilities: User Authentication, Real-time Sync, and Audit Logging.
Project Inventory
| File | Status | Description |
|---|---|---|
00-intent/intent.md | Created | High-level goals and non-goals |
01-analysis/requirement-analysis.md | Created | 14 requirements identified from source |
01-analysis/glossary.md | Created | 12 domain terms defined |
02-specs/ | Pending Gate A | EARS specs for Auth, Sync, and Logging |
traceability.md | Initialized | Tracking 14 requirements across phases |
Requirement Analysis Snippet
| ID | Requirement | Pri | Phase | Source |
|---|---|---|---|---|
| REQ-001 | When a user provides valid credentials, the system shall issue a JWT. | P0 | 1 | prd.md:L12 |
| REQ-002 | The system shall encrypt data at rest using AES-256. | P0 | 1 | prd.md:L45 |
| REQ-003 | While the server is unreachable, the client shall queue local changes. | P1 | 2 | prd.md:L22 |
Decisions Table (Clarification Required)
| Question | Default | Rationale |
|---|---|---|
| Use OAuth2 providers or email/pass? | Email/Password | PRD mentions "internal accounts" specifically. |
| Sync frequency for real-time? | < 500ms | Standard for collaborative editing tools. |
Next steps
- Review the Decisions Table and confirm or override the defaults.
- Approve Gate A in
blueprint/README.mdto proceed to EARS specification. - Run
python3 scripts/generate_register.pyto verify the current budget.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop building on shaky foundations. Developers often jump into code before the requirements are actually prepped, leading to scope creep and architectural debt. This skill enforces a spec-driven planning phase that turns raw briefs into a traceable, agent-ready blueprint.
What it does
- Requirement Analysis: Classifies every statement in your source doc into a structured breakdown with priority and phase.
- EARS Specification: Generates precise Easy Approach to Requirements Syntax (EARS) specs with concrete acceptance criteria.
- Architectural Guardrails: Creates ADRs and architecture docs that define test-enforceable dependency rules.
- Traceability Management: Links every line of code back to a specific requirement using a generated traceability register.
- Agent Orchestration: Produces custom
.cursorrulesor.clauderulesto ensure coding agents stay aligned with the blueprint.
How it works
- Intake: Point the tool at a PRD, research report, or existing codebase to inventory the current state.
- Clarification: Review a generated decisions table where the agent flags unsettled questions with proposed defaults.
- Layered Blueprinting: The agent builds the intent, specs, design, and roadmap in sequence, pausing for user approval at specific gates.
- Validation: It runs Python scripts to verify link integrity and ensures the requirement count stays within your defined budget.
Frameworks & tools
This skill utilizes Python 3.12 for registry generation and link checking. It generates configuration for Claude Code, Cursor, and GitHub Copilot, using EARS for requirements and ADRs for design decisions.
Why this beats prompting it yourself
Generic prompts often mix implementation details with requirements or hallucinate dependencies. This skill uses a strict, append-only procedural framework that separates "what" from "how," ensuring your architecture never introduces behavior without a documented requirement.
Use cases
- Kick off a greenfield project with a full spec-to-backlog pipeline.
- Adopt spec-driven development on a messy existing codebase.
- Break down a 50-page enterprise requirement document into actionable capabilities.
- Formalize architectural decisions to prevent regression in multi-agent workflows.
Known limitations
Does not implement backlog items or fix bugs. Requires a valid requirement document or PRD as input. Scripts require a Python 3.12+ environment.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Requires Python 3.12+ for validation scripts. Does not write implementation code. Not for one-off bug fixes or single ADR updates.
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 buying a skill.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 7 days ago
- Free with an Agensi account
- Software
Python 3.12+