- Home
- Skills
- Product Management
- StreamTeem Spec Parser
Works with the AI Agents you already use
StreamTeem Spec Parser
Turns a spec file, or a structured Q&A when there is none, into a requirements summary with assumptions, blocking and deferred questions, and early warnings about dependencies, credentials, and access.
$1.99
StreamTeem Spec Parser
Example session with this skill installed
I need to implement the new user authentication flow. I don't have a spec file yet, so please ask me what you need to know to build one.
- Read your context and instructions
- Compiled the streamteem spec parser
I will initiate a structured Q&A session to build your spec.md. We will cover the problem statement, stakeholders, constraints, and success criteria.
1. Problem Statement
Question: What problem are you trying to solve with this new authentication flow, and who is currently affected by the lack of it?
Next steps
- Answer the problem statement question above.
- We will proceed through the remaining 6 categories (Solution, Users, Constraints, etc.).
- I will then generate the
spec.mdanddocs/design/requirements-summary.mdfor your review.
Connects securely to your tools. The creator never sees your data.
About this skill
Development begins with clarity. This skill prevents architectural drift and "I forgot to ask" sessions by enforcing a rigorous parsing of project specifications before a single line of code is written. It acts as a gatekeeper that ensures requirements are traceable, blocking questions are resolved, and assumptions are documented.
What it does
- Spec parsing extracts functional and non-functional requirements from existing markdown files.
- Guided discovery builds a
spec.mdfrom scratch using a structured 7-step Q&A session for new projects. - Gap analysis identifies missing information across behavior, constraints, and success criteria.
- Constraint mapping cross-references requirements against project-specific facts and coding standards.
- Incident assessment captures escalation details, affected systems, and evidence for production hotfixes.
- Prioritization separates high-risk blocking questions from deferred questions that can wait.
How it works
- Initialize by choosing between software development or production incident mode.
- Retrieve project specifications from the root directory or engage in a Q&A session to generate one.
- Audit the spec against existing project rules and architectural constraints.
- Generate a requirements summary file containing traceable requirements and specific assumptions.
- Classify and resolve blocking questions until the project is safe to move into the design phase.
Frameworks & tools
This skill operates on markdown-based documentation and integrates with project memory systems. It is optimized for teams using structured design documents and incident response logs.
Why this beats prompting it yourself
Generic prompts often overlook non-functional constraints or fail to distinguish between what must be known now and what can be decided later. This skill enforces a consistent schema for assumptions and traceability, ensuring that requirements are tied directly to their source in the spec.
Use cases
- Documenting requirements for a new feature when only a rough idea exists.
- Auditing an inherited spec file to find hidden dependencies or credential needs.
- Setting up a production incident war room with facts and evidence.
- Re-syncing project documentation after a major shift in product requirements.
Known limitations
Does not perform code execution or external API calls to fetch specs. Requires the user to provide file paths or respond to chat prompts for context.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
Does not perform code execution or external API calls. Requires manual input for spec paths or chat-based Q&A. Focuses on planning, not code generation.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Nothing to install. It runs in your AI agent.
Works alone or inside the Project Builder Pipeline. "Continue" is never treated as an answer to a blocking question.
Permissions
Reads the spec and project memory; writes the requirements summary (or incident assessment) and optionally spec.md when building one from Q&A.