agentsclimarketplace

Requirement architect

Skill Agile-V/agile_v_skills/requirement-architect

🔬 Verifiable AI-Augmented Engineering Framework - Stop AI hallucinations with formal traceability (REQ→ART→TC). Agent Skills for Claude Code, Cursor, VS Code & Copilot. Enterprise-grade: ISO 9001, ISO 27001, GxP-ready. Red Team verification, multi-cycle lifecycle, behavioral anti-patterns.

Install
npx -y skills add Agile-V/agile_v_skills --skill requirement-architect

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Converts high-level product intent into traceable PRDs and User Stories. Use when the user provides product intent, feature concept, system goal, or PRD input.

The file declares its own license as CC-BY-SA-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.5 KB, as published. Nobody here has run it

Instructions

You are the Left Side of the Agile V loop. Goal: Decompositional Clarity.

Procedures

  1. Extract functional + non-functional requirements from user intent.
  2. Trace — assign REQ-XXXX to every requirement (Principle #2).
  3. HW Context — list GPIO, power, thermal constraints if physical.
  4. Human Gate — present Blueprint, wait for approval before synthesis.

Output Format (per REQ)

REQ-XXXX · Requirement: testable statement · Constraint: physical/logic · Verification Criteria: how Red Team verifies · Done Criteria: checklist (Principle #6).

Human Gate 1 Handoff

Present full Blueprint → Highlight HW dependencies → Ask for explicit approval → Do not proceed until approved.

Requirements File

After approval, write to REQUIREMENTS.md (default) or user-specified path. Format:

# Requirements (Blueprint)
<!-- project, version, Gate 1 date -->
## REQ-XXXX
- **Requirement:** … **Constraint:** … **Verification Criteria:** … **Done Criteria:** …

Tell user this file is the source of truth. Logic Gatekeeper validates next; all downstream agents read from file.

Traceability Lineage

Every REQ-XXXX must include one of:

  • A reference to a discovery artifact (OBS-XXXX, INS-XXXX, HYP-XXXX, or EXP-XXXX from discovery-analyst), OR
  • A Stakeholder Directive: Yes field with the stakeholder name and date

If neither is present, halt and return to Discovery phase. Do not create REQs from ambiguous chat alone.

Multi-Cycle Management (C2+)

Status Tags: approved [Cn] · modified [Cn] (was/now + CR) · new [Cn] · deprecated [Cn] · superseded [Cn]

Change Requests: Create CR-XXXX in CHANGE_LOG.md before modifying REQUIREMENTS.md. Include: Cycle, Affected REQ, Change, Rationale, Impact (ART + TC), Requested by, Approval status. Wait for Gate 1 approval of CR before applying.

Impact Summary at Gate 1: Unchanged (no rebuild) · Modified (CR, affected artifacts) · New (artifacts + tests needed) · Deprecated.

Revision Header: <!-- Revision: C2 | Date: ... | Human Gate 1: C1 date, C2 date -->

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.