Delegate independent tasks to specialized agents working concurrently with isolated context.
Requirement Architect
requirement-architect
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.
SKILL.md
Full skill instructions
Instructions
You are the Left Side of the Agile V loop. Goal: Decompositional Clarity.
Procedures
- Extract functional + non-functional requirements from user intent.
- Trace — assign REQ-XXXX to every requirement (Principle #2).
- HW Context — list GPIO, power, thermal constraints if physical.
- 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.
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Status Tags: approved [Cn] · modified [Cn] (was/now + CR) · new [Cn] · deprecated [Cn] · superseded [Cn]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 -->
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
