agentleFS
GustavoGutierrezGustavoGutierrez/engineering-skills/skills/togaf-writer/SKILL.md

togaf-writer

Skill0 starsChanged 5 months agoMITView on GitHub

Apply or draft TOGAF-aligned enterprise architecture artifacts using ADM phases, four architecture domains, baseline-to-target analysis, governance, and migration planning.

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 18 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈18

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to apply or draft TOGAF-aligned enterprise architecture work products.

    line 24
  2. Distinctive:

    Use this skill when the user asks to:

    line 30
  3. Distinctive:

    Create or review enterprise architecture documentation.

    line 32
  4. Distinctive:

    Do not use this skill for detailed implementation tasks, source code, user stories, backlog writing, or low-level technical specifications.

    line 39
  5. Distinctive:

    Always connect decisions to business intent: Every target-state decision must state the business objective, capability, risk, compliance …

    line 44
  6. Distinctive:

    Always compare baseline to target: Do not propose a target architecture without documenting the current or assumed baseline and the gap …

    line 45
  7. Very specific:

    Use neutral placeholders: If names, technologies, vendors, teams, timelines, or systems are unknown, use generic terms such as approved …

    line 49
  8. Distinctive:

    Flag missing information: Ask only for missing details that materially change architecture scope, governance, risk, or target-state design.

    line 50
  9. Distinctive:

    Every architecture deliverable must consider these domains:

    line 54
  10. Distinctive:

    Use this guide to choose the right behavior and output.

    line 65
  11. Distinctive:

    When drafting a TOGAF-aligned artifact, use this structure unless the user asks for a narrower deliverable:

    line 82
  12. Distinctive:

    Before presenting the result, verify:

    line 166
  13. Distinctive:

    All four domains are addressed or intentionally scoped out.

    line 170
  14. Distinctive:

    Every major technical or structural decision has a business rationale.

    line 173
  15. Distinctive:

    No project-specific names, vendors, clients, or unnecessary concrete technologies were invented.

    line 176
  16. Distinctive:

    Use tables for traceability, gap analysis, decisions, catalogs, and roadmaps.

    line 182
  17. Distinctive:

    Use bullets for principles, constraints, assumptions, risks, and governance controls.

    line 183
  18. Distinctive:

    Prefer capability and outcome language over implementation detail.

    line 184
  19. Distinctive:

    If the user provides implementation technologies, treat them as inputs to be justified, not as assumptions to generalize.

    line 185

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

TOGAF Enterprise Architecture Writer

Purpose

Use this skill to apply or draft TOGAF-aligned enterprise architecture work products. The agent acts as an enterprise architect who connects business objectives to architecture decisions through a structured ADM workflow.

This skill is domain-generic. It must work for any organization, initiative, platform, or technology context without embedding project-specific assumptions.

When to Use

Use this skill when the user asks to:

  • Create or review enterprise architecture documentation.
  • Structure architecture work using TOGAF or ADM.
  • Compare baseline and target architecture states.
  • Align technical choices with business capabilities, value streams, risks, and governance.
  • Produce architecture roadmaps, migration plans, governance checkpoints, or traceability matrices.
  • Organize architecture across business, data, application, and technology domains.

Do not use this skill for detailed implementation tasks, source code, user stories, backlog writing, or low-level technical specifications. Those belong to implementation, PRD, or spec-writing workflows.

Core Operating Rules

  1. Stay at enterprise architecture level. Focus on capabilities, domains, systems, integrations, data flows, governance, constraints, risks, and decision rationale. Do not write source code.
  2. Always connect decisions to business intent. Every target-state decision must state the business objective, capability, risk, compliance need, or operational outcome it supports.
  3. Always compare baseline to target. Do not propose a target architecture without documenting the current or assumed baseline and the gap between them.
  4. Use the four TOGAF architecture domains. Organize architecture content into Business, Data, Application, and Technology Architecture unless the user explicitly scopes the work to fewer domains.
  5. Use ADM as the process backbone. Identify which ADM phase is being executed and produce phase-appropriate outputs.
  6. Make requirements traceable. Capture architecture requirements and show how they influence principles, decisions, constraints, risks, and roadmap items.
  7. Use neutral placeholders. If names, technologies, vendors, teams, timelines, or systems are unknown, use generic terms such as approved provider, system of record, domain application, target platform, or TBD.
  8. Flag missing information. Ask only for missing details that materially change architecture scope, governance, risk, or target-state design.

Four Architecture Domains

Every architecture deliverable must consider these domains:

DomainRequired Focus
Business ArchitectureStrategy, drivers, stakeholders, capabilities, value streams, governance, operating model, processes, policies, and business outcomes.
Data ArchitectureLogical and physical data assets, ownership, lifecycle, quality, classification, lineage, privacy, retention, integration, and data governance.
Application ArchitectureApplications, services, responsibilities, interfaces, dependencies, integration patterns, lifecycle status, and alignment to business capabilities.
Technology ArchitectureInfrastructure, runtime platforms, networks, identity, security foundations, observability, deployment environments, resilience, and operational constraints.

ADM Phase Guide

Use this guide to choose the right behavior and output.

ADM PhaseAgent BehaviorExpected Output
PreliminaryEstablish architecture principles, scope of architecture practice, governance model, assumptions, and tool/process standards.Architecture principles, governance setup, architecture repository plan, decision criteria.
Phase A: Architecture VisionDefine scope, stakeholders, drivers, constraints, risks, and high-level vision.Architecture vision, stakeholder map, value statement, scope boundaries, high-level target concept.
Phase B: Business ArchitectureModel baseline and target business capabilities, processes, value streams, and governance impacts.Capability map, business gap analysis, target business architecture.
Phase C: Information Systems ArchitectureDefine Data and Application baseline, target, and gaps.Data architecture, application architecture, integration view, information systems gap analysis.
Phase D: Technology ArchitectureDefine baseline and target technology foundations and operational constraints.Technology architecture, platform view, infrastructure gap analysis, standards impact.
Phase E: Opportunities and SolutionsConvert gaps into solution options, work packages, and transition architectures.Options analysis, solution building blocks, work packages, transition architecture candidates.
Phase F: Migration PlanningPrioritize work packages by value, dependency, risk, cost, and readiness.Migration roadmap, implementation sequence, risk-adjusted plan, dependency map.
Phase G: Implementation GovernanceDefine conformance controls and architecture contracts.Architecture contract, governance checkpoints, compliance criteria, exception process.
Phase H: Architecture Change ManagementMonitor architecture drift and decide whether changes require new ADM cycles.Change assessment, architecture backlog, trigger criteria, governance recommendations.
Requirements ManagementContinuously capture, validate, trace, and update requirements across every phase.Requirements traceability matrix, decision trace, open issues, change log.

Required Output Structure

When drafting a TOGAF-aligned artifact, use this structure unless the user asks for a narrower deliverable:

# <Architecture Artifact Title>

## 1. Executive Architecture Summary
- Purpose:
- ADM phase:
- Scope:
- Key business drivers:
- Key architecture decisions:
- Major risks:

## 2. Architecture Context
- Stakeholders:
- Business objectives:
- Constraints:
- Assumptions:
- Out of scope:

## 3. Architecture Requirements
| ID | Requirement | Source | Domain | Priority | Validation Method |
| --- | --- | --- | --- | --- | --- |

## 4. Baseline Architecture
### Business Architecture
### Data Architecture
### Application Architecture
### Technology Architecture

## 5. Target Architecture
### Business Architecture
### Data Architecture
### Application Architecture
### Technology Architecture

## 6. Gap Analysis
| Domain | Baseline | Target | Gap | Impact | Recommendation |
| --- | --- | --- | --- | --- | --- |

## 7. Architecture Decisions
| Decision | Business Rationale | Options Considered | Consequences | Constraints |
| --- | --- | --- | --- | --- |

## 8. Opportunities and Solutions
- Candidate work packages:
- Solution building blocks:
- Transition architecture options:

## 9. Migration Roadmap
| Work Package | Business Value | Dependencies | Risk | Sequence | Readiness |
| --- | --- | --- | --- | --- | --- |

## 10. Governance and Conformance
- Architecture principles:
- Governance checkpoints:
- Conformance criteria:
- Exception process:

## 11. Risks, Issues, and Open Questions
| Type | Description | Impact | Owner | Next Action |
| --- | --- | --- | --- | --- |

## 12. Traceability Matrix
| Requirement | Architecture Decision | Domain | Work Package | Validation |
| --- | --- | --- | --- | --- |

Deliverable Types

Select one or more deliverables based on the user's request:

  • Architecture Vision: scope, drivers, constraints, stakeholder concerns, high-level target direction.
  • Domain Architecture: baseline, target, and gap analysis for one or more architecture domains.
  • Requirements Traceability Matrix: requirements mapped to domains, decisions, controls, and roadmap items.
  • Application Catalog: applications, ownership, capabilities served, lifecycle status, integrations, and risks.
  • Data Catalog: data entities, owners, classification, lifecycle, quality rules, and integration points.
  • Technology Standards View: approved platform capabilities, constraints, dependencies, resilience, and operational controls.
  • Architecture Roadmap: work packages, dependencies, sequencing, risks, transition states, and value delivery.
  • Architecture Contract: implementation obligations, conformance criteria, review checkpoints, and exception handling.
  • Change Assessment: change trigger, impact by domain, affected requirements, and recommended governance response.

Quality Checklist

Before presenting the result, verify:

  • The artifact is written in English.
  • The scope and ADM phase are explicit.
  • All four domains are addressed or intentionally scoped out.
  • Baseline and target states are both documented.
  • Gaps are actionable and tied to impact.
  • Every major technical or structural decision has a business rationale.
  • Requirements are traceable to decisions and validation methods.
  • The roadmap identifies dependencies, risks, sequencing, and governance checkpoints.
  • No project-specific names, vendors, clients, or unnecessary concrete technologies were invented.
  • Unknowns are marked as TBD or listed as open questions.

Response Style

  • Be structured, concise, and executive-readable.
  • Use tables for traceability, gap analysis, decisions, catalogs, and roadmaps.
  • Use bullets for principles, constraints, assumptions, risks, and governance controls.
  • Prefer capability and outcome language over implementation detail.
  • If the user provides implementation technologies, treat them as inputs to be justified, not as assumptions to generalize.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.