spec-driven プラグイン
Spec Driven — orchestrator-first Agent Skills for spec-driven development. The orchestrator skill turns a PRD or idea into approved SPECs, tracked GitHub Issues, TDD-implemented slices, QA gates, and reviewed PRs. Includes gap-analysis, write-specs, execute-specs, scaffold-mvp, create-issues, qa-analyst, code-review-and-quality, sonarqube-autofix, draw.io/Mermaid architecture diagrams, and MCP integrations.
spec-driven プラグインのインストール方法
両方のコマンドを Claude Code 内で実行してください。最初のコマンドで marketplace を一度追加し、2 番目のコマンドでプラグインをインストールします。
/plugin marketplace add afonsoft/skills
/plugin install spec-driven@afonsoftspec-driven の内容
プラグイン自身のファイルから読み込まれた 62 個のパーツ です。
コマンド 27
/spec-driven:name として実行- /spec-driven:architecture
Execute spec-driven skill: architecture
- /spec-driven:building-mcp-servers
Execute spec-driven skill: building-mcp-servers
- /spec-driven:code-review-and-quality
Execute spec-driven skill: code-review-and-quality
- /spec-driven:composio-mcp
Execute spec-driven skill: composio-mcp
- /spec-driven:create-agent-harness
Execute spec-driven skill: create-agent-harness
- /spec-driven:create-issues
Execute spec-driven skill: create-issues
- /spec-driven:create-readme
Execute spec-driven skill: create-readme
- /spec-driven:design
Execute spec-driven skill: design
- /spec-driven:diagnose
Execute spec-driven skill: diagnose
- /spec-driven:drawio-architecture
Execute spec-driven skill: drawio-architecture
- /spec-driven:execute-specs
Execute spec-driven skill: execute-specs
- /spec-driven:gap-analysis
Execute spec-driven skill: gap-analysis
- /spec-driven:improve-codebase-architecture
Execute spec-driven skill: improve-codebase-architecture
- /spec-driven:mermaid-architecture
Execute spec-driven skill: mermaid-architecture
- /spec-driven:migration-planner
Execute spec-driven skill: migration-planner
- /spec-driven:notebooklm-mcp
Execute spec-driven skill: notebooklm-mcp
- /spec-driven:observability-and-instrumentation
Execute spec-driven skill: observability-and-instrumentation
- /spec-driven:obsidian
Execute spec-driven skill: obsidian
- /spec-driven:orchestrator
Execute spec-driven skill: orchestrator
- /spec-driven:qa-analyst
Execute spec-driven skill: qa-analyst
- /spec-driven:quality-test-implementation
Execute spec-driven skill: quality-test-implementation
- /spec-driven:scaffold-mvp
Execute spec-driven skill: scaffold-mvp
- /spec-driven:sonarqube-autofix
Execute spec-driven skill: sonarqube-autofix
- /spec-driven:spec-driven
Run the spec-driven pipeline via the orchestrator skill
- /spec-driven:web-design-guidelines
Execute spec-driven skill: web-design-guidelines
- /spec-driven:wordpress-mcp
Execute spec-driven skill: wordpress-mcp
- /spec-driven:write-specs
Execute spec-driven skill: write-specs
SKILL 27
タスクが一致したときに Claude が読み込みます- architecture
Single owner of everything under docs/architecture/ — ADRs, architecture and design documents, and architecture diagrams. Routes each deliverable to the right engine: /mermaid-architecture for Markdown-native diagrams, /drawio-architecture for editable .drawio diagrams, and the optional archify skill for interactive standalone HTML diagrams (used only when already installed in the environment; never installed at runtime). Use whenever architecture documentation, ADRs, or architecture diagrams must be created or updated.
- building-mcp-servers
Use when building a new MCP server in TypeScript, Python, or C# that exposes tools to LLMs.
- code-review-and-quality
Use when reviewing code before it merges, whether written by an agent or a human.
- composio-mcp
Use when the user asks to connect an AI agent to external apps via Composio, or when Composio CLI or MCP setup fails.
- create-agent-harness
Use when initializing or migrating an AI agent harness in a repository.
- create-issues
Use when turning approved plans, specs, PRDs, or Epics into trackable GitHub Issues.
- create-readme
Use when generating or updating a project README.md or CHANGELOG.md.
- design
Use when designing, redesigning, or improving a frontend interface in Angular, React, or Blazor. Use for landing pages, dashboards, components, forms, and responsive layouts that must work mobile-first and then scale to desktop.
- diagnose
Use when the user reports a hard bug, unexpected failure, or performance regression that needs root-cause analysis.
- drawio-architecture
Use when generating or editing draw.io/diagrams.net architecture diagrams via MCP or native XML.
- execute-specs
Use when the user asks to implement an approved SPEC SDD using test-driven development.
- gap-analysis
Use when auditing a repository for evidence-backed gaps between code, SPECs, architecture, and documentation — before a release, after a review, or when the user asks what is missing or divergent. Confirmed gaps become Draft SPECs via write-specs, a tracked GitHub Epic via create-issues, and orchestrated execution via orchestrator, with an explicit approval gate before any external action.
- improve-codebase-architecture
Use when the user wants to improve architecture, consolidate tightly-coupled modules, or make a codebase more testable.
- mermaid-architecture
Use when generating, documenting, or updating architecture diagrams, flowcharts, sequence, ER, class, or state diagrams using Mermaid in docs/architecture/.
- migration-planner
Use when planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces an evidence-based Strangler Fig migration plan with per-domain SPECs. Default target is .NET (Blazor WebAssembly, .NET MAUI, ASP.NET Core); other stacks allowed by user decision. Do NOT use to implement code or when approved SPECs already cover the migration.
- notebooklm-mcp
Use when the user wants to configure, authenticate, or use Google NotebookLM via the nlm CLI or MCP.
- observability-and-instrumentation
Use when adding logging, metrics, tracing, or alerting to production code, or when a past incident lacks diagnostic data.
- obsidian
Use when working with Obsidian vaults, notes, tasks, properties, bases, plugins, or themes.
- orchestrator
Central entry point of the afonsoft agent harness. Use when starting a new project, resuming an existing one, planning features/Epics/releases, or running any multi-step agent-driven work. Validates and reconciles SPECs (SDD), audits the codebase and harness for gaps (security, architecture, performance, hygiene), proposes improvements, fragments work into GitHub Issues, delegates implementation/QA/review to specialized skills, and re-validates everything until delivery. Also use to review unapproved SPECs, reconcile open GitHub Issues with code, or run a final gap check before closing a release.
- qa-analyst
Use when the user asks for QA analysis, test planning, test cases, or root-cause analysis of a defect. Also use for post-merge PR review analysis: auditing recent closed PRs for Devin/GitHub/security bot comments, verifying whether requested corrections were applied, and turning pending fixes into SPECs.
- quality-test-implementation
Use when raising code quality or test coverage across a .NET, Java, or Python repository.
- reverse-engineer
Use when reverse engineering binaries, firmware, mobile apps, JavaScript/Electron apps, .NET assemblies, network protocols, or malware samples; when decompiling, deobfuscating, unpacking, debugging, or hooking shipped artifacts; when building agent environments (AgentEnv bundles) of a web application from a live instance or a capture; when solving CTF challenges (pwn, crypto, forensics, web); when a conclusion needs evidence from a shipped artifact rather than available source; or when coordinating authorized security assessments. Analysis-first and consent-gated — all active work requires written authorization and an approved scope. Do not use for ordinary review of source code you already have.
- scaffold-mvp
Use when starting a new .NET/Blazor/Angular MVP project in an empty repository.
- sonarqube-autofix
Use when analyzing SonarQube issues and turning them into SPEC SDDs and tracked GitHub Issues for TDD implementation.
- web-design-guidelines
Use when auditing UI code for interface-guideline compliance (accessibility, forms, animation, images, performance, UX copy) and/or validating a deployed page against Lighthouse 95+ targets. Produces evidence-based findings (file:line + Lighthouse JSON) and turns confirmed pendencies into Draft SPECs via write-specs. Do NOT use to design/build UI from scratch (use design) or to fix findings inline — fixes go through the SPEC pipeline.
- wordpress-mcp
Use when exposing a WordPress site to AI agents via MCP, or when WordPress MCP setup fails.
- write-specs
Use when the user needs to create or refine a feature SPEC SDD before implementation.
MCP server 8
プラグインとともに起動します- composiohttp
https://connect.composio.dev/mcp
- deepwikihttp
https://mcp.deepwiki.com/mcp
- drawiostdio
npx -y @drawio/mcp@latest
- notebooklm-mcpstdio
notebooklm-mcp
- obsidianstdio
npx mcp-obsidian-cli@latest
- wordpress-ai-enginehttp
https://<YOUR_DOMAIN>/wp-json/mcp/v1/http
- wordpress-mcphttp
https://<YOUR_DOMAIN>/wp-json/mcp/mcp-adapter-default-server
- wordpress-ultimatehttp
https://<YOUR_DOMAIN>/wp-json/mcp-ultimate/v1
Claude Code での spec-driven の使用方法
Claude Code セッションでコマンドを入力してください:
/spec-driven:architecture
/spec-driven:building-mcp-servers
/spec-driven:code-review-and-qualitySKILL にコマンドは不要です。リクエストが説明と一致したときに Claude が読み込みます。
更新、オフ、または削除
- プラグインを更新 (shell)
- claude plugin update spec-driven@afonsoft
- marketplace を更新
- /plugin marketplace update afonsoft
- 一時的にオフにする
- /plugin disable spec-driven@afonsoft
- 削除する
- /plugin uninstall spec-driven@afonsoft
spec-driven のスキル
- architectureafonsoft/skills
Single owner of everything under docs/architecture/ — ADRs, architecture and design documents, and architecture diagrams. Routes each deliverable to the right engine: /mermaid-architecture for Markdown-native diagrams, /drawio-architecture for editable .drawio diagrams, and the optional archify skill for interactive standalone HTML diagrams (used only when already installed in the environment; never installed at runtime). Use whenever architecture documentation, ADRs, or architecture diagrams must be created or updated.
4件のファイル19スター - building-mcp-serversafonsoft/skills
Use when building a new MCP server in TypeScript, Python, or C# that exposes tools to LLMs.
9件のファイル19スター - code-review-and-qualityafonsoft/skills
Use when reviewing code before it merges, whether written by an agent or a human.
3件のファイル19スター - composio-mcpafonsoft/skills
Use when the user asks to connect an AI agent to external apps via Composio, or when Composio CLI or MCP setup fails.
8件のファイル19スター - create-agent-harnessafonsoft/skills
Use when initializing or migrating an AI agent harness in a repository.
13件のファイル19スター - create-issuesafonsoft/skills
Use when turning approved plans, specs, PRDs, or Epics into trackable GitHub Issues.
2件のファイル19スター - designafonsoft/skills
Use when designing, redesigning, or improving a frontend interface in Angular, React, or Blazor. Use for landing pages, dashboards, components, forms, and responsive layouts that must work mobile-first and then scale to desktop.
24件のファイル19スター - diagnoseafonsoft/skills
Use when the user reports a hard bug, unexpected failure, or performance regression that needs root-cause analysis.
10件のファイル19スター - drawio-architectureafonsoft/skills
Use when generating or editing draw.io/diagrams.net architecture diagrams via MCP or native XML.
13件のファイル19スター - execute-specsafonsoft/skills
Use when the user asks to implement an approved SPEC SDD using test-driven development.
7件のファイル19スター - gap-analysisafonsoft/skills
Use when auditing a repository for evidence-backed gaps between code, SPECs, architecture, and documentation — before a release, after a review, or when the user asks what is missing or divergent. Confirmed gaps become Draft SPECs via write-specs, a tracked GitHub Epic via create-issues, and orchestrated execution via orchestrator, with an explicit approval gate before any external action.
4件のファイル19スター - improve-codebase-architectureafonsoft/skills
Use when the user wants to improve architecture, consolidate tightly-coupled modules, or make a codebase more testable.
5件のファイル19スター - mermaid-architectureafonsoft/skills
Use when generating, documenting, or updating architecture diagrams, flowcharts, sequence, ER, class, or state diagrams using Mermaid in docs/architecture/.
25件のファイル19スター - migration-plannerafonsoft/skills
Use when planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces an evidence-based Strangler Fig migration plan with per-domain SPECs. Default target is .NET (Blazor WebAssembly, .NET MAUI, ASP.NET Core); other stacks allowed by user decision. Do NOT use to implement code or when approved SPECs already cover the migration.
8件のファイル19スター - notebooklm-mcpafonsoft/skills
Use when the user wants to configure, authenticate, or use Google NotebookLM via the nlm CLI or MCP.
7件のファイル19スター - observability-and-instrumentationafonsoft/skills
Use when adding logging, metrics, tracing, or alerting to production code, or when a past incident lacks diagnostic data.
2件のファイル19スター - obsidianafonsoft/skills
Use when working with Obsidian vaults, notes, tasks, properties, bases, plugins, or themes.
8件のファイル19スター - orchestratorafonsoft/skills
Central entry point of the afonsoft agent harness. Use when starting a new project, resuming an existing one, planning features/Epics/releases, or running any multi-step agent-driven work. Validates and reconciles SPECs (SDD), audits the codebase and harness for gaps (security, architecture, performance, hygiene), proposes improvements, fragments work into GitHub Issues, delegates implementation/QA/review to specialized skills, and re-validates everything until delivery. Also use to review unapproved SPECs, reconcile open GitHub Issues with code, or run a final gap check before closing a release.
4件のファイル19スター - qa-analystafonsoft/skills
Use when the user asks for QA analysis, test planning, test cases, or root-cause analysis of a defect. Also use for post-merge PR review analysis: auditing recent closed PRs for Devin/GitHub/security bot comments, verifying whether requested corrections were applied, and turning pending fixes into SPECs.
3件のファイル19スター - quality-test-implementationafonsoft/skills
Use when raising code quality or test coverage across a .NET, Java, or Python repository.
5件のファイル19スター - reverse-engineerafonsoft/skills
Use when reverse engineering binaries, firmware, mobile apps, JavaScript/Electron apps, .NET assemblies, network protocols, or malware samples; when decompiling, deobfuscating, unpacking, debugging, or hooking shipped artifacts; when building agent environments (AgentEnv bundles) of a web application from a live instance or a capture; when solving CTF challenges (pwn, crypto, forensics, web); when a conclusion needs evidence from a shipped artifact rather than available source; or when coordinating authorized security assessments. Analysis-first and consent-gated — all active work requires written authorization and an approved scope. Do not use for ordinary review of source code you already have.
200件のファイル19スター - sonarqube-autofixafonsoft/skills
Use when analyzing SonarQube issues and turning them into SPEC SDDs and tracked GitHub Issues for TDD implementation.
15件のファイル19スター - web-design-guidelinesafonsoft/skills
Use when auditing UI code for interface-guideline compliance (accessibility, forms, animation, images, performance, UX copy) and/or validating a deployed page against Lighthouse 95+ targets. Produces evidence-based findings (file:line + Lighthouse JSON) and turns confirmed pendencies into Draft SPECs via write-specs. Do NOT use to design/build UI from scratch (use design) or to fix findings inline — fixes go through the SPEC pipeline.
4件のファイル19スター - wordpress-mcpafonsoft/skills
Use when exposing a WordPress site to AI agents via MCP, or when WordPress MCP setup fails.
11件のファイル19スター - write-specsafonsoft/skills
Use when the user needs to create or refine a feature SPEC SDD before implementation.
2件のファイル19スター - create-readmeafonsoft/skills
Use when generating or updating a project README.md or CHANGELOG.md.
19スター - scaffold-mvpafonsoft/skills
Use when starting a new .NET/Blazor/Angular MVP project in an empty repository.
19スター
spec-driven プラグインに関する質問
spec-driven プラグインをインストールするにはどうすればよいですか。
Claude Code で /plugin marketplace add afonsoft/skills を実行し、続いて /plugin install spec-driven@afonsoft を実行します。
spec-driven プラグインには何が含まれていますか。
spec-driven には 27 件のコマンド, 27 件のスキル, MCP サーバー が含まれています。
spec-driven プラグインにはどのようなコマンドが追加されますか？
/spec-driven:architecture, /spec-driven:building-mcp-servers, /spec-driven:code-review-and-quality, /spec-driven:composio-mcp, /spec-driven:create-agent-harness, /spec-driven:create-issues +21 が追加されます。Claude Code でプラグインのプレフィックスを使用して、例えば /spec-driven:architecture のように実行してください。
spec-driven プラグインを更新または削除するにはどうすればよいですか？
shell で claude plugin update spec-driven@afonsoft を使用して更新するか、/plugin の Installed タブから行ってください。削除するには /plugin uninstall spec-driven@afonsoft を使用してください。
spec-driven プラグインのライセンスは何ですか？
プラグインのマニフェストに記載されている MIT です。