mastra-ai-architecture-rules
Mastra をランタイムとする AI サービスの設計・実装・リファクタリングで、agent / workflow / tool / memory / state の責務分離と、LLM に任せる範囲と決定的コードの境界を判断するスキル。『Mastra で設計して』『workflow を作って』『state…
Skill by efoo-team
Chalk Labs
Need help deploying mastra-ai-architecture-rules?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/efoo-team-mastra-ai-architecture-rules
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, ml, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mastra-ai-architecture-rules
What's inside
- Skill name
mastra-ai-architecture-rules- Description
- Mastra をランタイムとする AI サービスの設計・実装・リファクタリングで、agent / workflow / tool / memory / state の責務分離と、LLM に任せる範囲と決定的コードの境界を判断するスキル。『Mastra で設計して』『workflow を作って』『state に何を持つべきか』『memory や workspace が必要か』で使用し、single-agent first・workflow 最小化を適用する。現行 API 仕様の確認・検証・バージョン移行は mastra-framework-guide を使う。
- License
- unknown
- Instructions
- 444 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- design-memo-and-completion.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from efoo-team/skills
- 0.565score
logo-design
efoo-team
Only use when the user explicitly invokes /logo-design (or $logo-design in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
issue-report-user
efoo-team
Only use when the user explicitly invokes /issue-report-user (or $issue-report-user in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
create-skill
efoo-team
Only use when the user explicitly invokes /create-skill (or $create-skill in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
issue-report-dev
efoo-team
Only use when the user explicitly invokes /issue-report-dev (or $issue-report-dev in Codex).
SkillAFreshness: AClaude Code +9 - 0.561score
agent-native-project-design
efoo-team
Claude Code / Codex 等の既製AIエージェント・ハーネス上で運用するリポジトリ/プロジェクト側（CLAUDE.md / AGENTS.md・Agent Skills・hooks・subagents）を設計・整理・刈り込みするスキル。『CLAUDE.mdを設計/整理して』『この作業をエージェントに任せ…
SkillAFreshness: AClaude Code +9 - 0.561score
agent-harness-engineering
efoo-team
AIエージェントのハーネス（ループ・ツール表面・コンテキスト管理・認可・状態・停止条件・評価・可観測性）を設計・実装・調達する設計憲章。『ハーネスを設計して』『自作/SDK/既製のどれにするか』『ツール/MCP…
SkillAFreshness: AClaude Code +9 - 0.559score
execute
efoo-team
Only use when the user explicitly invokes /execute (or $execute in Codex).
SkillAFreshness: AClaude Code +9 - 0.556score
agent-prompt-design
efoo-team
AIエージェントに与えるプロンプト・instructions・システムプロンプト・委譲文・スキルや指示ファイルと、LLM judge のプロンプト・rubric の文面を書く/直す/レビューするときの執筆原則。エージェントサービスやスキルの指示文を設計する場面で、明示されなくても使用する。記述高度・既習概念の指名・工…
SkillAFreshness: AClaude Code +9 - 0.556score
define
efoo-team
機能の要望を受けたとき、実装前に要求・要件・設計方針・受け入れ条件をユーザーとの対話で確定し、要件定義書（Markdown）を作成するスキル。『〜を作りたい』『〜機能を追加/改修したい』『〜できるようにしたい』『要件定義して』と言われたとき、および仕様が未確定のまま実装を依頼されたときに、明示されなくても実装着手前に…
SkillAFreshness: AClaude Code +9 - 0.524score
estimate-proposal
efoo-team
Only use when the user explicitly invokes /estimate-proposal (or $estimate-proposal in Codex).
SkillBFreshness: BClaude Code +9 - 0.524score
agents-md-sync
efoo-team
Only use when the user explicitly invokes /agents-md-sync (or $agents-md-sync in Codex).
SkillBFreshness: BClaude Code +9 - 0.519score
oracle
efoo-team
Runs Oracle CLI in ChatGPT browser mode to ask an external cloud model for high-level reasoning, decomposition, review, or final evaluation.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 4
- Last commit (this folder)
- Oct 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/efoo-team/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from efoo-team
- 0.565score
issue-report-user
efoo-team
Only use when the user explicitly invokes /issue-report-user (or $issue-report-user in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
create-skill
efoo-team
Only use when the user explicitly invokes /create-skill (or $create-skill in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
logo-design
efoo-team
Only use when the user explicitly invokes /logo-design (or $logo-design in Codex).
SkillAFreshness: AClaude Code +9 - 0.565score
issue-report-dev
efoo-team
Only use when the user explicitly invokes /issue-report-dev (or $issue-report-dev in Codex).
SkillAFreshness: AClaude Code +9 - 0.561score
agent-native-project-design
efoo-team
Claude Code / Codex 等の既製AIエージェント・ハーネス上で運用するリポジトリ/プロジェクト側（CLAUDE.md / AGENTS.md・Agent Skills・hooks・subagents）を設計・整理・刈り込みするスキル。『CLAUDE.mdを設計/整理して』『この作業をエージェントに任せ…
SkillAFreshness: AClaude Code +9 - 0.561score
agent-harness-engineering
efoo-team
AIエージェントのハーネス（ループ・ツール表面・コンテキスト管理・認可・状態・停止条件・評価・可観測性）を設計・実装・調達する設計憲章。『ハーネスを設計して』『自作/SDK/既製のどれにするか』『ツール/MCP…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get mastra-ai-architecture-rules running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
mastra-ai-architecture-rules skill. Agent Mart. https://agentmart.dev/skills/efoo-team-mastra-ai-architecture-rules (last updated 2026-10-24)