菜单
Comprehensive map and workflows for the API domain. Triggers when users ask to 'design an API', 'secure the APIs', 'update endpoints', 'view the API ecosystem', or want to see all available API orchestration skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create, optimize, critique, and programmatically structure prompts for AI systems. Use this skill whenever the user is designing or improving a static prompt, system prompt, coding prompt, agent prompt, workflow prompt, MCP-oriented prompt package, or an algorithmic prompt optimization pipeline. Also use it when the user asks to turn vague AI behavior into a precise instruction set, tool policy, agent spec, evaluation metric, or prompt architecture.
Enforce and manage DESIGN.md specifications, extract design systems from URLs, and combine design reasoning with token roles to prevent drift.
Assumption-first architecture review skill to stress-test project plans and expose hidden risks.
Forces the agent to act with a Claude-like product mindset, prioritizing user journey, UX states, and visual quality before coding.
Compiles and extracts session knowledge into a living, interconnected LLM-Wiki. Instead of writing isolated logs, it identifies key entities, updates cross-referenced topic files in docs/knowledgelib/, and maintains an index and chronological log. Use this to ensure persistent, compounding project knowledge.
Overrides the agent's behavior to enter an interactive, consulting mode. Instead of guessing or immediately executing a task, the agent will analyze the request and ask guiding, targeted questions to clarify intent, constraints, and requirements first.
| name | ecosystem-api |
| description | Comprehensive map and workflows for the API domain. Triggers when users ask to 'design an API', 'secure the APIs', 'update endpoints', 'view the API ecosystem', or want to see all available API orchestration skills. |
Welcome to the api domain ecosystem. This directory contains specialized agentic skills for designing, scaling, securing, and evolving Application Programming Interfaces (REST, GraphQL, gRPC).
For Orchestrator Agents (
task-decomposer,parallel-planner): When asked to plan an API-related task, you MUST consult the workflows below. Do not hallucinate steps; map your plan strictly to these available skills in the order defined.
When the user asks to "design a new API", "create endpoints", or "build an API from scratch", execute these skills sequentially:
@contract-first-designer -> Designs the OpenAPI/Swagger specification or GraphQL schema.@api-mock-designer -> Generates mock servers and fake data responses based on the contract.@sdk-scaffolder -> Generates client SDKs or typed interfaces (e.g., TypeScript interfaces) from the contract.When the user asks to "secure the API" or "prepare the API for high traffic":
@protocol-selector -> Evaluates REST vs. GraphQL vs. gRPC needs if not yet decided.@auth-flow-designer -> Designs OAuth2, JWT, or Session-based authentication and authorization mechanisms.@rate-limit-strategist -> Prevents abuse by designing throttling, rate-limiting, and quota rules.When the user asks to "update the API", "release v2", or "change endpoints":
@breaking-change-detector -> Analyzes the new contract against the old one to flag backward-incompatible changes.@changelog-generator -> Compiles developer-friendly release notes mapping the API changes.When the user asks to "make the API production-ready" or "add webhooks":
@webhook-architect@api-observability-planner to define logging, tracing, and metric alerts.API development is contract-driven and security-first. Every skill in this domain is programmed to defend against breaking changes for API consumers and ensure robust security boundaries. Never prioritize speed over backward compatibility in a public API environment.
As an AI Agent reading this ecosystem file, you must actively guide the user to install the missing skills for the selected workflow.
To install all skills within this ecosystem at once, you must execute or instruct the user to execute the provided installation script:
python skills/ecosystem-api/scripts/install_all.py
Execution Rule: Do not attempt to perform the tasks of these skills yourself. Your job is to install them and hand off the execution to the appropriate skill, or instruct the user to trigger the newly installed skills in order.