integrate-context-matic

作者: github

Discovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration guidance,…

npx skills add https://github.com/github/awesome-copilot --skill integrate-context-matic

API Integration

When the user asks to integrate a third-party API or implement anything involving an external API or SDK, follow this workflow. Do not rely on your own knowledge for available APIs or their capabilities — always use the context-matic MCP server.

When to Apply

Apply this skill when the user:

  • Asks to integrate a third-party API
  • Wants to add a client or SDK for an external service
  • Requests implementation that depends on an external API
  • Mentions a specific API (e.g. PayPal, Twilio) and implementation or integration

Workflow

1. Ensure Guidelines and Skills Exist

1a. Detect the Project's Primary Language

Before checking for guidelines or skills, identify the project's primary programming language by inspecting the workspace:

File / PatternLanguage
*.csproj, *.slncsharp
package.json with "typescript" dep or .ts filestypescript
requirements.txt, pyproject.toml, *.pypython
go.mod, *.gogo
pom.xml, build.gradle, *.javajava
Gemfile, *.rbruby
composer.json, *.phpphp

Use the detected language in all subsequent steps wherever language is required.

1b. Check for Existing Guidelines and Skills

Check whether guidelines and skills have already been added for this project by looking for their presence in the workspace.

  • {language}-conventions is the skill produced by add_skills.
  • {language}-security-guidelines.md and {language}-test-guidelines.md are language-specific guideline files produced by add_guidelines.
  • update-activity-workflow.md is a workflow guideline file produced by add_guidelines (it is not language-specific).
  • Check these independently. Do not treat the presence of one set as proof that the other set already exists.
  • If any required guideline files for this project are missing: Call add_guidelines.
  • If {language}-conventions is missing for the project's language: Call add_skills.
  • If all required guideline files and {language}-conventions already exist: Skip this step and proceed to step 2.

2. Discover Available APIs

Call fetch_api to find available APIs — always start here.

  • Always provide the language parameter using the language detected in step 1a.
  • Always provide the key parameter: pass the API name/key from the user's request (e.g. "paypal", "twilio").
  • If the user did not provide an API name/key, ask them which API they want to integrate, then call fetch_api with that value.
  • The tool returns only the matching API on an exact match, or the full API catalog (name, description, and key) when there is no exact match.
  • Identify the API that matches the user's request based on the name and description.
  • Extract the correct key for the user's requested API before proceeding. This key will be used for all subsequent tool calls related to that API.

If the requested API is not in the list:

  • Inform the user that the API is not currently available in this plugin (context-matic) and stop.
  • Request guidance from user on how to proceed with the API's integration.

3. Get Integration Guidance

  • Provide ask with: language, key (from step 2), and your query.
  • Break complex questions into smaller focused queries for best results:
    • "How do I authenticate?"
    • "How do I create a payment?"
    • "What are the rate limits?"

4. Look Up SDK Models and Endpoints (as needed)

These tools return definitions only — they do not call APIs or generate code.

  • model_search — look up a model/object definition.
    • Provide: language, key, and an exact or partial case-sensitive model name as query (e.g. availableBalance, TransactionId).
  • endpoint_search — look up an endpoint method's details.
    • Provide: language, key, and an exact or partial case-sensitive method name as query (e.g. createUser, get_account_balance).

5. Record Milestones

Call update_activity (with the appropriate milestone) whenever one of these is concretely reached in code or infrastructure — not merely mentioned or planned:

MilestoneWhen to pass it
sdk_setupSDK package is installed in the project (e.g. npm install, pip install, go get has run and succeeded).
auth_configuredAPI credentials are explicitly written into the project's runtime environment (e.g. present in a .env file, secrets manager, or config file) and referenced in actual code.
first_call_madeFirst API call code written and executed
error_encounteredDeveloper reports a bug, error response, or failing call
error_resolvedFix applied and API call confirmed working

Checklist

  • Project's primary language detected (step 1a)
  • add_guidelines called if guideline files were missing, otherwise skipped
  • add_skills called if {language}-conventions was missing, otherwise skipped
  • fetch_api called with correct language and key (API name)
  • Correct key identified for the requested API (or user informed if not found)
  • update_activity called only when a milestone is concretely reached in code/infrastructure — never for questions, searches, or tool lookups
  • update_activity called with the appropriate milestone at each integration milestone
  • ask used for integration guidance and code samples
  • model_search / endpoint_search used as needed for SDK details
  • Project compiles after each code modification

Notes

  • API not found: If an API is missing from fetch_api, do not guess at SDK usage — inform the user that the API is not currently available in this plugin and stop.
  • update_activity and fetch_api: fetch_api is API discovery, not integration — do not call update_activity before it.

来自 github 的更多技能

console-rendering
github
在Go中使用基于结构体标签的控制台渲染系统的说明
official
acquire-codebase-knowledge
github
当用户明确要求映射、记录或熟悉现有代码库时使用此技能。触发词如“映射此代码库”、“记录…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
通过AgentRC指令命令生成定制化的AI代理指令文件。生成.github/copilot-instructions.md(默认,推荐用于VS Code中的Copilot…
official
acreadiness-policy
github
帮助用户选择、编写或应用AgentRC策略。策略通过禁用无关检查、覆盖影响/级别、设置…来定制就绪评分。
official
add-educational-comments
github
为代码文件添加教育性注释,将其转化为有效的学习资源。根据三个可配置的知识水平(初级、中级、高级)调整解释深度和语气。若未提供文件,自动请求文件,并附带编号列表以便快速选择。仅通过教育性注释将文件扩展最多125%(硬性限制:新增400行;超过1000行的文件限制为300行)。保留文件编码、缩进风格、语法正确性以及...
official
adobe-illustrator-scripting
github
使用ExtendScript(JavaScript/JSX)编写、调试和优化Adobe Illustrator自动化脚本。在创建或修改操作…的脚本时使用。
official
agent-governance
github
声明式策略、意图分类及审计追踪,用于控制AI代理工具访问与行为。可组合的治理策略定义允许/禁止的工具、内容过滤器、速率限制及审批要求——以配置而非代码形式存储。语义意图分类在执行工具前通过基于模式的信号检测危险提示(数据泄露、权限提升、提示注入)。工具级治理装饰器在函数层面强制执行策略...
official