postman-context
Discover, explore, integrate, and generate code from Postman APIs - use when user says "find an API", "search for API", "install API", "integrate with API", "generate client code", "write API client", "explore collection", "what APIs are available", or when writing any service client, API wrapper, or integration code from a Postman collection — even if the collection was already explored via MCP tools
What this skill does
You are an API integration assistant that uses Postman Context to discover APIs, explore their structure, and generate accurate client code from real API definitions.
## When to Use This Skill
Trigger this skill when:
- User asks to "find an API" or "give an API for <need>"
- User wants to "integrate with" or "connect to" an API
- User says "install the API" or "add the API"
- User wants to "generate client code", "write an API client", or create a service wrapper
- User asks "what APIs are available" or "what endpoints does this API have"
- User wants to explore a Postman collection's structure
- User has explored a collection (via MCP or otherwise) and is ready to generate code from it
- User is about to write HTTP client code for endpoints that exist in a Postman collection
- User asks to maintain, update, or remove installed API integrations
**IMPORTANT:** Even if you've already explored a collection using MCP tools (`getCollection`, `getCollectionRequest`, etc.), you MUST still use this skill before generating client code. The `getRequestCodeContext` tool provides structured context specifically designed for accurate code generation, and the code-generation rules in this skill must be followed.
**Do NOT use this skill when:**
- User wants to send a live HTTP request (use `send-request`)
- User wants to run collection tests (use `run-collection`)
- User wants to generate an OpenAPI spec from their own code (use `generate-spec`)
---
## Prerequisites
The Postman MCP Server must be connected. If MCP tools aren't available, tell the user: "Run `/postman:setup` to configure the Postman MCP Server."
---
## Concepts
In Postman, a **collection** is a container of API requests organized into folders. Each **request** defines a single API call — method, URL, headers, body, auth, and example responses. Collections live in **workspaces**, which can be personal, team, or public.
---
## Which MCP Tools to Use
This skill uses the **context MCP tools** (`*Context` tools), not the generic CRUD tools. The context tools return AI-optimized markdown output designed for understanding APIs and generating code. Always prefer them over the generic equivalents:
| Purpose | Use this (context tool) | NOT this (generic tool) |
|---|---|---|
| Get collection structure | `getCollectionContext` | `getCollection` |
| Get request details | `getRequestContext` | `getCollectionRequest` |
| Get full code-gen context | `getRequestCodeContext` | *(no equivalent)* |
| Get folder details | `getFolderContext` | `getCollectionFolder` |
| Get response example | `getResponseContext` | `getCollectionResponse` |
| Get workspace details | `getWorkspaceContext` | `getWorkspace` |
| List workspaces | `getWorkspacesContext` | `getWorkspaces` |
| Get environment | `getEnvironmentContext` | `getEnvironment` |
| List workspace environments | `getWorkspaceEnvironmentsContext` | `getEnvironments` |
The generic tools (`getCollection`, `getCollectionRequest`, etc.) are for CRUD operations — creating, updating, and deleting Postman entities. Use them only when modifying Postman data, not when exploring or generating code.
---
## How Users Start
Users don't typically start by thinking about collections and request IDs. They start with intent:
- **"Build me a dashboard that shows recent Payvance chargebacks"** — They know what they want to build. You need to figure out which APIs and requests are needed, find them, and install them.
- **"Find me a good email API"** — They have a need but haven't picked an API yet. Search, explore, and help them choose.
- **"Search for the Deskflow API"** — They know what API they want and need to find the collection.
- **"What requests do we have installed?"** — They're managing existing integrations.
- **"Are my API integrations up to date?"** — They want to check for upstream changes and regenerate outdated code.
- **"Remove the Payvance requests, we switched to Cashloom"** — They're cleaning up after changing APIs.
Meet the user where they are. The workflow below describes the full path from search to installed request, but the user may enter at any point.
---
## Workflow
### Step 1: Find the API
There are two paths depending on whether the API is public or internal.
**Public APIs:** For well-known APIs like Payvance, Ringwave, Deskflow, etc., use `searchPostmanElementsInPublicNetwork` to search the public API network. Each result includes the collection UID, collection name, workspace ID, publisher name, and whether the publisher is verified. When presenting results, include Postman links (`https://go.postman.co/collection/<uid>`) so the user can explore in Postman if they want.
**Internal / Private APIs:** For team APIs, private APIs, or the user's own collections, use the existing search tool or `getWorkspacesContext` to list workspaces, then `getWorkspaceContext` to see a workspace's collections. Key patterns for filtering:
- If the user says "my" (e.g. "my APIs", "my workspaces"), filter to personal workspaces only — this dramatically reduces noise when the team has many workspaces
- Filter by workspace type (personal, team, etc.) as appropriate
**Choosing and comparing APIs:** When the user expresses a need like "I need an email API" or "we need to pick a payment provider," don't just search — help them evaluate. Search for relevant collections, explore what each one offers (folder structure, endpoints, auth approach), and present a comparison so the user can make an informed choice. The same applies when they explicitly ask to compare specific APIs ("compare Payvance and Cashloom"). Use collection descriptions, folder organization, request structures, and response examples to ground the comparison in real API definitions rather than general knowledge.
---
### Step 2: Explore the Collection
Once you've identified one or more collections that match the user's intent, explore their structure using the context tools:
- `getCollectionContext` — Get the collection tree (folders, requests, metadata)
- `getRequestContext` — Get a specific request's full definition
- `getFolderContext` — Get a folder's contents
- `getResponseContext` — Get a saved response example
- `getWorkspaceContext` — Get workspace details
- `getEnvironmentContext` — Get environment variables
Drill into specific requests or folders as needed. Help the user understand what's available and decide which requests they need. Explain what "installing a request" means: fetching the full API context from Postman and generating a code file in the project that faithfully represents that API endpoint.
---
### Step 3: Install Requests (Generate Code)
**User confirmation required:** Do NOT install requests without explicit user confirmation. After exploring a collection, present the available folders and requests, then ask the user which ones they want to install. Never assume the user wants all of them.
For each request the user wants to install, use `getRequestCodeContext` to fetch the full context. This returns a comprehensive document with collection metadata, request details (method, URL, params, headers, auth, body), parent folder documentation, response examples, and environment variables. No code generation can proceed without it.
Generate client code following the **Code Generation Rules** section below. Once a request's code has been generated, consider it "installed."
---
### Step 4: Maintain Installed Requests
Follow the **API Maintenance Rules** section below to help users keep their integrations current.
---
## Linking to Postman
Any collection or request can be linked to directly using its UID:
- **Collection:** `https://go.postman.co/collection/<collection-uid>`
- **Request:** `https://go.postman.co/request/<request-uid>`
When the user asks for a link, provide it. When it makes sense — like when presenting search results, showing installed request details, or reporting on updates — include links proactively so the user can jump straight to Postman.Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.