postman
Full API lifecycle management through Postman. Sync OpenAPI specs to collections, generate typed client code, run API tests, create mock servers, publish documentation, audit security against OWASP Top 10, and discover APIs across workspaces. Requires the Postman MCP Server. Use this skill when the user mentions Postman, API collections, syncing specs, generating SDKs, running API tests, creating mocks, API documentation, or API security audits. Triggers on tasks involving API development workflows, collection management, or any Postman-related operations.
What this skill does
# Postman Agent Skill
Full API lifecycle management through the Postman MCP Server. Sync specs, generate code, run tests, create mocks, publish docs, and audit security.
**Version**: 2.0.1
**Requires**: Postman MCP Server
## Prerequisites
This skill requires the Postman MCP Server to be configured. The MCP server exposes 111+ tools for interacting with Postman workspaces, collections, specs, environments, mocks, monitors, and more.
**Setup check**: Call `getAuthenticatedUser` via MCP. If it succeeds, you're connected. If it fails, walk through Setup below.
## Important: MCP Tool Behavior
Before using the workflows below, be aware of these behaviors:
- **`getWorkspaces` returns ALL workspaces.** For large organizations this can be 300KB+. If you already have a workspace ID, use `getWorkspace(workspaceId)` directly instead.
- **`getCollection` default response is a lightweight map** with `itemRefs` (folder/request tree). This is efficient for discovery. Only use `model=full` when you need complete request/response bodies, and be aware it can exceed 300KB for large collections. Prefer targeted `getCollectionRequest` and `getCollectionResponse` calls for specific endpoints.
- **`getTaggedEntities` returns 404 for missing tags**, not an empty array. Handle this gracefully. Tag functionality may require an Enterprise plan.
- **`runCollection` returns aggregate results only** (total requests, passed, failed, duration). It does NOT return per-request detail or error messages. For debugging specific failures, examine individual requests with `getCollectionRequest` and `getCollectionResponse` after the run.
- **`searchPostmanElements` only searches the PUBLIC Postman network**, not private workspaces. Always search private workspace first with `getCollections`.
## Setup
If MCP tools are not available or `getAuthenticatedUser` fails:
1. Get a Postman API key:
- Go to https://postman.postman.co/settings/me/api-keys
- Click "Generate API Key", name it "Claude Code"
- Copy the key (starts with PMAK-)
2. Set the environment variable:
```
export POSTMAN_API_KEY=PMAK-your-key-here
```
Add to `~/.zshrc` or `~/.bashrc` to persist.
3. Verify: Call `getAuthenticatedUser`. On success, call `getWorkspaces` to list workspaces, then `getCollections` with the workspace ID to count resources.
Present:
```
Connected as: <user name>
Your workspaces:
- My Workspace (personal) - 12 collections, 3 specs
- Team APIs (team) - 8 collections, 5 specs
You're all set.
```
## Routing
When the user's request involves Postman or APIs, match their intent to the correct workflow below. Always prefer these structured workflows over raw MCP tool calls.
| User Intent | Workflow |
|-------------|----------|
| Import a spec, push spec to Postman, create collection from spec, sync, push changes | **Sync Collections** |
| Generate client code, SDK, wrapper, typed client, consume an API | **Generate Client Code** |
| Find API, search endpoints, what's available, discover APIs | **Discover APIs** |
| Run tests, check if tests pass, validate API, test collection | **Run Collection Tests** |
| Create mock server, fake API, mock for frontend, mock URL | **Create Mock Servers** |
| Generate docs, improve documentation, publish docs, API docs | **API Documentation** |
| Security audit, vulnerabilities, OWASP, security check | **API Security Audit** |
| Is my API agent-ready?, scan my API, analyze spec for AI | Use the **postman-api-readiness** skill |
**Routing rules:**
1. Specific workflows take priority. If intent clearly maps to one, use it.
2. Ambiguous requests: ask the user what they need.
3. Multi-step requests chain workflows. "Import my spec and run tests" = Sync then Test.
4. Only use `mcp__postman__*` tools directly for single targeted updates or when the user explicitly asks.
---
## Workflow: Sync Collections
Keep Postman collections in sync with API code. Create new collections from OpenAPI specs, update existing ones, or push endpoint changes.
### Step 1: Understand What Changed
Detect or ask:
- Is there a local OpenAPI spec? Search for `**/openapi.{json,yaml,yml}`, `**/swagger.{json,yaml,yml}`
- Did the user add/remove/modify endpoints?
- Is there an existing Postman collection to update, or do they need a new one?
### Step 2: Resolve Workspace
If the user provides a workspace ID, call `getWorkspace(workspaceId)` directly. Otherwise, call `getCollections` with a workspace ID if known, or ask the user which workspace to use. Avoid calling `getWorkspaces` (no filter) on large org accounts as it returns all workspaces (300KB+).
### Step 3: Find or Create the Collection
**Updating an existing collection:**
1. Call `getCollections` with the `workspace` parameter
2. Match by name or ask which collection
3. Call `getCollection` to get current state
**Creating from a spec:**
1. Read the local OpenAPI spec
2. Call `createSpec` with `workspaceId`, `name`, `type` (one of `OPENAPI:2.0`, `OPENAPI:3.0`, `OPENAPI:3.1`, `ASYNCAPI:2.0`), and `files` (array of `{path, content}`)
3. Call `generateCollection` from the spec. **This is async (HTTP 202).** Poll `getGeneratedCollectionSpecs` or `getSpecCollections` until complete.
4. Call `createEnvironment` with variables from the spec:
- `base_url` from `servers[0].url`
- Auth variables from `securitySchemes` (mark as `secret`)
- Common path parameters
### Step 4: Sync
**Spec to Collection (most common):**
1. Call `createSpec` or `updateSpecFile` with local spec content
2. Call `syncCollectionWithSpec` to update the collection. **Async (HTTP 202).** Poll `getCollectionUpdatesTasks` for completion.
3. Note: `syncCollectionWithSpec` only supports OpenAPI 3.0. For Swagger 2.0 or OpenAPI 3.1, use `updateSpecFile` and regenerate via `generateCollection`.
4. Report what changed
**Collection to Spec (reverse sync):**
1. Call `syncSpecWithCollection` to update the spec from collection changes
2. Write the updated spec back to the local file
**Manual updates (no spec):**
1. `createCollectionRequest` to add new endpoints
2. `updateCollectionRequest` to modify existing ones
3. `createCollectionFolder` to organize by resource
4. `createCollectionResponse` to add example responses
### Step 5: Confirm
```
Collection synced: "Pet Store API" (15 requests)
Added: POST /pets/{id}/vaccinations
Updated: GET /pets - added 'breed' filter parameter
Removed: (none)
Environment: "Pet Store - Development" updated
Spec Hub: petstore-v3.1.0 pushed
```
---
## Workflow: Generate Client Code
Generate typed client code from Postman collections. Reads private API definitions and writes production-ready code matching the project's conventions.
### Step 1: Find the API
1. If workspace ID is known, call `getWorkspace(workspaceId)` to get the full inventory (collections, specs, environments) in one call. Otherwise ask the user which workspace.
2. Call `getCollections` with `workspace` parameter. Use `name` filter if specified.
3. If no results in private workspace, fall back to `searchPostmanElements` (public network only)
4. Call `getCollection` for the lightweight map (default, no `model` param)
5. Call `getSpecDefinition` if a linked spec exists (richer type info)
### Step 2: Understand the API Shape
For each relevant endpoint:
1. Call `getCollectionFolder` for resource grouping
2. Call `getCollectionRequest` for method, URL, headers, auth, body schema, parameters
3. Call `getCollectionResponse` for status codes, response shapes, error formats
4. Call `getEnvironment` for base URLs and variables
5. Call `getCodeGenerationInstructions` for Postman-specific codegen guidance
### Step 3: Detect Project Language
If not specified, detect from the project:
- `package.json` or `tsconfig.json` -> TypeScript/JavaScript
- `requirements.txt` or `pyproject.toml` -> Python
- `go.mod` -> Go
- `Cargo.toml` -> Rust
- `pom.xml` or `build.gradle` -> Java
- `Gemfile` -> Ruby
### Step 3b: Check for Variable Mismatches
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.