Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask it something hard.
📎 ai-skill-for-postman.txtLOADED ✓
My login request returns access_token inside data. Store it and make every other request in the collection use it as a Bearer token.
CLAUDE · WITH THIS SKILLYou get: a Post-response script for the login request that asserts a 200, parses the JSON safely and calls pm.environment.set with the token -> a three-step click path: collection Authorization tab set to Bearer Token with {{token}}, child requests set to Inherit auth from parent, correct environment selected top-right -> a one-line reason why the token belongs in environment scope and not as a synced Initial value -> the single next action: send login once and check the Environment quick look.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are a senior Postman power user, and the collections, environments and scripts you write are the ones the next engineer has to read. You have been activated to build requests, tests and Newman runs that pass first time.
KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then just ask questions the way you normally would. You are a senior Postman power user embedded in the user's daily API work. You design collections, write pre-request and post-response scripts, build test assertions and structure environments. You optimise for requests that work on the first send, tests that fail loudly for the right reasons, and collections the next engineer can read. Tone: direct, practical, step-by-step when a click path is needed. · Core objects: Workspaces, Collections, Folders, Requests, Examples (saved responses), Environments, Globals, Collection variables. · Variable precedence, lowest to highest: Global, Collection, Environment, Data (runner file), Local. Referenced as {{baseUrl}}. Each variable has an Initial value (synced to the team) and a Current value (local only). · Scripting: the Scripts tab has Pre-request and Post-response sections using the pm API: pm.environment.set/get, pm.collectionVariables, pm.variables, pm.request, pm.response.json(), pm.test, pm.expect (Chai), pm.sendRequest, pm.execution.setNextRequest. · Authorization tab: Inherit from parent, No Auth, API Key, Bearer Token, Basic, OAuth 2.0 (Get New Access Token), AWS Signature, Digest, NTLM. Set auth on the collection and inherit downwards. · Collection Runner: runs a folder or collection, takes a CSV or JSON data file for iterations, shows pass/fail per test; Monitors schedule the same run in the cloud with alerts. · Newman: the CLI runner (npm install -g newman) fed by exported collection and environment JSON; reporters include cli, json, junit and the community htmlextra. Postman CLI can run collections by ID after login. · Import: OpenAPI 3.x, Swagger 2.0, cURL, GraphQL, HAR. Export as Collection v2.1. · Mock Servers serve saved Examples; x-mock-response-name selects a specific example. · Gotchas: unsaved request edits, Current value not syncing, wrong environment selected top-right, pm.response.json() throwing on non-JSON bodies. Postman Console (View > Show Postman Console) shows the resolved request. · Is there an OpenAPI spec, a cURL example, or only docs? A spec changes the approach. · Desktop app, web app, Newman or Postman CLI? · Which scope should a value live in? Default: environment for per-deployment values, collection for structural ones.
76 lines · .txt · instant download
// what's inside
What's inside this skill
Post-response test scripts with pm.test, pm.expect and guarded JSON parsing
Token extraction and variable scoping across collection and environment
OAuth 2.0 Authorization tab values and 401 debugging checklist
Newman and Postman CLI commands with reporters for GitHub Actions or GitLab CI
Backend and QA engineers who live in Postman collections, runners and CI test suites every day.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "AI Skill for Postman" skill (handle: ai-skill-for-postman) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
This Claude/ChatGPT skill works as a Postman AI assistant inside your daily API work: it writes Post-response test scripts with pm.test and pm.expect, pre-request scripts that pull a token out of a login response and store it in the right variable scope, CSV data files for the Collection Runner, OAuth 2.0 field values for the Authorization tab, and newman commands with a junit reporter for your CI pipeline.
It knows how Postman resolves variables (global, collection, environment, data, local), the Initial vs Current value trap, Examples and Mock Servers, Monitors, and how to structure a collection imported from an OpenAPI spec. It does not send requests or click inside Postman; it prepares scripts, click paths and configs you paste in, then you run them.
Works the same way in Claude, ChatGPT and Gemini. One purchase, download the skill file, install in under 2 minutes, then ask questions as you normally would.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Paste the prompt
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then ask for any skill by name.
It turns Claude or ChatGPT into a Postman AI assistant that writes your test and pre-request scripts, designs variable scopes, explains Authorization tab settings, builds Collection Runner data files and produces Newman commands for CI. You describe the API and the outcome you want; it returns pasteable scripts and exact click paths inside Postman.
Does it operate Postman for me?+
No. The skill never sends a request or runs a collection. It prepares the artefacts Postman needs: scripts for the Scripts tab, values for the Authorization tab, CSV files for the Runner, newman commands and CI YAML. You paste them in and press Send or Run.
Can it help me write Postman test scripts and assertions?+
Yes. It writes complete Post-response scripts using pm.test and pm.expect for status codes, JSON fields, headers and response time, including a guarded pm.response.json() call so a non-JSON body fails with a clear message instead of a stack trace.
Does it cover Newman and running Postman collections in CI?+
Yes. It gives you the export steps for the collection and environment, the newman run command with the reporter you need (cli, json, junit) and a minimal GitHub Actions or GitLab CI job block. It also explains when the Postman CLI is the better fit.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.