mcp-tool-designer SKILL.md skillA

mcp-tool-designer from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pramoddutta/aitesterblueprint4x/mcp-tool-designer@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pramoddutta/aitesterblueprint4x
Path
chapter_14_MCP_Create_VIBE/testskill-finder-mcp/skills/framework-packs/mcp-pack/mcp-tool-designer/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Oct 10, 2026
Size
4,011 bytes
Repository stars
14
License
none declared

Designs MCP tools an LLM can pick and call correctly: clear names, schemas with enums and bounds, descriptions that say when to use the tool, and paginated, size-capped responses. Use when an engineer says "design the tools for my MCP server", "review my MCP tool schema", "the model keeps calling the wrong tool", or pastes tool definitions. Produces tool specs and a FastMCP draft for the engineer to implement and verify.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# MCP Tool Designer

You design tools for the model, not for the API: **few tools, obvious names, tight schemas,
and bounded responses**, so the LLM picks the right tool with the right arguments.

## When to use
- A new MCP server is being planned and the tool list is still a REST endpoint dump.
- The model calls the wrong tool, invents arguments, or floods context with huge results.
- A tool review before release: names, schemas, descriptions, and response sizes.

## Workflow
1. **Start from user jobs.** List the 5-10 tasks users bring (ask if missing); one tool per job.
2. **Name tools.** `verb_noun` snake_case with a consistent domain noun (`search_test_cases`,
   `get_test_case`, `create_test_case`); no two names that sound interchangeable.
3. **Tighten the schema.** Few required params; enums (`Literal`); bounds (`Field(ge=1, le=50)`);
   length or pattern; defaults; IDs in the format other tools return; no free-form `options: dict`.
4. **Write the description.** What it does, "Use when ...", "Do not use for ..., call X instead",
   an example per param. Instructions about other tools or data are a tool-poisoning smell.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pramoddutta/aitesterblueprint4x/mcp-tool-designer@sha256:450a2573a648790b

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wxoq6yt2kjjpghay.svg)](https://markdownregistry.com/a/art_wxoq6yt2kjjpghay)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 10, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-10 265c235 4,011 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4011 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wxoq6yt2kjjpghay
GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/mcp-tool-designer
GET https://markdownregistry.com/api/v1/blob/450a2573a648790b686527ea37ea0ba420860d901a019657877d17499adb494a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from pramoddutta/aitesterblueprint4x

api-authorization-boundary-tester SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-authorization-boundary-tester/SKILL.md · Design safe API authorization-boundary tests across roles, scopes, tenants, and object ownership. Use when asked to…
v1.0.0 · audit A · 14 stars
api-collection-builder SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-collection-builder/SKILL.md · Convert approved API test cases into a Postman/Newman or Bruno collection. Use when asked to build an API collection…
v1.0.0 · audit A · 14 stars
api-contract-validator SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-contract-validator/SKILL.md · Compare observed HTTP API requests and responses with an OpenAPI or equivalent endpoint contract. Use when asked to…
v1.0.0 · audit A · 14 stars
api-performance-test-planner SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-performance-test-planner/SKILL.md · Create a review-ready API performance plan and optional k6 or JMeter draft. Use when asked to plan load, stress, spike…
v1.0.0 · audit A · 14 stars
api-resilience-tester SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-resilience-tester/SKILL.md · Plan controlled API resilience tests for timeouts, retries, throttling, duplicate delivery, dependency failures…
v1.0.0 · audit A · 14 stars
api-workflow-tester SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/api_testing/api-workflow-tester/SKILL.md · Design stateful tests spanning multiple API calls, lifecycle transitions, asynchronous jobs, events, or callbacks. Use…
v1.0.0 · audit A · 14 stars
pw-accessibility-auditor SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-accessibility-auditor/SKILL.md · Integrates automated accessibility checks into Playwright tests using axe-core. Use when an SDET says "add a11y…
v1.0.0 · audit A · 14 stars
pw-api-tester SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-api-tester/SKILL.md · Designs and generates API tests using Playwright's request context. Use when an SDET says "write API tests for this…
v1.0.0 · audit A · 14 stars
pw-ci-configurator SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-ci-configurator/SKILL.md · Generates CI configuration (GitHub Actions) for a Playwright suite. Use when an SDET says "set up Playwright in CI"…
v1.0.0 · audit A · 14 stars
pw-fixture-designer SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-fixture-designer/SKILL.md · Designs custom Playwright test fixtures (auth/session, seeded data, page objects) with correct setup/teardown and…
v1.0.0 · audit A · 14 stars
pw-flaky-debugger SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-flaky-debugger/SKILL.md · Diagnoses a flaky Playwright test and proposes web-first fixes. Use when an SDET says "this test is flaky", "passes…
v1.0.0 · audit A · 14 stars
pw-locator-fixer SKILL.md skill
pramoddutta/aitesterblueprint4x · chapter_02_Prompt_Eng/prompt_templates/playwright/pw-locator-fixer/SKILL.md · Scans a Playwright spec or Page Object for brittle locators and rewrites them to resilient ones. Use when an SDET says…
v1.0.0 · audit A · 14 stars

Every file in pramoddutta/aitesterblueprint4x

Browse by kind, by grade A, or by owner.