Dev & Engineering ✓ Microsoft · Official prompt-authoringreusable-promptsprompt-filesvscodeagent-customization

Reusable Prompt Creator

Turn recurring tasks into reusable .prompt.md files.

FollowSkills review · FSRS-2.0
Not recommended
45/ 100 5-point scale 2.3 / 5
Trust13 / 25 · 2.6/5

The skill asks the agent to review conversation history, extract implicit inputs, and save a prompt file, but it does not specify file permissions, sensitive-data handling, data flows, user confirmation, rollback, or external side effects. No malicious or clearly excessive behavior is shown, so the score remains moderate-low with deductions for these governance gaps.

Reliability8 / 20 · 2.0/5

The main extract-clarify-draft-iterate flow is coherent, but it depends on the unavailable agent-customization/prompts.md and gives no diagnostic handling for save failures, insufficient input, file conflicts, or abnormal conversations. The score is constrained by the static-review ceiling.

Adaptability9 / 15 · 3.0/5

The purpose of creating reusable .prompt.md files for repeatable tasks is clear, and the skill asks about fixed context, arguments, and scope. However, trigger boundaries, non-fit cases, input/output constraints, Chinese-language support, and environment reachability are unspecified, so points are deducted.

Convention6 / 15 · 2.0/5

The YAML metadata provides a name, description, argument hint, and disabled model invocation, while the body presents a progressive workflow. It lacks installation/dependency notes, examples, FAQs, limitations, versioning, changelog, and a maintenance path; the key related guide is also absent from the supplied evidence.

Effectiveness6 / 15 · 2.0/5

The skill plausibly completes the core task of turning a repeated conversation pattern into a reusable prompt and identifies .prompt.md as the artifact. However, its template, quality criteria, representative outputs, and benefit over manual authoring are not verified, and the saved result may still require substantial review, so the static ceiling applies.

Verifiability3 / 10 · 1.5/5

The skill file itself is auditable, and the repository includes general CI and testing signals, but the supplied evidence contains no skill-specific key-path tests, execution records, or independent corroboration. Only limited static verifiability is justified.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 5b3e1be7be9e
Before you use it
  • The referenced agent-customization/prompts.md is not included, so its templates, constraints, and dependencies cannot be verified.
  • The instruction to save the file does not define the destination, overwrite confirmation, sensitive-content filtering, or recovery behavior.
  • Chinese-language generation, cross-platform behavior, and offline applicability are not stated.
  • The supplied CI and test files primarily cover other components and do not establish that this skill itself executes reliably or produces consistently usable output.
See the full review method →

What it does & when to use it

This skill helps users extract a repeatable task pattern from the current conversation and create a .prompt.md prompt file. It identifies the recurring task, implicit inputs, and desired output format or style. When no clear pattern is present, it asks about the task, argument handling, and whether the prompt should be workspace-scoped or personal. It then drafts the file, asks about the weakest or most ambiguous parts, and finishes with a summary, example invocations, and related customization ideas.

It first reviews conversation history to extract repeated tasks, implicit inputs, and output requirements; if the information is insufficient, it asks what the prompt should do, whether it should accept arguments, and what scope it should have. It then drafts and saves a .prompt.md file, identifies ambiguous or weak sections, and asks the user about them. After finalization, it summarizes the prompt's purpose, provides example invocations, and suggests related customizations to create next. It also instructs the client to follow the agent-customization skill's prompts.md template and principles.

  1. A developer repeatedly asks for code explanations and wants to turn that workflow into a consistent code-explanation prompt.
  2. An engineer frequently generates tests for similar code and wants a reusable test-generation .prompt.md file.
  3. A maintainer performs recurring refactoring tasks and wants to formalize their inputs and output expectations in a prompt.
  4. A user has a repeated workflow but needs help deciding whether the prompt should use arguments, fixed context, workspace scope, or personal scope.

Pros & cons

Pros
  • Extracts a prompt from an actual conversation instead of requiring the user to start from a blank template.
  • Covers recurring tasks, implicit inputs, output format, and scope explicitly.
  • Uses an iterative draft, ambiguity review, clarification, and final-summary workflow.
  • Fits repeated development workflows such as code explanation, test generation, and refactoring.
Limitations
  • It depends on the agent-customization skill and prompts.md, whose contents and location are not included in the supplied source.
  • It is not automatically invoked and requires explicit user activation.
  • It does not specify the exact .prompt.md destination, installation procedure, or client trigger command.
  • The supplied SKILL.md contains no test examples, so its behavior across different clients cannot be confirmed from the source alone.

How to install

The repository is Microsoft's Visual Studio Code (Code - OSS) source repository, licensed under MIT, and bundles 61 skills; this profile covers only extensions/copilot/assets/prompts/skills/create-prompt/SKILL.md. The source material does not document a standalone installation command or installer for this skill. You can obtain the repository at https://github.com/microsoft/vscode and locate the path above; the standalone deployment location and client configuration procedure are not specified in the provided material.

How to use

In a client that supports the skill, invoke it explicitly because its metadata sets disable-model-invocation: true. Example request: "Turn our recurring TypeScript test-generation workflow into a reusable prompt. What arguments should it take, and should it be workspace-scoped or personal?" Answer its follow-up questions about the task pattern, inputs, output format, and scope. The source material does not define a slash command, trigger syntax, or required .prompt.md destination.

FAQ

Will it automatically create a prompt from any conversation?
No. The metadata sets disable-model-invocation to true, so the user must invoke it explicitly. Once invoked, it reviews the conversation and starts the creation workflow.
Where does it save the prompt?
The skill instructs the client to draft and save a .prompt.md file, but the supplied material does not specify the directory or the concrete configuration for workspace and personal prompts.
Does it require a network connection, Shell, or a runtime dependency?
The source shows no requirement for network access, Shell, MCP, or a specific runtime. It does require the client to provide conversation access and filesystem access so it can review the conversation and save the generated file.

More skills from this repository

All from microsoft/vscode

Dev & Engineering ✓ Microsoft · Official

Tool Rename Compatibility Check

Protect existing prompts and tool configurations when built-in tools are renamed.

Dev & Engineering ✓ Microsoft · Official

Copilot Chat OpenTelemetry Instrumentation

A repository-specific guide for consistent OpenTelemetry instrumentation in Copilot Chat.

Dev & Engineering ✓ Microsoft · Official

VS Code Configuration Policy Maintainer

Standardize VS Code policy registration, export, and validation.

Design & Frontend ✓ Microsoft · Official

VS Code Design Philosophy

Turn vague UI discomfort into concrete fixes using shared values, principles, and design moves.

Dev & Engineering ✓ Microsoft · Official

Agent Host E2E Test Assistant

Maintain VS Code Agent Host end-to-end tests with strict replay fixtures.

Dev & Engineering ✓ Microsoft · Official

VS Code Integrated Browser Architecture

A practical architecture guide for safely changing VS Code's cross-process integrated browser.

Dev & Engineering ✓ Microsoft · Official

VS Code Agents Window Sessions

Safely implement and repair VS Code Agents window features.

Dev & Engineering ✓ Microsoft · Official

Commit Assistant

Creates repository-style commit messages and safely commits code changes.

Dev & Engineering ✓ Microsoft · Official

Agent Host Log Investigator

Trace session, transport, and host failures in Agent Host debug exports.

Dev & Engineering ✓ Microsoft · Official

VS Code Unit Test Runner

Run VS Code repository unit tests by file, test name, or compiled-output glob.

Dev & Engineering ✓ Microsoft · Official

VS Code Agent Customization Assistant

Create, repair, and troubleshoot VS Code Agent customization files and their loading behavior.

Dev & Engineering ✓ Microsoft · Official

Code OSS Launch & Debug

Launch a built-from-source VS Code with isolated profiles, Playwright control, and multi-process debugging ports.

Dev & Engineering ✓ Microsoft · Official

VS Code Accessibility Development Guide

A practical specification for accessible interactive features in VS Code.

Design & Frontend ✓ Microsoft · Official

VS Code CSS Layout Standards

Build reliable VS Code-style CSS layouts and text truncation behavior

Dev & Engineering ✓ Microsoft · Official

VS Code Chat Performance Lab

Benchmark chat rendering and detect memory growth across VS Code builds.

Dev & Engineering ✓ Microsoft · Official

Component Fixtures for Screenshot Testing

Create stable, theme-aware VS Code component fixtures for isolated screenshot testing.

Dev & Engineering ✓ Microsoft · Official

VS Code Smoke Test Assistant

Run, filter, and debug VS Code end-to-end smoke tests.

Dev & Engineering ✓ Microsoft · Official

VS Code Crash Dump Symbolicator

Turn native VS Code crash dumps into readable backtraces with method names.

Dev & Engineering ✓ Microsoft · Official

Local VS Code Web Workbench

Validate VS Code workbench and Agents window changes in a local vscode.dev instance.

Dev & Engineering ✓ Microsoft · Official

Feedback Action

Reads current-session feedback and applies the requested code changes.

Related skills