What does this skill do, and when should you 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.
- A developer repeatedly asks for code explanations and wants to turn that workflow into a consistent code-explanation prompt.
- An engineer frequently generates tests for similar code and wants a reusable test-generation .prompt.md file.
- A maintainer performs recurring refactoring tasks and wants to formalize their inputs and output expectations in a prompt.
- A user has a repeated workflow but needs help deciding whether the prompt should use arguments, fixed context, workspace scope, or personal scope.
How do you install this skill?
- 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.
- Local filesystem
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.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/microsoft/vscode.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/extensions/copilot/assets/prompts/skills/create-prompt" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Turn our recurring TypeScript test-generation workflow into a reusable prompt. What arguments should it take, and should it be workspace-scoped or personal?
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.
What are this skill's strengths and limitations?
- 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.
- 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 does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Reusable Prompt Creator this page ✓ Microsoft · Official | 45 · Not recommended | ★ 194k | 11d ago | MIT |
| VS Code Agent Customization Assistant ✓ Microsoft · Official | 55 · Use with care | ★ 194k | 11d ago | MIT |
| Project Instruction Builder ✓ Microsoft · Official | 51 · Use with care | ★ 194k | 11d ago | MIT |
| Workflow Skill Builder ✓ Microsoft · Official | 50 · Use with care | ★ 194k | 11d ago | MIT |
| Tool Rename Compatibility Check ✓ Microsoft · Official | 63 · Recommended | ★ 194k | 11d ago | MIT |
How did FollowSkills review this skill?
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.
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.
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.
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.
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.
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.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →