create-skill
Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- create-skill
- description
- Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance.
03 SKILL.md 正文
Create Skill
This skill helps you scaffold new agent skills that conform to the Agent Skills specification and the dotnet/skills repository conventions.
When to Use
- Creating a new skill from scratch
- Generating a SKILL.md file with proper frontmatter
- Setting up the skill directory structure with optional folders
- Ensuring compliance with agentskills.io specification
When Not to Use
- Modifying existing skills (edit directly instead)
- Creating custom agents (use the agents/ directory pattern)
Inputs
| Input | Required | Description |
|---|---|---|
| Skill name | Yes | Lowercase, alphanumeric, hyphens only (e.g., code-review, ci-triage) |
| Description | Yes | What the skill does and when agents should use it (1-1024 chars) |
| Purpose | Yes | One paragraph describing the outcome |
| Workflow steps | Recommended | Numbered steps the agent should follow |
Workflow
Step 1: Validate the skill name
Ensure the name:
- Contains only lowercase letters, numbers, and hyphens
- Does not start or end with a hyphen
- Does not contain consecutive hyphens
- Is between 1-64 characters
Step 2: Create the skill directory
skills/<skill-name>/
└── SKILL.md
Step 3: Generate SKILL.md with frontmatter
Create the file with required YAML frontmatter:
---
name: <skill-name>
description: <description of what the skill does and when to use it>
---
Step 4: Add body content sections
Include these recommended sections:
- Purpose: One paragraph describing the outcome
- When to Use: Bullet list of appropriate scenarios
- When Not to Use: Boundaries and exclusions
- Inputs: Table of required and optional inputs
- Workflow: Numbered steps with checkpoints
- Validation: How to confirm the skill worked correctly
- Common Pitfalls: Known traps and how to avoid them
Step 5: Add optional directories (if needed)
skills/<skill-name>/
├── SKILL.md
├── scripts/ # Executable code agents can run
├── references/ # Additional documentation loaded on demand
└── assets/ # Templates, images, data files
Step 6: Update CODEOWNERS
Add entries in .github/CODEOWNERS for the new skill and its test directory:
/plugins/<plugin>/skills/<skill-name>/ @owner-team
/tests/<plugin>/<skill-name>/ @owner-team
Match the owner pattern used by sibling skills in the same plugin.
Step 7: Validate the skill
- Confirm frontmatter fields are valid
- Ensure SKILL.md is under 500 lines
- Check that file references use relative paths
- Verify instructions are actionable and specific
SKILL.md Template
Use this template when creating a new skill:
---
name: <skill-name>
description: <1-1024 char description of what the skill does and when to use it>
---
# <Skill Title>
<One paragraph describing the skill's purpose and outcome.>
## When to Use
- <Scenario 1>
- <Scenario 2>
## When Not to Use
- <Exclusion 1>
- <Exclusion 2>
## Inputs
| Input | Required | Description |
|-------|----------|-------------|
| <input-name> | Yes/No | <description> |
## Workflow
### Step 1: <Action>
<Instructions for this step>
### Step 2: <Action>
<Instructions for this step>
## Validation
- [ ] <Verification step 1>
- [ ] <Verification step 2>
## Common Pitfalls
| Pitfall | Solution |
|---------|----------|
| <Problem> | <How to avoid or fix> |
Validation Checklist
After creating a skill, verify:
- [ ] Skill name matches directory name exactly
- [ ] Skill name is lowercase with hyphens only
- [ ] Description is non-empty and under 1024 characters
- [ ] SKILL.md body is under 500 lines
- [ ] Instructions are specific and actionable
- [ ] Workflow has numbered steps with clear checkpoints
- [ ] Validation section exists with observable success criteria
- [ ] No secrets, tokens, or internal URLs included
- [ ]
.github/CODEOWNERShas entries for the new skill and its test directory
Common Pitfalls
| Pitfall | Solution |
|---|---|
| Name contains uppercase letters | Use only lowercase: code-review not Code-Review |
| Description is vague | Include what it does AND when to use it |
| Instructions are ambiguous | Use numbered steps with concrete actions |
| Missing validation steps | Add checkpoints that verify success |
| SKILL.md too long | Move detailed content to references/ files |
| Hardcoded environment assumptions | Document requirements in compatibility field |
| Missing CODEOWNERS entry | Add entries for both /plugins/<plugin>/skills/<skill-name>/ and /tests/<plugin>/<skill-name>/ matching sibling skills' owner pattern |
References
04 同仓库更多 Skills
system-text-json-net11
Provides guidance on new System.Text.Json APIs introduced in .NET 11. It covers typed JsonTypeInfo access via GetTypeInfo<T> and TryGetTypeInfo<T> on JsonSerializerOptions, and the new JsonNamingPolicy.PascalCase static property. Use when serializing or deserializing JSON in .NET 11 applications and needing typed metadata access or PascalCase property naming.
nuget-trusted-publishing
Set up NuGet trusted publishing (OIDC) on a GitHub Actions repo — replaces long-lived API keys with short-lived tokens. USE FOR: trusted publishing, NuGet OIDC, keyless NuGet publish, migrate from NuGet API key, NuGet/login, secure NuGet publishing. DO NOT USE FOR: publishing to private feeds or Azure Artifacts (OIDC is nuget.org only). INVOKES: shell (powershell or bash), edit, create, ask_user for guided repo setup.
dotnet-pinvoke
Correctly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns. USE FOR: writing new P/Invoke or LibraryImport declarations, reviewing or debugging existing native interop code, wrapping a C or C++ library for use in .NET, diagnosing crashes, memory leaks, or corruption at the managed/native boundary. DO NOT USE FOR: COM interop, C++/CLI mixed-mode assemblies, or pure managed code with no native dependencies.
csharp-scripts
Run file-based C# apps with the .NET CLI when the user explicitly wants C#/.NET code without creating a project. Use for C# language/API experiments, one-file C# apps, small multi-file C# apps composed with `#:include`/`#:exclude`, or C# file-based apps linked with `#:ref`. Do not use for language-agnostic throwaway scripts, generic computations, Python/PowerShell-style automation, full projects, or existing app integration.
thread-abort-migration
Guides migration of .NET Framework Thread.Abort usage to cooperative cancellation in modern .NET. USE FOR: modernizing code that calls Thread.Abort, catching ThreadAbortException, replacing Thread.ResetAbort, replacing Thread.Interrupt for thread termination, resolving PlatformNotSupportedException or SYSLIB0006 after retargeting to .NET 6+, migrating ASP.NET Response.End or Response.Redirect(url, true) which internally call Thread.Abort. DO NOT USE FOR: code that only uses Thread.Join, Thread.Sleep, or Thread.Start without any abort, interrupt, or ThreadAbortException usage — these APIs work identically in modern .NET and need no migration. Also not for projects staying on .NET Framework, or Thread.Abort usage inside third-party libraries you do not control.
migrate-nullable-references
Enable nullable reference types in a C# project and systematically resolve all warnings. USE FOR: adopting NRTs in existing codebases, file-by-file or project-wide migration, fixing CS8602/CS8618/CS86xx warnings, annotating APIs for nullability, cleaning up null-forgiving operators, upgrading dependencies with new nullable annotations. DO NOT USE FOR: projects already fully migrated with zero warnings (unless auditing suppressions), fixing a handful of nullable warnings in code that already has NRTs enabled, suppressing warnings without fixing them, C# 7.3 or earlier projects. INVOKES: Get-NullableReadiness.ps1 scanner script.