菜单
Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
Stress-test solutions using the STRIKE framework. Systematically attack proposals to find weaknesses before deployment.
Exhaustive solution space exploration. Use when you need ALL viable options (not just the best), solution space is unknown, or you can't afford to miss alternatives.
Diagnostic reasoning for finding root causes. Generates multiple hypotheses, designs tests to eliminate each, and converges on the true cause through evidence.
| name | skill-creator |
| description | Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead. |
| license | Complete terms in LICENSE.txt |
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
Metadata Quality: The name and description in YAML frontmatter determine when Claude will use the skill. Be specific about what the skill does and when to use it. Use the third-person (e.g. "This skill should be used when..." instead of "Use this skill when...").
scripts/)Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
scripts/rotate_pdf.py for PDF rotation tasksreferences/)Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specificationsassets/)Files not intended to be loaded into context, but rather used within the output Claude produces.
assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typographySkills use a three-level loading system to manage context efficiently:
*Unlimited because scripts can be executed without reading into context window.
Skills should be created in the standard Claude Code skills directory:
~/.claude/skills/
This is the default location where Claude Code loads skills at startup. Skills placed here are automatically discovered and loaded based on their metadata.
Directory structure:
~/.claude/skills/
├── skill-name-1/
│ └── SKILL.md
├── skill-name-2/
│ ├── SKILL.md
│ └── scripts/
└── skill-name-3/
├── SKILL.md
├── references/
└── assets/
When creating skills, avoid these common mistakes:
Incorrect: Creating skills in ~/.claude/plugins/ or other non-standard directories
Correct: Always use ~/.claude/skills/ as the base directory
Incorrect: Creating skills as direct .md files like ~/.claude/skills/my-skill.md
Correct: Create a directory with uppercase SKILL.md inside: ~/.claude/skills/my-skill/SKILL.md
Incorrect: Adding custom fields to YAML frontmatter
---
name: my-skill
description: Does things
commands: ["command1", "command2"] # ❌ Invalid custom field
version: 1.0 # ❌ Invalid custom field
---
Correct: Only use required fields (name and description)
---
name: my-skill
description: Does things when users need to do X
---
Incorrect: Using skill.md, README.md, or index.md
Correct: Always use uppercase SKILL.md (case-sensitive)
Incorrect: Vague descriptions that don't specify when to use the skill
description: Helps with legal documents
Correct: Specific descriptions with trigger scenarios
description: Validates legal citations against Finlex (Finnish law) and EUR-Lex (EU law) databases to prevent hallucination. Use when generating legal documents with statute citations.
For the authoritative specification and examples, refer to Anthropic's official documentation:
These resources provide:
To create a skill, follow the "Skill Creation Process" in order, skipping steps only if there is a clear reason why they are not applicable.
Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
For example, when building an image-editor skill, relevant questions include:
To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
Conclude this step when there is a clear sense of the functionality the skill should support.
To turn concrete examples into an effective skill, analyze each example by:
Example: When building a pdf-editor skill to handle queries like "Help me rotate this PDF," the analysis shows:
scripts/rotate_pdf.py script would be helpful to store in the skillExample: When designing a frontend-webapp-builder skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skillExample: When building a big-query skill to handle queries like "How many users have logged in today?" the analysis shows:
references/schema.md file documenting the table schemas would be helpful to store in the skillTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
When creating a new skill from scratch, always run the init_skill.py script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
Usage:
scripts/init_skill.py <skill-name> --path <output-directory>
The script:
scripts/, references/, and assets/After initialization, customize or remove the generated SKILL.md and example files as needed.
When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Focus on including information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.
Also, delete any example files and directories not needed for the skill. The initialization script creates example files in scripts/, references/, and assets/ to demonstrate structure, but most skills won't need all of them.
Writing Style: Write the entire skill using imperative/infinitive form (verb-first instructions), not second person. Use objective, instructional language (e.g., "To accomplish X, do Y" rather than "You should do X" or "If you need to do X"). This maintains consistency and clarity for AI consumption.
To complete SKILL.md, answer the following questions:
Once the skill is ready, it should be packaged into a distributable zip file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:
scripts/package_skill.py <path/to/skill-folder>
Optional output directory specification:
scripts/package_skill.py <path/to/skill-folder> ./dist
The packaging script will:
Validate the skill automatically, checking:
Package the skill if validation passes, creating a zip file named after the skill (e.g., my-skill.zip) that includes all files and maintains the proper directory structure for distribution.
If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
Iteration workflow: