All skills
anthropics avatar

/skill-creator

@bb4a2b3

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use this Skill: https://skilld.dev/gh/anthropics/financial-services-plugins/skill-creator

This session only. Nothing lands on disk.

referencesoutput-patterns.md

≈454 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Output Patterns

Use these patterns when skills need to produce consistent, high-quality output.

Template Pattern

Provide templates for output format. Match the level of strictness to your needs.

For strict requirements (like API responses or data formats):

## Report structure

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary
[One-paragraph overview of key findings]

## Key findings
- Finding 1 with supporting data
- Finding 2 with supporting data
- Finding 3 with supporting data

## Recommendations
1. Specific actionable recommendation
2. Specific actionable recommendation

For flexible guidance (when adaptation is useful):

## Report structure

Here is a sensible default format, but use your best judgment:

# [Analysis Title]

## Executive summary
[Overview]

## Key findings
[Adapt sections based on what you discover]

## Recommendations
[Tailor to the specific context]

Adjust sections as needed for the specific analysis type.

Examples Pattern

For skills where output quality depends on seeing examples, provide input/output pairs:

## Commit message format

Generate commit messages following these examples:

**Example 1:**
Input: Added user authentication with JWT tokens
Output:

feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware


**Example 2:**
Input: Fixed bug where dates displayed incorrectly in reports
Output:

fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation


Follow this style: type(scope): brief description, then detailed explanation.

Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.

Source: SKILL.md on GitHub

No alerts16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a framework and utility scripts for scaffolding and packaging other AI agent skills. The included scripts perform standard local filesystem operations for project initialization and validation, and no security risks were identified.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    7 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at bb4a2b3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 5 months ago
  • Documentation
  • skill-creation
  • workflow
  • claude
  • ai-agents
  • prompt-engineering
  • context-management

README badge

README badge for anthropics/financial-services-plugins

This skill provides guidance for structuring and writing SKILL.md files—the instruction templates that AI agents load to extend their capabilities with specialized knowledge, workflows, and tool integrations. It covers skill anatomy (required SKILL.md frontmatter and body, optional bundled scripts/references/assets), context management principles (conciseness, progressive disclosure, appropriate degrees of freedom), and a five-step creation process (understand use cases, plan reusable contents, initialize, implement, package). Use this skill when designing a new skill or refactoring an existing one to meet the skilld.dev standard.

Generated from the current SKILL.md.

What is the difference between a skill and a plugin or package?
A skill is a modular instruction file (SKILL.md) with optional bundled scripts, references, and assets that extend Claude's capabilities on-demand. It is not a package, plugin, or extension—it is an onboarding guide that transforms Claude into a specialized agent for specific domains or tasks.
How much content should I put in SKILL.md versus bundled reference files?
Keep SKILL.md under 500 lines with only essential procedural instructions and workflow guidance. Move detailed reference material, schemas, examples, and variant-specific details into separate reference files and link them from SKILL.md so Claude loads them only when needed.
When should I create a script versus putting instructions in SKILL.md?
Create a script when the same code is rewritten repeatedly or deterministic reliability is critical. Use text-based SKILL.md instructions when multiple approaches are valid and decisions depend on context.
What files should I avoid including in a skill?
Do not include auxiliary documentation like README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, or other files not directly needed for the skill to function. Keep only SKILL.md and bundled resources (scripts, references, assets) that support the skill's core functionality.
How do I organize a skill that supports multiple frameworks or domains?
Create separate reference files organized by framework or domain (e.g., references/aws.md, references/gcp.md) and link them from SKILL.md. Claude will only load the relevant reference file when the user specifies their choice, avoiding unnecessary context bloat.

Generated from the current SKILL.md. These answers refresh after source changes.