personalagentproxy/proxy/skill-authoring

Claude Code and agent skill by personalagentproxy/proxy

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Create and improve Claude Code skills following Anthropic's best practices. Use when authoring new skills, refactoring existing skills, or reviewing skill quality.

Install

npx vskill@latest install personalagentproxy/proxy/skill-authoring

SKILL.md

Skill Authoring

Quick Reference

Structure:

skill-name/
└── SKILL.md # Main file (under 500 lines)
├── frontmatter # name + description (required)
└── body # Instructions, examples, references

Frontmatter:

yaml
---
name: lowercase-with-hyphens # max 64 chars, no "anthropic"/"claude"
description: What it does and when to use it. Written in third person.
---

Core Principles

Be Concise

Claude is smart. Only add context Claude doesn't already have.

Good (~50 tokens):

`markdown
Use pdfplumber for text extraction:

import pdfplumber with pdfplumber.open("file.pdf") as pdf: text = pdf.pages[0].extract_text()

Bad (~150 tokens): Explaining what PDFs are, why pdfplumber exists, etc.

Set Appropriate Freedom
Freedom LevelWhen to UseExample
High (text)Multiple valid approachesCode review guidelines
Medium (pseudocode)Preferred pattern existsReport templates
Low (exact script)Fragile operationsDatabase migrations
Naming

Use gerund form (verb + -ing):

  • processing-pdfs
  • analyzing-data
  • writing-documentation

Avoid: helper, utils, tools, vague names

Descriptions

Always third person. Include what AND when:

yaml
# Good
description: Extracts text from PDFs and fills forms. Use when working with PDF files or document extraction.
# Bad
description: Helps with documents

Progressive Disclosure

Keep SKILL.md as overview, link to detail files:

markdown
## Quick start
[Core instructions here]
## Advanced
**Form filling**: See [FORMS.md](FORMS.md)
**API reference**: See [REFERENCE.md](REFERENCE.md)

Rules:

  • Keep references one level deep (no nested chains)
  • Add table of contents to files over 100 lines
  • Use forward slashes in paths (reference/guide.md)

Patterns

Template Pattern
markdown
## Output format
Use this structure:
[template here]
Examples Pattern
markdown
## Examples
**Input**: Added authentication
**Output**: `feat(auth): implement JWT authentication`
Workflow Pattern
markdown
## Workflow
1.Analyze input
2.Validate results
3.If errors, fix and return to step 2
4.Generate output

Anti-Patterns

  • Offering too many library choices (pick one default)
  • Time-sensitive info ("before August 2025...")
  • Inconsistent terminology
  • Windows-style paths (docs\file.md)
  • Deep reference chains (A → B → C)
  • Over-explaining concepts Claude knows

Checklist

Before finalizing:

  • [ ] Description includes what AND when
  • [ ] SKILL.md under 500 lines
  • [ ] Third person throughout
  • [ ] Consistent terminology
  • [ ] No time-sensitive content
  • [ ] References one level deep
  • [ ] Forward slashes in paths

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/personalagentproxy/proxy/skill-authoring/badge)](https://verified-skill.com/skills/personalagentproxy/proxy/skill-authoring)

Something wrong with this skill or its page? Tell us.