ggprompts/my-plugins/prompt-craft
Claude Code and agent skill by ggprompts/my-plugins
- community
Checking that the SKILL.md file is still in the repository.
Craft effective worker prompts from backlog issues using Claude 4 best practices. Use when preparing issues for workers, writing prompts, or optimizing prompt quality. Trigger with "craft prompt", "write prompt", "prepare issue", "make ready".
Install
npx vskill@latest install ggprompts/my-plugins/prompt-craftSKILL.md
Prompt Craft - Claude 4 Best Practices
Craft effective prompts for Claude workers using proven patterns.
Core Principles
1. Be Explicit
Claude 4.x follows instructions precisely. Use action verbs.
| Less Effective | More Effective | |
|---|---|---|
| "Can you suggest improvements?" | "Update the function to improve performance." | |
| "Look at this code" | "Find and fix the null check bug" | |
| "Help with testing" | "Write unit tests for the auth module" |
2. Add Context/Motivation
Explain WHY, not just WHAT. Claude generalizes from explanations.
| Less Effective | More Effective | |
|---|---|---|
| "NEVER use ellipses" | "Never use ellipses since the TTS engine won't pronounce them correctly." | |
| "Always add error handling" | "Add error handling so users see helpful messages instead of stack traces." |
3. Natural Skill Triggers
Use natural language, avoid aggressive markers.
| Avoid | Use | |
|---|---|---|
| "CRITICAL: You MUST use this tool when..." | "Use the X skill for Y." | |
| "ALWAYS: This is REQUIRED" | "Use this approach when..." | |
| "IMPORTANT!!!: Never forget to..." | "Remember to..." |
4. Positive Framing
Tell Claude what TO do, not just what to avoid.
| Less Effective | More Effective | |
|---|---|---|
| "Don't write long functions" | "Keep functions under 20 lines" | |
| "Avoid complex logic" | "Use simple, readable patterns" |
Prompt Structure
Skill Matching
Match skills based on content:
| Content Signal | Suggested Skill | |
|---|---|---|
.tsx, .jsx, React | frontend-development | |
| terminal, xterm, resize | xterm-js | |
| auth, login, session | better-auth | |
| database, SQL, query | databases | |
| API, REST, endpoint | backend-development | |
| CSS, styling, theme | ui-styling | |
| docs, markdown | docs-seeker |
Subagent Hints
Claude 4.5 naturally delegates. Add hints when beneficial:
Parallelization Hints
For tasks with independent subtasks:
Complexity Guidelines
| Prompt Length | When to Use | |
|---|---|---|
| Short (3-5 lines) | Simple bug fixes, single-file changes | |
| Medium (10-15 lines) | Feature work, multi-file changes | |
| Long (20+ lines) | Complex features, architectural changes |
Rule: If you need more than 20 lines, the issue might need breaking down.
Anti-Patterns
Avoid these common mistakes:
- Overloading: Too many skills, too many files, too much context
- Vague tasks: "Make it better" without specific criteria
- All caps: CRITICAL, IMPORTANT, MUST - creates anxiety, not clarity
- Negative framing: Lists of don'ts without corresponding dos
- No completion criteria: Worker doesn't know when they're done
References
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
- SKILL.md in the repositoryCheckingplugins/tools/prompt-writer/skills/prompt-craft/SKILL.md
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
[](https://verified-skill.com/skills/ggprompts/my-plugins/prompt-craft)