effective-prompting
Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing Claude interactions, or troubleshooting why Claude misunderstood a request. Covers @ mentions, thinking keywords, task framing, and iterative refinement.
npx skills add majiayu000/claude-skill-registry --skill effective-prompting-hgeldenhuys-claude-code-sdk --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Effective Prompting for Claude Code Write prompts that Claude Code understands and executes correctly the first time. ## Quick Reference | Technique | When to Use | Example | |-----------|-------------|---------| | @ mentions | Include specific context | `@src/api/users.ts` | | ultrathink | Complex reasoning tasks | "ultrathink about the architecture" | | Success criteria | Clear deliverables | "Done when tests pass" | | Task decomposition | Multi-step work | "First X, then Y, finally Z" | | /compact | Long sessions | Summarize and continue | ## @ Mentions (Context Injection) @ mentions pull specific context into your prompt. Use them liberally. ### Types | Mention | Purpose | Example | |---------|---------|---------| | `@file` | Single file | `@src/utils/auth.ts` | | `@folder` | Directory contents | `@src/api/` | | `@url` | Web content | `@https://docs.example.com/api` | | `@git` | Git context | `@git:diff`, `@git:log` | ### File Patterns ``` @src/api/*.ts # All TS files in api folder @src/**/*.test.ts # All test files recursively @package.json # Specific file @src/components/ # Entire folder ``` ### Best Practices - **Be specific**: `@src/api/users.ts` > `@src/` - **Include tes
- Quick Reference
- @ Mentions (Context Injection)
- Types
- File Patterns
- Best Practices
- Thinking Keywords
- When to Use Extended Thinking
- Example
- Task Framing
- The WHAT-WHY-HOW Pattern
- Success Criteria
- Constraints Pattern
- Multi-Step Tasks
- Sequential Steps
What does the effective-prompting skill do?
Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing Claude interactions, or troubleshooting why Claude misunderstood a request. Covers @ mentions, thinking keywords, task framing, and iterative refinement.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill effective-prompting-hgeldenhuys-claude-code-sdk --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.