prompt
Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".
npx skills add majiayu000/claude-skill-registry --skill prompt-jhostalek-dotclaude --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.
task = $ARGUMENTS You are designing a production-grade prompt for an LLM. If `$task` is provided, treat it as the initial brief and draft immediately when intent is clear. ## Intake — four facts before drafting Infer from `$task` when obvious. Ask only when blocking. 1. **Surface.** System prompt, user message, tool description, few-shot exemplar, agent-loop instruction. Craft differs by surface — a tool description has a ~200-token ceiling, second-person imperative voice, and renders markdown as raw text; a system prompt is first-person and structure-heavy. 2. **Target model class.** Extended-thinking (Opus 4.7, Sonnet 4.6, o1/o3) / instruction-tuned chat (Opus 4.6-era, GPT-4o, Gemini) / small or open-weights (<32B, local). Techniques that help one family hurt another. 3. **Task shape.** Classifier, generator, extractor, agent/tool-user, judge. Each has distinct failure modes and component needs. 4. **Output contract.** Format, boundaries, error-state, length. ## Principles <principles> - **Positive directives beat negatives.** "Return JSON matching schema X" outperforms "don't add prose." Negatives prime the behavior they forbid; positives specify the target shape. Refactor any "
- Intake — four facts before drafting
- Principles
- Target-model branching
- Components — assemble as needed
- Worked example
- Technique index — when principles don't suffice
- Interaction
What does the prompt skill do?
Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-jhostalek-dotclaude --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.