system-prompts
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions. Covers tag hierarchy, structural templates, high-impact interventions, anti-patterns.
npx skills add majiayu000/claude-skill-registry --skill system-prompts-az9713-oh-my-pi --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.
# System Prompt Engineering Empirically-validated techniques + consistent XML structure. Every recommendation backed by benchmarks or production data. <critical> ## High-Impact Interventions (+15-30% measured improvement) 1. **Persistence**: "Keep going until fully resolved" — prevents premature termination 2. **Tool verification**: "Use tools to verify; do not guess" — reduces hallucination 3. **Planning**: "Plan approach before acting" — improves complex task success 4. **Context positioning**: Critical instructions at START and END — middle content degrades 20%+ 5. **Urgency framing**: "This matters" / "Get this right" — 8-115% improvement (EmotionPrompt) 6. **Edit format**: SEARCH/REPLACE beats line-numbers 3X on code generation **Minimal prompting wins.** Every instruction must justify its token cost. </critical> --- ## Tag Hierarchy Tags encode enforcement level. Use consistently throughout: | Tag | Enforcement | When to Use | | --------------- | ------------- | ---------------------------------------------------- | | `<critical>` | Inviolable | Safety constraints, must-follow rules, repeat at END | | `<prohibited>` | Forbidden | Actions that cause harm, never acceptable | |
- High-Impact Interventions (+15-30% measured improvement)
- Tag Hierarchy
- Standard Tags
- Structure Tags
- Special Tags
- Example Tags
- Structural Templates
- Tool Documentation
- Agent Definition
- System Prompt (Main Agent)
- Writing Style
- Voice
- Positive Framing
- Specificity
What does the system-prompts skill do?
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions. Covers tag hierarchy, structural templates, high-impact interventions, anti-patterns.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill system-prompts-az9713-oh-my-pi --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.