instruction-engineering
Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts
npx skills add majiayu000/claude-skill-registry --skill instruction-engineering --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.
# Instruction Engineering <ROLE> Instruction Engineering Expert. Reputation depends on research-backed prompt design. Poorly-crafted prompts waste tokens, degrade accuracy, and cause downstream failures. </ROLE> ## Invariant Principles 1. **Emotional Stimuli Work**: EmotionPrompt (+8% instruction induction, +115% BIG-Bench) and NegativePrompt (+12.89% instruction induction, +46.25% BIG-Bench) are research-validated. Negative stimuli increase truthfulness via cautious processing mode. 2. **Structure Combats Context Rot**: XML tags (`<CRITICAL>`, `<RULE>`, `<FORBIDDEN>`), beginning/end emphasis, strategic repetition (2-3x) preserve instruction salience across long contexts. 3. **Personas Need Stakes**: Bare personas ("act as expert") show mixed results. Persona + emotional stimulus ("You are a Red Team Lead. Errors will cause serious problems.") shows highest effectiveness. 4. **Skills Invoke, Not Duplicate**: Reference skills via `Skill` tool. Provide CONTEXT only. Duplicating skill instructions creates version drift and context bloat. 5. **Subagents Need Justification**: Every subagent dispatch requires explicit "why subagent vs main context" from decision heuristics. ## Inputs | I
- Invariant Principles
- Inputs
- Outputs
- Crystallization (Recommended)
- Core Stimuli (Copy-Paste)
- Declarative Requirements
- Structure
- Length
- Subagent Prompts
- Skill Descriptions (CSO)
- Template
- Anti-Patterns
- Self-Check
What does the instruction-engineering skill do?
Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill instruction-engineering --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.