npx claudepluginhub it-bens/claude-code-plugins --plugin prompt-engineeringWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Evaluates proposed changes to LLM-targeted content (skills, agents, commands) and guides toward corrections over additions. MUST invoke when editing SKILL.md files, modifying agent markdown in agents/, updating command markdown in commands/, adding new sections or instructions, expanding skill content, user says "is this too long", "content bloat", "should I add this", or improving/enhancing skills.
This skill uses the workspace's default tool permissions.
Content Editing for LLM
Enforce the principle: prefer correcting existing content over adding new instructions.
Core Principle
Undesired behavior stems from incorrect information, not missing information. Adding more instructions increases complexity without addressing root causes. Shorter is better.
Decision Framework
Before adding new content, ask:
- Does existing content already address this behavior incorrectly?
- If YES: Correct the existing content instead of adding
- Can the issue be fixed by clarifying or rewording current instructions?
- If YES: Modify existing wording instead of adding
- Would adding content create redundancy or conflict with existing guidance?
- If YES: Consolidate or remove conflicting content first
Only add new content when ALL conditions are met:
- The capability genuinely doesn't exist in current instructions
- Existing content cannot reasonably be extended to cover the case
- The addition addresses a distinct, orthogonal concern
When Addition is Warranted
If adding is truly necessary:
- Consider progressive disclosure - move detailed content to
references/ - Consider agent delegation - split responsibilities into focused agents
- Keep additions orthogonal - distinct from existing content
Balance is key—additions are appropriate when they fill genuine gaps.
Similar Skills
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.