create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
npx skills add majiayu000/claude-skill-registry --skill create-meta-prompts --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.
What it does
The skill generates prompts for Claude-to-Claude pipelines that operate across research, plan, and implement stages. It structures outputs as XMLMetadata-enabled artifacts and keeps a SUMMARY.md for quick human scanning. Each prompt gets its own folder under .prompts/ with a dedicated completed subfolder after execution, enabling provenance tracking and chain detection.
How it works
- Intake and adaptive analysis determine purpose (Do, Plan, Research, Refine) and topic. If context is missing, it asks targeted questions; if present, it infers purpose from keywords.
- It scans existing prompts to detect references and potential dependencies, then proposes a chain/ordering. It loads purpose-specific prompt patterns and intelligence rules.
- It builds a prompt package containing:
- Objective, Context, Requirements, Output specification, Metadata requirements
- SUMMARY.md requirement with specific sections
- For Research/Plan outputs: include <confidence>, <dependencies>, <open_questions>, <assumptions>
- It creates a folder .prompts/{number}-{topic}-{purpose}/ with a completed/ subfolder, and writes the prompt to .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md; the prompt instructs the agent to generate output into .prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md
- After execution, it archives the prompt and presents a decision tree for next steps, and outputs a SUMMARY.md inside the prompt folder.
When to use it
Use when building prompts that will produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement). It is intended to create organized, multi-stage prompt pipelines with clear provenance.
What it can touch
- Tool: claude-code (declared)
- File system: creates and writes under .prompts/ and its subfolders, including SUMMARY.md and the various .md prompt outputs. It archives completed prompts into completed/.
Caveats
- All sections and outputs are constrained to what the skill explicitly specifies, including XML-like metadata for research/plan outputs when applicable.
- It relies on the existence of .prompts structure and unique numbering to avoid conflicts; if a conflict is detected, the workflow includes prompts to resolve it.
<objective> Create prompts optimized for Claude-to-Claude communication in multi-stage workflows. Outputs are structured with XML and metadata for efficient parsing by subsequent prompts. Every execution produces a `SUMMARY.md` for quick human scanning without reading full outputs. Each prompt gets its own folder in `.prompts/` with its output artifacts, enabling clear provenance and chain detection. </objective> <quick_start> <workflow> 1. **Intake**: Determine purpose (Do/Plan/Research/Refine), gather requirements 2. **Chain detection**: Check for existing research/plan files to reference 3. **Generate**: Create prompt using purpose-specific patterns 4. **Save**: Create folder in `.prompts/{number}-{topic}-{purpose}/` 5. **Present**: Show decision tree for running 6. **Execute**: Run prompt(s) with dependency-aware execution engine 7. **Summarize**: Create SUMMARY.md for human scanning </workflow> <folder_structure> ``` .prompts/ ├── 001-auth-research/ │ ├── completed/ │ │ └── 001-auth-research.md # Prompt (archived after run) │ ├── auth-research.md # Full output (XML for Claude) │ └── SUMMARY.md # Executive summary (markdown for human) ├── 002-auth-plan/ │ ├── completed/ │ │ └──
mv .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md \What does the create-meta-prompts skill do?
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill create-meta-prompts --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.