{
  "id": "page:docs-reference-repos-nidhinjs-prompt-master-research",
  "_kind": "Page",
  "_file": "wiki/docs/reference-repos/nidhinjs/prompt-master/research.md",
  "_cluster": "wiki",
  "attributes": {
    "nodeKind": "Page",
    "sourcePath": "docs/reference-repos/nidhinjs/prompt-master/research.md",
    "sourceKind": "repo-docs",
    "title": "nidhinjs/prompt-master",
    "displayName": "nidhinjs/prompt-master",
    "slug": "docs/reference-repos/nidhinjs/prompt-master/research",
    "articlePath": "wiki/docs/reference-repos/nidhinjs/prompt-master/research.md",
    "article": "\n# nidhinjs/prompt-master\n\n## Metadata\n- **Stars:** 4,992\n- **License:** MIT\n- **Last pushed:** 2026-03-31\n- **Description:** A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention.\n\n## Archetype: Specialization Process (prompt-engineering domain)\n\n## Structure\n- `SKILL.md` — Complete prompt engineering skill with tool-routing logic\n- `references/` — `templates.md` and `patterns.md` for category-specific templates\n\n## Extractable Value\n\n### As a Babysitter Process: `specializations/shared/prompt-engineering`\nThe SKILL.md contains a well-structured prompt engineering methodology:\n\n1. **9-dimension intent extraction framework** — Task, Target tool, Output format, Constraints, Input, Context, Audience, Success criteria, Examples. Each dimension marked as critical/conditional.\n2. **Tool-specific routing logic** — Detailed prompting guidance for 16+ tools/models:\n   - Claude (4.x), ChatGPT/GPT-5.x, o3/o4-mini reasoning models, Gemini 2.x/3, Qwen 2.5/3, Ollama, Llama/Mistral, DeepSeek-R1, MiniMax M2.7/M2.5, Claude Code, Antigravity, Cursor/Windsurf, Cline, GitHub Copilot\n3. **Anti-pattern enforcement** — Hard rules against techniques that cause fabrication in single-prompt execution (Mixture of Experts, Tree of Thought, Graph of Thought, etc.)\n4. **Model-specific constraints** — e.g., \"NEVER add CoT to reasoning-native models\", \"Claude Opus 4.x over-engineers by default\"\n\n### Key Differentiators\n- The tool-routing approach is unique — maps target tool to specific prompting strategy\n- Anti-fabrication rules are concrete and actionable (not vague \"be careful\" advice)\n- The 9-dimension intent extraction is a reusable analysis framework\n- Output format is strictly enforced: copyable prompt block + target + optimization note\n\n### Process Mapping\nWould map well to a babysitter process with:\n- Breakpoint for tool identification when ambiguous\n- Task for intent extraction across 9 dimensions\n- Tool-routing logic as branching in the process\n- Output formatting as final stage\n\n## Processes\n\n### 1. Advanced Prompt Engineering Methodology\n- **Source**: SKILL.md 9-dimension intent extraction framework and tool-routing logic\n- **Placement**: `specializations/shared/advanced-prompt-engineering.js`\n- **Description**: Comprehensive prompt engineering process: extract intent across 9 dimensions (task, target tool, output format, constraints, input, context, audience, success criteria, examples) → apply tool-specific routing logic for 16+ AI models → enforce anti-fabrication rules → generate optimized prompt with target tool and optimization notes.\n\n## Plugin Ideas\n\n- **Prompt Engineering Suite**: Babysitter marketplace plugin that provides advanced prompt engineering capabilities with tool-routing logic and anti-pattern enforcement for optimal AI model communication.\n\n## Library Mapping\n\n| Extractable Process | Library Status | Action | Existing Path | Target Placement |\n|-------------------|----------------|--------|---------------|------------------|\n| Advanced Prompt Engineering Methodology | NEW | 9-dimension intent extraction with tool-specific routing for 16+ AI models | - | specializations/shared/advanced-prompt-engineering.js |\n| Tool-Specific Routing Logic | NEW | Detailed prompting guidance mapped to specific AI tools and models | - | specializations/shared/tool-specific-routing-logic.js |\n| Anti-Fabrication Pattern Enforcement | NEW | Hard rules against techniques that cause hallucination in single-prompt execution | - | specializations/shared/anti-fabrication-pattern-enforcement.js |\n| Model-Specific Constraint Systems | NEW | Model-specific prompting constraints (e.g., no CoT for reasoning models, over-engineering prevention) | - | specializations/shared/model-specific-constraint-systems.js |\n\n## Plugin Marketplace Mapping\n\n| Plugin Idea | Marketplace Status | Action | Existing Plugin | Target Placement |\n|-------------|-------------------|--------|-----------------|------------------|\n| Prompt Engineering Suite | NEW | Advanced prompt engineering with tool routing, anti-pattern enforcement, and optimization | - | plugins/a5c/marketplace/plugins/prompt-engineering-suite/ |\n\n## Classification Rationale\nCross-domain (works for any AI tool/model), so fits in `specializations/shared/`. The tool-routing logic and anti-fabrication rules are unique contributions not found in the current process library.\n",
    "documents": []
  },
  "outgoingEdges": [],
  "incomingEdges": [
    {
      "from": "page:docs-reference-repos",
      "to": "page:docs-reference-repos-nidhinjs-prompt-master-research",
      "kind": "contains_page"
    }
  ]
}