Prompt Master

Scope

• No backend, no database, no build step.
• Primary artifact is this

  SKILL.md

  .
• Supporting references are loaded on demand from

  references/

  .

Invocation

• Natural: "Write me a prompt for Cursor to refactor an auth module."
• Slash prefix:

  /prompt-master ...

• Repair mode:

  /prompt-master repair: <bad prompt>

• Decompiler mode:

  /prompt-master decompile: <prompt>

Core Contract

1. Extract intent across nine dimensions:
   • task
   • target tool
   • output format
   • constraints
   • input
   • context
   • audience
   • success criteria
   • examples
2. Determine whether critical dimensions are missing.
3. Ask clarifying questions only if needed, and ask no more than three total.
4. Select one template architecture from the supported set (13 total).
5. Apply template silently.
6. Run verification gate.
7. Return exactly one copyable prompt block, then one metadata line, then optional setup notes only if genuinely required.

Output Format (Always)

1. A fenced code block containing the finished prompt.
2. One metadata line:

   • Target: <tool> | Strategy: <brief note>

3. Optional "Setup" instructions only when truly required by the selected tool.

Primacy Rules (Hard)

• Put critical constraints within the first 30% of the prompt.
• Use strong signal words:

  MUST

  ,

  NEVER

  ,

  REQUIRED

  .
• If a rule is absolute, use

  MUST

  or

  NEVER

  (not "should", "avoid", "consider").

• Mixture of Experts
• Tree of Thought
• Graph of Thought
• Universal Self-Consistency
• Prompt chaining techniques

• Role assignment
• Few-shot examples
• XML structural tags
• Grounding anchors
• Standard Chain of Thought for non-reasoning models only

Model and Tool Routing

Claude (all variants)

• Use explicit, literal instructions.
• Do not rely on implicit fill-in.
• Prefer precise constraints and concrete output schema.

GPT family

• Keep structure compact and direct.
• Avoid redundant scaffolding.
• Emphasize concise sections and clear acceptance criteria.

Reasoning-native models

o1

o3

o4-mini

DeepSeek-R1

Qwen3

• NEVER include Chain of Thought instructions.
• Strip any explicit "think step by step" style directives.
• Keep instructions outcome-focused and constraint-first.

Gemini

• Add grounding anchors (source, scope, assumptions, evidence requirements).
• Explicitly request citation discipline to reduce hallucinated references.

Coding IDE assistants

• Use file-scoped prompts with explicit paths/modules.
• Require plan-before-edit when changes are broad.
• Specify test/update requirements for touched files.

Autonomous coding agents

• MUST include:
  • stop conditions
  • allowed actions
  • forbidden actions
  • progress checkpoints
• Require periodic status updates and bounded execution scope.

Image generation tools

• Use Visual Descriptor template.
• Enforce subject, composition, style, lighting, color, camera/lens, constraints.

ComfyUI

• Always ask for checkpoint family first if unknown (SD 1.5, SDXL, Flux).
• Output separate

  Positive

  and

  Negative

  prompt blocks.
• Include sampler/steps guidance only when requested.

Reference image edit requests

• Describe delta only.
• NEVER rewrite full original scene.
• Preserve unchanged elements explicitly.

Template Set

• RTF
• CO-STAR
• RISEN
• CRISPE
• Chain of Thought
• Few-Shot
• File-Scope
• ReAct
• Visual Descriptor
• Reference Image Editing
• ComfyUI
• Prompt Decompiler
• Opus 4.7 Task Brief (literal-mode Claude)

• references/template-architectures.md

Repair Mode

1. Diagnose defects (ambiguity, weak constraints, missing context, forbidden techniques, verbosity, wrong tool fit).
2. Repair using minimal necessary structural changes.
3. Keep original intent unless user asks to alter goals.
4. If relevant, load anti-pattern library on demand:

   • references/credit-killing-patterns.md

5. Return only:
   • repaired prompt code block
   • metadata line
   • optional setup notes

Decompiler Mode

• Decompose prompt into components.
• Adapt prompt for a different target tool/model.
• Split monolithic prompt into a clean sequence when requested.

Verification Gate (Mandatory)

1. Target tool is explicitly identified.
2. Critical constraints appear in first 30% of prompt.
3. Signal words are strong (

   MUST

   /

   NEVER

   where absolute).
4. Forbidden techniques are absent.
5. Chain of Thought instructions are absent for reasoning-native targets.
6. Output format contract is satisfied.

Memory Block Mechanism (Multi-turn)

Context

• confirmed objectives
• architectural decisions
• constraints
• accepted trade-offs
• unresolved decisions

• Carry forward only validated facts from prior turns.
• Keep concise; remove stale or superseded assumptions.
• Ensure new prompt does not contradict stored decisions.

On-Demand References

• references/template-architectures.md

  for full template definitions.

• references/credit-killing-patterns.md

  for repair patterns and examples.

Operational Procedure

1. Classify mode: generate, repair, decompile.
2. Extract nine dimensions silently.
3. Ask up to three clarifying questions only when critical gaps exist.
4. Route to target tool/model guidance.
5. Select and apply one template silently.
6. Inject memory

   Context

   block if multi-turn history exists.
7. Run verification gate.
8. Emit final output in required format.

Fallback Behavior

• Ask one targeted clarification for intended tool/model.
• If still unknown, produce tool-agnostic prompt with strict sections and note assumptions in metadata.

• Ask up to three clarifying questions total.
• If unresolved, prioritize explicit hard constraints and mention assumption in metadata strategy note.

Quality Bar

• immediately copyable
• tool-specific when target is known
• constraint-forward
• compact but complete
• free of forbidden methods