Promptify Skill

Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelli…

tolibear

@tolibear

What This Skill Does

Analyzes and restructures vague or unstructured prompts into clear, effective ones by enforcing a four-element contract (role, task, constraints, output) and auto-detecting whether to dispatch sub-agents for codebase research, clarifying questions, or web search.

Replaces manual prompt rewriting and guesswork by systematically applying a proven framework and routing to specialized sub-agents when context is missing.

When to Use It

  • Improve a vague prompt like 'make it better' by adding missing role, task, constraints, and output format
  • Optimize a coding prompt by specifying edge cases, framework details, and implementation steps
  • Clarify a prompt that references 'this project' or 'our API' by triggering codebase research
  • Enhance a prompt about best practices or external libraries by pulling in web search results
  • Refine a creative writing prompt by injecting tone, audience, and novelty constraints
  • Restructure a multi-part prompt into XML-tagged sections for complex agent instructions

Install

$ openclaw skills install @tolibear/promptify

Prompt Optimizer

Transform prompts into clear, effective ones. Model-agnostic.

Modifiers (parse from ARGUMENTS)

  • +ask → Force clarifying questions
  • +deep → Force codebase exploration
  • +web → Force web search

No modifiers? Auto-detect what's needed.

Auto-Detection Triggers

TriggerSignals
codebase-researcher"this project", "our API", specific files/functions, "integrate", "extend", "refactor"
clarifierAmbiguous ("make it better"), multiple interpretations, missing constraints, vague pronouns
web-researcher"best practices", "latest", external APIs/libraries, framework patterns, year references

Agent Dispatch

When agents needed:

  1. Announce which and why
  2. Run in parallel via Task tool (agents/ directory)
  3. Synthesize findings
  4. Optimize with gathered context

Core Contract (every prompt needs all four)

ElementIf Missing
RoleAdd persona with expertise
TaskMake action specific
ConstraintsInfer from context
OutputSpecify format/structure

Process

  1. If image: Analyze, incorporate context
  2. Detect type: coding/writing/analysis/creative/data
  3. Convert output→process: "Write X" → "Analyze → Plan → Implement → Validate"
  4. Strip fluff: "please", "I want you to", filler, apologies
  5. Apply contract: Verify all 4 elements
  6. Add structure: XML tags for complex prompts

Type Focus

  • Coding: Specs, edge cases, framework
  • Writing: Tone, audience, length
  • Analysis: Criteria, depth
  • Creative: Constraints, novelty
  • Data: I/O format, edge cases

Output

  1. Optimized prompt in code block
  2. echo 'PROMPT' | pbcopy
  3. 2-3 sentence explanation

Top skills in this category