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/promptifyPrompt 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
| Trigger | Signals |
|---|---|
| codebase-researcher | "this project", "our API", specific files/functions, "integrate", "extend", "refactor" |
| clarifier | Ambiguous ("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:
- Announce which and why
- Run in parallel via Task tool (agents/ directory)
- Synthesize findings
- Optimize with gathered context
Core Contract (every prompt needs all four)
| Element | If Missing |
|---|---|
| Role | Add persona with expertise |
| Task | Make action specific |
| Constraints | Infer from context |
| Output | Specify format/structure |
Process
- If image: Analyze, incorporate context
- Detect type: coding/writing/analysis/creative/data
- Convert output→process: "Write X" → "Analyze → Plan → Implement → Validate"
- Strip fluff: "please", "I want you to", filler, apologies
- Apply contract: Verify all 4 elements
- 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
- Optimized prompt in code block
echo 'PROMPT' | pbcopy- 2-3 sentence explanation
Top skills in this category
Multi Search Engine
@gpyangyoujunMulti search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Openai Whisper
@steipeteLocal speech-to-text with the Whisper CLI (no API key).
Tavily 搜索
@jacky1n7Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable...
Baidu web search
@ide-reaSearch the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.