From sundial-org-awesome-openclaw-skills-4
Optimizes prompts for clarity and effectiveness. Routes to sub-agents for codebase research, clarifying questions, or web search. Use when user asks to improve a prompt.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sundial-org-awesome-openclaw-skills-4:promptifyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Transform prompts into clear, effective ones. Model-agnostic.
Transform prompts into clear, effective ones. Model-agnostic.
No modifiers? Auto-detect what's needed.
| 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 |
When agents needed:
| Element | If Missing |
|---|---|
| Role | Add persona with expertise |
| Task | Make action specific |
| Constraints | Infer from context |
| Output | Specify format/structure |
echo 'PROMPT' | pbcopynpx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin sundial-org-awesome-openclaw-skills-4Analyzes and improves prompts for clarity, structure, and completeness. Use when auditing or fixing vague instructions to produce a before/after optimization report.
Transforms rough prompts, task descriptions, or jobs into optimized AI instruction prompts using best practices. Activates on requests to improve, optimize, or refine prompts for Claude/GPT.
Refines rough prompts, vague ideas, or task descriptions into finished, copy-pasteable prompts for any LLM chat interface. Outputs a single code block with no placeholders.