Prompt enhancer
Skill Dokuganrryu/ai-agent-skills-and-subagents/skills/prompt-enhancer
Portable AI agent skills and specialist subagents for prompt enhancement, workspace resume, source-grounded research, and release readiness.
npx -y skills add Dokuganrryu/ai-agent-skills-and-subagents --skill prompt-enhancerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Compile raw prompts into Task, Context, Constraints, Done-when before acting, then invoke any clearly relevant skills. Use when the user asks to enhance, strengthen, clarify, decompose, make rigorous, or execute a non-trivial coding/technical prompt.
SKILL.md
1.7 KB, as published. Nobody here has run it
Prompt Enhancer
Treat every raw prompt as an uncompiled signature.
When
Before any coding or technical task that isn't a single-line, unambiguous edit.
Do
- Deconstruct into:
- Task: What exactly to build, fix, or produce
- Context: Which files, errors, source systems, or prior decisions matter
- Constraints: Language, framework, performance, security, style, scope
- Done-when: Objective completion criteria and verification
- Identify relevant skills:
- Check available skill names and descriptions for a clear match.
- Invoke the most specific matching skill when it materially improves correctness, speed, consistency, or verification.
- Stack skills only when each owns a distinct part of the job.
- If a matching skill calls for custom agents and the task is broad or investigation-heavy, include the relevant agents in the route.
- Gather missing fields from the conversation, workspace, or tools if obvious.
- If any required field is still missing, halt and ask one concise question.
- Execute the compiled prompt, never the raw prompt.
Rules
- Do not invent constraints or context.
- Do not proceed if a required field is missing.
- Do not invoke skills speculatively.
- Keep the compiled prompt concise and operational.
- Usually state only the selected skill route, then act; show the full compiled prompt only when useful.