prompt-enhance
Rewrites a rough prompt, voice dump, or half-written instruction into an agent-ready prompt. Use when the user asks to make a prompt better, enhance/refine a prompt, clean up instructions for an agent, or improve pasted prompt text. One-shot transformer; does not interview.
- Installs
- 48
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/owainlewis/agent-skills --skill prompt-enhance- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads prompt-enhance automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Prompt Enhance
Return one refined prompt a coding or knowledge agent can execute.
Do not interview.
When information is missing, use an assumption or [NEEDS: ...].
Workflow
- Read the input and referenced context: repo, files,
AGENTS.md,CLAUDE.md,README.md, relevant code. - Resolve unambiguous references such as "the thing" or "that script".
- Identify defects: vague goal, buried intent, contradictions, missing scope, missing output format, missing success criteria, negative phrasing, premature-stop scaffolding, irrelevant noise.
- Rewrite the prompt. Preserve intent. Remove filler. Keep substance.
- Return the refined prompt, then
Changed,Assumptions, andGapslines as needed. - Offer one action: run it now, save it to
prompts/<slug>.md, or stop.
Principles
- Lead with the goal in one sentence.
- State output, format, constraints, and scope directly.
- Resolve contradictions or state priority.
- Say what is in scope and what is out of scope.
- Use numbered steps only when order matters.
- Prefer positive instructions.
- Include only context that changes the work.
- Specify output contract: format, structure, length, path, naming, overwrite behavior.
- State success criteria: tests, files, observed behavior, or other proof.
- Tell the agent to proceed on reasonable assumptions unless genuinely blocked.
- Use a role only when it changes tone or judgment.
- Separate instructions, context, examples, and pasted input when they could be confused.
- Add examples only for exact format or style.
Gaps
- Use a sensible default when safe. Record it under
Assumptions. - Use
[NEEDS: <missing detail>]when no safe default exists. - Do not ask questions. Use
clarifyfor interviews.
Output
Refined prompt:
<rewritten, self-contained prompt that reads cold>
---
Changed: <substantive improvements>
Assumptions: <defaults baked in, omit if none>
Gaps: <remaining [NEEDS: ...] items, omit if none>
Then offer: run it now, save it to prompts/<slug>.md, or stop.
Example
Input:
script that pulls podcast mp3s and transcribes them, use whisper, don't make it slow, cache stuff somewhere sensible
Output:
Refined prompt:
Build a Python CLI script that downloads podcast episodes from an RSS feed and transcribes each MP3 with OpenAI Whisper.
Input: RSS feed URL as a required argument.
Output: save each MP3 and transcript (`.txt`, same basename) under `data/<podcast-slug>/`.
Caching: skip any episode whose MP3 and transcript already exist.
Performance: download and transcribe episodes concurrently.
Failure: exit non-zero for a bad feed URL; skip and log individual episode failures.
Success: running twice performs no redundant downloads or transcriptions.
Out of scope: UI, speaker diarization, non-MP3 formats.
---
Changed: added input, output, caching, concurrency, failure handling, and success criteria.
Assumptions: RSS feed input; local `data/` output.
FAQ
What does the prompt-enhance skill do?
Rewrites a rough prompt, voice dump, or half-written instruction into an agent-ready prompt. Use when the user asks to make a prompt better, enhance/refine a prompt, clean up instructions for an agent, or improve pasted prompt text. One-shot transformer; does not interview.
How do I install prompt-enhance?
Run npx skills add https://github.com/owainlewis/agent-skills --skill prompt-enhance in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/prompt-enhance/ (personal) or .claude/skills/prompt-enhance/ (project).
Which AI agents can use prompt-enhance?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is prompt-enhance safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains prompt-enhance?
It is published by owainlewis in owainlewis/agent-skills. It has 48 recorded installs.
More from owainlewis/agent-skills
explain-visually
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
clarify
owainlewis/agent-skills
Turn a vague request, voice dump, rough plan, or half-written prompt into a self-contained prompt that a fresh agent can execute. Use when asked to clarify, refine, improve, tighten, or stress-test an agent task. Resolve safe defaults directly. Ask one question at a time only when the answer would materially change the work.
compress
owainlewis/agent-skills
Shorten a prompt, specification, plan, skill, note, or brain dump without changing its meaning or behaviour. Use when asked to compress, shorten, simplify, tighten, remove repetition, or use fewer tokens. Preserve facts, constraints, examples, edge cases, and checks that affect the result.
humanizer
owainlewis/agent-skills
Rewrite any writing so it sounds clear, human, and plain. Use for landing pages, emails, docs, posts, scripts, lessons, prompts, and messages with AI slop, purple prose, cliches, em dashes, hype, vague claims, or over-polished language.
feynman
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
backlog-manager
owainlewis/agent-skills
Manage an engineering backlog for humans and AI agents: classify issues, improve issue quality, sync PR state, and label safe tickets for agent execution. Use when GitHub Issues, GitHub Projects, Linear, or an explicit local backlog path is the source of truth.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available