prompt-refiner
Skill1 starsChanged 7 months agoNo licenceView on GitHub
Prompt 结构化改进工具 — 当 prompt 效果不好、AI 理解偏差、输出太烂时使用。诊断六大维度（角色/任务/约束/示例/格式/上下文），输出具体改进版本并解释每一步。触发场景：prompt 效果差、ChatGPT 答非所问、Claude 跑偏了、prompt 不知道怎么改、输出质量不稳定、想让 AI 更听话。当用户说"prompt 怎么改"、"为什么 AI 听不懂"、"输出不对"、"帮我优化一下 prompt"、"prompt 效果不好"时调用。
9 other projects use a version of this.
Adopted by
Most recently taken up by
- Data-Wise/crafttheir own version, first seen Oct 31, 2026
- chrysogonus/power-agentstheir own version, first seen Oct 13, 2026
- packetgloss/skillstheir own version, first seen Aug 12, 2026
- jqwang07-dotcom/prompt-refinertheir own version, first seen Jul 31, 2026
- benngarnish/sage-free-skillstheir own version, first seen Jul 25, 2026
- InfiniteRoomLabs/agent-opstheir own version, first seen Jun 23, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- chrysogonus/power-agents★ 4same name
- Data-Wise/craft★ 4same name
- doivamong/agent-workbench★ 2same name
- itsyasirkhandev/spec-driven-development★ 1same name
- jqwang07-dotcom/prompt-refiner★ 1same name
- willcagas/skills★ 1same name
- benngarnish/sage-free-skills★ 0same name
- InfiniteRoomLabs/agent-ops★ 0same name
- packetgloss/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- clarity-auditSkill
- codebase-inspectionSkill
- command-life-guardSkill
- first-commit-guideSkill
- http-status-explainerSkill
- shell-command-builderSkill
- skill-matchmakerSkill
- standup-scribeSkill
- trending-briefingSkill
- weekly-reviewSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.