prompt-craft
Skill0 starsChanged 2 months agoNo licenceView on GitHub
Use when the user has a vague/underspecified request they want to turn into a well-formed prompt for an AI tool (any AI, not just Claude) — e.g. \"幫我寫封信\" \"幫我看一下這份資料\" \"幫我回這個客訴\" without saying who it's for, what format, or what tone. Also use when the user explicitly asks how to write a better prompt, or says a prompt/reply from an AI came out wrong because they didn't specify enough. Detects which of 6 dimensions (role/context/format/audience-tone/example/constraints) are missing from the raw request, asks ONE consolidated clarifying question for what's missing (does not silently guess), then assembles a structured prompt with a one-line note explaining why each filled-in field matters — grounded in Anthropic/OpenAI/Google's own prompt engineering guides plus workplace-survey data on why non-technical staff struggle to prompt (34% confident at task decomposition, LinkedIn/TalentLMS 2026).
7 other projects use a version of this.
Adopted by
Most recently taken up by
- phntm7/skillstheir own version, first seen Nov 1, 2026
- antonailog/skillstheir own version, first seen Nov 1, 2026
- soreavis/ai-docenttheir own version, first seen Oct 13, 2026
- kravcovtech/prompt-crafttheir own version, first seen Sep 4, 2026
- wpc725562-dotcom/dsh-agent-kittheir own version, first seen Aug 24, 2026
- breeze-r/claude-prompt-craft-skilltheir own version, first seen Jul 11, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- NatureBlueee/Nature-use-skills★ 39same name
- breeze-r/claude-prompt-craft-skill★ 11same name
- antonailog/skills★ 1same name
- phntm7/skills★ 1same name
- kravcovtech/prompt-craft★ 0same name
- soreavis/ai-docent★ 0same name
- wpc725562-dotcom/dsh-agent-kit★ 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 repository4 other files it gives its agents.
- bigtech-career-radarSkill
- dating-profile-checkerSkill
- resume-jd-checkerSkill
- youtube-contentSkill
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.