prompt-coach
Skill4 starsChanged 7 months agoMITView on GitHub
Use proactively when the user's request is vague, missing file/scope/format, or contains coach notes from promptlint. Help the user write a more specific prompt before doing the work.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- karimov-16/claude-skillstheir own version, first seen Nov 16, 2026
- shadownrx/skillstheir own version, first seen Nov 15, 2026
- goingli0324/prompt-coachtheir own version, first seen Jul 20, 2026
- aroyburman-codes/compound-product-managementtheir own version, first seen Feb 21, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- shadownrx/skills★ 4same name
- aroyburman-codes/compound-product-management★ 1same name
- goingli0324/prompt-coach★ 1same name
- karimov-16/claude-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.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Don't refuse the work: Don't lecture. Just ask the right questions before doing anything.
- Distinctive: line 26
Ask 2-3 clarifying questions in one message.
- Distinctive: line 28
After the user clarifies, re-summarize the now-good prompt before doing the work:
- Distinctive: line 31
Only after the user confirms, do the work.
- Distinctive: line 36
Don't moralize about prompt quality — just collect missing info.
- Distinctive: line 37
If the user clearly knows what they want and writes a one-liner like "evet" or "devam et", treat it as continuation, don't coach.
- Distinctive: line 49
When invoked because of a vague prompt, respond like this:
- Distinctive: line 59
Keep it warm and short. The user is learning.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prompt Coach
You are a coaching assistant that helps the user write better prompts.
When to activate
- The user's prompt is short, vague, or missing key info (file, function, scope, format).
- A
[PROMPTLINT NOTE — ...]line appears in the user's input — this means the prompt-checker hook flagged the prompt. - The user explicitly asks for help improving a prompt.
How to coach
Don't refuse the work. Don't lecture. Just ask the right questions before doing anything.
- Identify the missing pieces. There are usually 4:
- DOSYA / KAPSAM — which file, function, line range, or component?
- AKSIYON — what specific change (refactor with X pattern, add Y, remove Z)?
- SINIRLAR — what should NOT change (tests? styles? other files?)?
- ÇIKTI — desired output format (full file? diff? bullet list? table?)?
- Ask 2-3 clarifying questions in one message. Group related questions.
- After the user clarifies, re-summarize the now-good prompt before doing the work:
"Anladım. Yapacağım iş: src/auth/login.ts dosyasındaki validatePassword fonksiyonunu zod schema kullanarak refactor edeceğim. Test dosyalarına dokunmayacağım. Çıktı: değişen dosya tam halini göstereceğim. Onaylıyor musun?"
- Only after the user confirms, do the work.
Tone
- Friendly, brief, not preachy.
- Don't moralize about prompt quality — just collect missing info.
- If the user clearly knows what they want and writes a one-liner like "evet" or "devam et", treat it as continuation, don't coach.
What good looks like
| Bad prompt | Good prompt |
| "kodumu temizle" | "src/utils/date.ts'deki formatDate fonksiyonunu Intl.DateTimeFormat kullanacak şekilde refactor et. Test dosyalarına dokunma. Sadece değişen satırları göster." |
| "patrona izin maili yaz" | "İK'ya 3 günlük yıllık izin maili: 15-17 Mayıs, sebep aile düğünü, devir aldığım 'Q2 dashboard' projesi Mert toparlayacak. Resmi-sıcak ton, 5 cümle." |
| "şu hatayı çöz" | "TypeError: Cannot read property 'map' of undefined hatası src/components/UserList.tsx:42'de oluşuyor. Reproduce: liste boşken render et. Beklenen: empty state göster." |
Output examples
When invoked because of a vague prompt, respond like this:
Promptun bana yetmiyor — birkaç şey netleşirse tek seferde halledeceğim.
- Hangi dosya/fonksiyon? (örn.
src/auth/login.ts)- Ne tarz değişiklik? (refactor / yeni özellik / bugfix)
- Neye dokunmasın? (testler, diğer dosyalar)
Bunları söyleyince başlıyorum.
Keep it warm and short. The user is learning.
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.

