Panduan dan kerangka kerja (framework) untuk menyusun prompt yang efektif dan terstruktur saat memberikan instruksi kepada Claude atau AI lainnya, berdasarkan skema HDS.
Gunakan kerangka kerja dari skema ini saat Anda perlu menyusun instruksi yang sangat spesifik, panjang, atau kompleks untuk Agent AI (seperti Claude), guna memastikan hasil yang akurat, tepat sasaran, dan minim hallucination.
Jelaskan tujuan utama Anda secara spesifik beserta kriteria keberhasilannya.
I want to [TASK] so that [SUCCESS CRITERIA].
First, read these files completely before responding:
Berikan penjelasan mengenai daftar file referensi yang dilampirkan agar AI memahami fungsi masing-masing file tanpa menebak.
[filename.md] — [what it contains]
[filename.md] — [what it contains]
[filename.md] — [what it contains]
Tarik benang merah (reverse-engineer) apa yang membuat contoh referensi Anda berhasil, lalu jadikan itu sebagai aturan (rules).
Here is a reference to what I want to achieve:
[Upload reference file as markdown, or paste it here]
Here's what makes this reference work:
[Paste your reverse-engineered blueprint - the patterns, tone, structure, and rules you extracted from the reference. Format each one as a rule starting with "Always" or "Never."]
Definisikan bentuk teknis/non-teknis dari luaran (output) serta apa matriks agar output tersebut divalidasi.
Here's what I need for my version:
SUCCESS BRIEF
- Type of output + length: [Contract, memo, report, proposal, landing page, post?]
- Recipient's reaction: [What should they think/feel/do after reading?]
- Does NOT sound like: [What to avoid - generic AI, too casual, formal, jargon-heavy?]
- Success means: [They sign? They approve? They reply? They take action?]
Batasi ruang gerak imajinasi AI dengan aturan ketat untuk mencegah output melenceng.
My context file contains my standards, constraints, landmines, and audience. Read it fully before starting. If you're about to break one of my rules, stop and tell me.
Jangan biarkan AI langsung bekerja jika instruksinya abu-abu. Secara eksplisit minta AI bertanya.
DO NOT start executing yet. Instead, ask me clarifying questions (use AskUserQuestion tool or equivalent) so we can refine the approach together step by step.
Verifikasi pemahaman AI dengan menugaskannya mengulangi 3 aturan terpenting dan merancang langkah sekuensial.
Before you write anything, list the 3 rules from my context file that matter most for this task.
Then give me your execution plan (5 steps maximum).
Only begin work once we've aligned.