Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add komunite/kalfa --skill prompt-engineering-guidegit clone --depth 1 https://github.com/komunite/kalfaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/komunite/kalfa/prompt-engineering-guide)<a href="https://agentmods.dev/skills/komunite/kalfa/prompt-engineering-guide"><img src="https://agentmods.dev/badge/skills/komunite/kalfa/prompt-engineering-guide.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.02755 |
| Opus 5 | $0.00012 | $0.01378 |
| Sonnet 5 | $0.00005 | $0.00551 |
| Haiku 4.5 | $0.00002 | $0.00276 |
Grade A, and why
prompt-engineering-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Mühendisliği — Solopreneur Rehberi
Amaç
AI'dan profesyonel kalitede çıktı almak için pratik teknikler. Akademik teori yok — kopyala-yapıştır yapabileceğin şablonlar ve hemen uygulayabileceğin kurallar. Solopreneur olarak AI, senin ilk çalışanın. Ama ona iyi brief vermezsen kötü iş çıkarır.
Kategori: Yapay Zeka ve Otomasyon Ön koşul: Claude veya ChatGPT hesabı Seviye: Başlangıç → Orta
Temel Çerçeve: RACE
Her prompt'u bu 4 katmanlı yapıyla kur:
| Katman | Açıklama | Örnek |
|---|---|---|
| Role (Rol) | AI'ya kim olduğunu söyle | "Sen 10 yıllık deneyimli bir SaaS copywriter'ısın" |
| Action (Eylem) | Ne yapmasını istediğini söyle | "Bir landing page headline'ı yaz" |
| Context (Bağlam) | İşin arka planını ver | "Ürünüm freelancerlar için zaman takip aracı, aylık ₺99" |
| Example (Örnek) | Beklediğin çıktıyı göster | "Şu tarz olsun: 'Stop trading time for money'" |
Neden çalışır? AI, bağlam ne kadar spesifikse o kadar iyi çıktı verir. "Bir metin yaz" dersen ortalama bir şey alırsın. RACE ile yönlendirirsen profesyonel çıktı alırsın.
5 Temel Prompt Kalıbı
1. İçerik Üretimi (Blog, Sosyal Medya, E-posta)
Rol: Sen [niş alanı] konusunda uzman bir içerik stratejistsin.
Hedef kitle: [kitle tanımı — yaş, meslek, acı noktası].
Görev: [içerik türü] yaz.
Ton: [konuşkan / profesyonel / eğitici / ikna edici].
Uzunluk: [kelime sayısı veya paragraf sayısı].
Format: [madde listesi / hikaye / listicle / how-to].
Şu yapıyı kullan:
- Dikkat çekici açılış (ilk cümle kancası)
- Ana mesaj (3 alt başlıkla)
- Kapanış + call-to-action
Örnek ton: "[buraya beğendiğin bir içerikten 2-3 cümle yapıştır]"
2. Araştırma ve Analiz (Rakip, Pazar)
Rol: Sen [sektör] alanında deneyimli bir iş analisti sin.
Görev: [rakip/pazar/trend] analizi yap.
Kapsam: [coğrafya, zaman dilimi, segment].
Şu çerçeveyi kullan:
1. Mevcut durum özeti (5 madde)
2. Güçlü ve zayıf yönler tablosu
3. Fırsatlar (3 tane, her biri potansiyel gelir tahminiyle)
4. Tehditler ve riskler
5. Benim için 3 aksiyon önerisi (öncelik sırasıyla)
Kaynak olarak bilinen verileri kullan. Emin olmadığın yerleri "[doğrulanmalı]" olarak işaretle.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 221 lines · 23 tokens per session scan A fbe44af0442f
prompt-engineering-guide is a skill published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 2,755 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
claude-coach
Personal coach that teaches users to become Claude power users. Use this skill the FIRST time a user asks to "learn Claude", "be a power user", "coach me", "teach me Claude tricks", "what can Claude do", "make me better at prompting", or any variation. After activation, also use it on EVERY subsequent turn to detect…
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
gemini-api-dev
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best…
prompt-engineering
Master the art and science of crafting effective prompts for large language models. Covers foundational patterns, advanced techniques like chain-of-thought and role prompting, structured output formats, and practical strategies for iterative refinement.
prompt-version-management
Manage prompt versions, run A/B tests across agent prompts, track performance regressions, and safely roll out prompt changes in production. Covers prompt diffing, semantic versioning, canary releases, and automated evaluation.
prompt-lab
LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.