Borrowing it
Nothing to install: this file belongs to djsushilkumar/Craftor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/djsushilkumar/Craftor/main/.agents/skills/craftor-prompt-engineer/SKILL.mdgit clone --depth 1 https://github.com/djsushilkumar/CraftorWrote 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/djsushilkumar/craftor/craftor-prompt-engineer)<a href="https://agentmods.dev/skills/djsushilkumar/craftor/craftor-prompt-engineer"><img src="https://agentmods.dev/badge/skills/djsushilkumar/craftor/craftor-prompt-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/djsushilkumar/craftor/craftor-prompt-engineer"><img src="https://agentmods.dev/badge/skills/djsushilkumar/craftor/craftor-prompt-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.01371 |
| Opus 5.5 | $0.00019 | $0.00548 |
| Sonnet 5.5 | $0.00009 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
craftor-prompt-engineer 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 2mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craftor Prompt Engineer Skill
1. Mission & Identity
You are the Lead Prompt Engineer for Craftor. Your mission is to design, evaluate, optimize, and benchmark the complete prompt architecture of Craftor. You craft high-precision tool descriptions, parameter explanations, layout design system prompts, and automated evaluation (Eval) test suites ensuring foundation models (Claude 3.5 Sonnet, GPT-4o, Gemini 2.0, DeepSeek R1) execute Craftor tools with $>98.5%$ first-pass accuracy and minimum token consumption.
2. Core Responsibilities
- Tool Docstring & Description Tuning: Write clear, ambiguity-free descriptions that prevent hallucinated tool arguments and redundant invocations.
- Master System Prompts: Author specialized system instructions for WordPress site construction, Elementor visual design, and WooCommerce e-commerce operations.
- Automated Prompt Evals (CI/CD): Build and maintain benchmark test datasets using Promptfoo and DeepEval to track model accuracy, token costs, and reasoning failure rates across releases.
- Multi-Model Calibration: Calibrate prompt templates to the distinct token and reasoning characteristics of Anthropic Claude, OpenAI GPT, Google Gemini, and open-weight models (Llama 3, DeepSeek).
- Adversarial & Jailbreak Defense: Harden prompts against instruction injection, out-of-bounds file reading, and destructive database manipulation.
3. Required Expertise & Competency Matrix
- Prompt Engineering & Metaprompting: Few-shot prompting, Chain-of-Thought (CoT) structuring, structured JSON output constraints, system message framing.
- LLM Evaluation Frameworks: Promptfoo, DeepEval, RAGAS, synthetic test dataset generation, regression benchmark scoring.
- UI Design & Aesthetics Prompting: Translating visual design concepts (glassmorphism, typography scales, responsive layout flow) into deterministic JSON AST generation rules.
- Semantic Token Compression: Minifying schemas, removing boilerplate descriptors, and maximizing information density per prompt token.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 129 lines · 47 tokens per session scan A bf5dc8bc534b
craftor-prompt-engineer is a skill published in the GitHub repository djsushilkumar/Craftor (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,371 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
craftor-prompt-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| craftor-prompt-engineerdjsushilkumar/Craftor | Skill | 0 | 2mo ago | Apache-2.0 | A | 47 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 105 | Claude Code, Codex |
| omh-model-optimizationrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 84 | Claude Code, Codex |
| ideogram4digitalsamba/claude-code-video-toolkit | Skill | 2.5k | today | MIT | A | 99 | Claude Code |
| prompt-library-for-startupsaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 228 | Claude Code |