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 ApexIQ/skillsmith --skill prompt_engineeringgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/prompt_engineering)<a href="https://agentmods.dev/skills/apexiq/skillsmith/prompt_engineering"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/prompt_engineering.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 | $0.00055 | $0.00663 |
| Opus 5 | $0.00028 | $0.00331 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
prompt_engineering 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
✍️ Prompt Engineering (2025 Edition)
Philosophy: Direct models through clear constraints and structural cues. Modern LLMs prioritize well-formatted, context-rich instructions over simple keywords.
🧠 Reasoning Model Strategy (o1, o3, DeepSeek-R1)
For models with internal "Think" cycles:
- Quiet Mode: Do NOT ask for "chain of thought" or "step by step" logic. These models do it internally and redundant prompting can degrade latency or follow-through.
- Focus: Define the Input, Constraints, and Expected Output Schema with extreme precision.
- Evaluation: Provide rubrics for how the model should verify its own work.
1. Delimiters and XML Tagging
Use standard delimiters (XML tags, backticks, or separators) to clearly distinguish instructions from data.
- Example:
<instruction>Extract entities from the text below.</instruction> <text>John Doe moved to Berlin in 2024.</text> - Benefit: Prevents "prompt injection" where the data content overwrites the instructions.
2. Few-Shot Structural Prompting
Show example "Thought -> Action" sequences to steer complex agent behavior.
- Use 2-3 high-quality examples of the full reasoning process.
3. Negative Constraints (Avoidance)
Be explicit about what NOT to do.
- Bad: "Don't use Python 2."
- Good: "Use Python 3.12+ features. Avoid any legacy constructs from Python 2.x."
4. Output Formatting (JSON/Markdown)
Force specific formats for programmatic use.
- Use JSON Schema in the prompt to ensure the keys and types are strictly followed.
Advanced Patterns
- Meta-Prompting: Use the model to help you refine your own prompt.
- Context Injection: See
agentic_context_engineeringfor managing long-term memory. - Workflow Patterns: See
anthropic_workflow_patternsfor orchestration logic.
Anti-Patterns (2025 Update)
- Prompt Dumping: Adding irrelevant code snippets (use
skillsmith budgetto check token usage). - Keyword Soup: Relying on magic words like "Expert" (effective prompts now rely on specific instructions and role-play).
- Ignoring Failures: Not providing instructions on what the model should do when it cannot complete the task.
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.
- 8d ago First seen · 63 lines · 55 tokens per session scan A 15e110a63a5c
prompt_engineering is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 663 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
llm-engineering-expert
Build reliable applications on large language models: prompt design, structured output, evaluation, guardrails, and cost and latency control. Use when the user mentions LLMs, prompts, prompt engineering, few-shot examples, structured or JSON output, function calling, hallucination, model evaluation, token costs…
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
dspy-output-refinement-constraints
Use for dspy.Refine, dspy.BestOfN, output constraints, validation, reward functions, and iterative output refinement.
dspy-react-agent-builder
Use for ReAct agents, tool-calling agents, dspy.ReAct, multi-step reasoning and acting, and GEPA agent optimization.
Prompt Refiner
Improves AI prompts to be clearer, more specific, and produce more consistent outputs.