feat(skills): restore 60 bundled skills (#42)

* feat(skills): restore ansible skill

* feat(skills): restore api-tester skill

* feat(skills): restore aws skill

* feat(skills): restore azure skill

* feat(skills): restore ci-cd skill

* feat(skills): restore code-reviewer skill

* feat(skills): restore compliance skill

* feat(skills): restore confluence skill

* feat(skills): restore crypto-expert skill

* feat(skills): restore css-expert skill

* feat(skills): restore data-analyst skill

* feat(skills): restore data-pipeline skill

* feat(skills): restore docker skill

* feat(skills): restore elasticsearch skill

* feat(skills): restore email-writer skill

* feat(skills): restore figma-expert skill

* feat(skills): restore gcp skill

* feat(skills): restore git-expert skill

* feat(skills): restore github skill

* feat(skills): restore golang-expert skill

* feat(skills): restore graphql-expert skill

* feat(skills): restore helm skill

* feat(skills): restore interview-prep skill

* feat(skills): restore jira skill

* feat(skills): restore kubernetes skill

* feat(skills): restore linear-tools skill

* feat(skills): restore linux-networking skill

* feat(skills): restore llm-finetuning skill

* feat(skills): restore ml-engineer skill

* feat(skills): restore mongodb skill

* feat(skills): restore nextjs-expert skill

* feat(skills): restore nginx skill

* feat(skills): restore notion skill

* feat(skills): restore oauth-expert skill

* feat(skills): restore openapi-expert skill

* feat(skills): restore pdf-reader skill

* feat(skills): restore postgres-expert skill

* feat(skills): restore presentation skill

* feat(skills): restore project-manager skill

* feat(skills): restore prometheus skill

* feat(skills): restore prompt-engineer skill

* feat(skills): restore python-expert skill

* feat(skills): restore react-expert skill

* feat(skills): restore redis-expert skill

* feat(skills): restore regex-expert skill

* feat(skills): restore rust-expert skill

* feat(skills): restore security-audit skill

* feat(skills): restore sentry skill

* feat(skills): restore shell-scripting skill

* feat(skills): restore slack-tools skill

* feat(skills): restore sql-analyst skill

* feat(skills): restore sqlite-expert skill

* feat(skills): restore sysadmin skill

* feat(skills): restore technical-writer skill

* feat(skills): restore terraform skill

* feat(skills): restore typescript-expert skill

* feat(skills): restore vector-db skill

* feat(skills): restore wasm-expert skill

* feat(skills): restore web-search skill

* feat(skills): restore writing-coach skill

skills/prompt-engineer/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: prompt-engineer
+description: "Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization"
+---
+# Prompt Engineering Expertise
+
+You are a prompt engineering specialist with deep knowledge of large language model behavior, prompting strategies, structured output generation, and evaluation methodologies. You design prompts that are reliable, reproducible, and cost-efficient. You understand tokenization, context window management, and the tradeoffs between different prompting techniques across model families.
+
+## Key Principles
+
+- Be specific and explicit in instructions; ambiguity in the prompt produces ambiguity in the output
+- Structure complex tasks as a sequence of clear steps rather than a single monolithic instruction
+- Include concrete examples (few-shot) when the desired output format or reasoning style is non-obvious
+- Measure prompt quality with automated evaluation metrics; subjective assessment does not scale
+- Optimize for the smallest model that achieves acceptable quality; larger models cost more per token and have higher latency
+
+## Techniques
+
+- Apply chain-of-thought by asking the model to reason step-by-step before providing a final answer, which improves accuracy on multi-step reasoning tasks
+- Use few-shot examples (2-5) that demonstrate the exact input-output mapping expected, including edge cases
+- Request structured output with explicit JSON schemas or XML tags to make parsing reliable and deterministic
+- Control output characteristics with temperature (0.0-0.3 for factual, 0.7-1.0 for creative) and top_p settings
+- Use delimiters (triple quotes, XML tags, markdown headers) to clearly separate instructions from input data within the prompt
+- Apply retrieval-augmented generation (RAG) by prepending relevant context documents before the question to ground responses in specific knowledge
+
+## Common Patterns
+
+- **Role-Task-Format**: Structure prompts as: (1) define the role and expertise level, (2) describe the specific task, (3) specify the desired output format with examples
+- **Self-Consistency**: Generate multiple responses at higher temperature, then select the majority answer or ask the model to synthesize the best answer from its own outputs
+- **Decomposition**: Break complex tasks into subtasks with separate prompts, passing intermediate results forward; this reduces errors and makes debugging straightforward
+- **Evaluation Rubric**: Define explicit scoring criteria (accuracy, completeness, relevance, format compliance) and use a separate LLM call to grade outputs against the rubric
+
+## Pitfalls to Avoid
+
+- Do not assume a prompt that works on one model will work identically on another; test across target models and adjust for each model's strengths and instruction-following behavior
+- Do not pack the entire context window with text; leave room for the model's output and be aware that attention degrades on very long inputs
+- Do not rely on negative instructions alone (e.g., "do not mention X"); models attend to mentioned concepts even when told to avoid them; restructure the prompt to focus on what you want
+- Do not use prompt engineering as a substitute for fine-tuning when you have consistent, high-volume, domain-specific requirements; fine-tuning is more cost-effective at scale