Agent skills for Codex CLI

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

Caching strategies for LLM prompts including Anthropic prompt

Transforms a rough idea into a detailed design document with implementation plan.

Analyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy, email campaigns…

Expert guide on prompt engineering patterns, best practices, and optimization techniques.

A comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts)…

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional…

Builds or extends the tracked AI-answer prompt set from real buyer evidence, structured by buying-journey stage and proximity to the…

Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset.

Structured prompt template creation with variables, formatting, and version control

Use when writing, refactoring, or evaluating LLM prompts (system prompts, user prompts, few-shot examples, or tool-call schemas) for agent…

Orchestrates parallel prompt validation for Finesse planning sessions

Generate AI personalization prompts for cold email campaigns.

Set up Promptbook \u2014 connect your account to start tracking builds.\n\

Generate/create/write PromQL queries, metric expressions, alerting rules, recording rules, Prometheus dashboards.

Scans lyrics for pronunciation risks and prevents Suno mispronunciations.

Use when designing the proof technique, algorithm, or simulation protocol for an Operations Research (OR) manuscript — choosing the right…

Assist in constructing algorithm correctness proofs

Rigorous mathematical proof verification and fixing workflow.

Design QA audit — red flags, severity classification, visual quality scorecard.

Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro…