Prompt Writing

prompt-optimizer is a prompt-optimizer skill that analyzes rough prompts, finds missing context, and rewrites them into clearer, ready-to-paste prompts. It is best for prompt-optimizer guide work, prompt review, and prompt-optimizer for Prompt Writing, especially when you need better structure for Claude Code or ECC workflows. It does not execute the underlying task.

prompt-engineering-patterns is a practical skill for production prompt design, covering install context, reusable templates, few-shot examples, structured outputs, and prompt optimization workflows for Context Engineering.

ai-prompt-engineering-safety-review is a prompt audit skill for reviewing LLM prompts for safety, bias, security weaknesses, and output quality before production, evaluation, or customer-facing use.

mama is a narration-style variant of the pua skill that keeps the same core rules but switches to a Chinese nagging-mom voice. Use it to install a reusable trigger pattern for persistent troubleshooting, debugging, and Prompt Writing workflows, with inherited escalation, checklists, and stronger follow-through.

The enhance-prompt skill turns vague UI ideas into clearer, Stitch-ready prompts with stronger structure, UI/UX vocabulary, and design-system context. Use this enhance-prompt guide to improve prompt specificity, reduce guesswork, and get more consistent results for prompt writing and UI generation.

create-ex is a repo-based skill that turns chat history and relationship context into a reusable digital persona workflow, with guided intake, transcript analysis, preview, and file output.

veo-3.2-prompter is a prompt-design skill for Google Veo 3.x workflows. It helps turn mixed assets and rough intent into a structured JSON prompt with reference-role mapping, recommended parameters, and practical guidance for install, usage, and Veo-ready prompt writing.

seedance-2.0-prompter helps turn multimodal Seedance 2.0 assets into structured prompts with clear roles, @asset syntax, and reusable templates for install, setup, and practical usage.

anti-distill is a rewriting skill that classifies and rewrites skill files, work guides, and persona docs into cleaned versions with core know-how removed. It supports manual install in Claude Code or OpenClaw, then runs with /anti-distill on files, folders, or pasted content.

distill-mentor turns public academic data into a reusable mentor-style skill. It supports browser-first collection, deep paper analysis, bilingual output, and saved artifacts under ~/.claude/mentors/ and ~/.claude/skills/.

create-senpai is a Claude Code skill that turns chat exports, meeting notes, screenshots, and photos into a reusable senpai persona with group memory, correction flow, and ongoing updates.

create-crush is a Claude Code skill that turns chat logs, photos, and social posts into a reusable persona and Relationship Memory, with optional parsers, correction flows, and updateable skill outputs for Skill Authoring.

seedance-prompt is a Seedance 2.0 motion-graphics prompt skill for turning product ideas, brand assets, or screenshots into structured 15-second promo video prompts. It supports style selection, reference-image handling, and a practical seedance-prompt guide for product demos and launch clips.

fengge-wangmingtianya-perspective is a Chinese prompt-writing skill for a fictional wandering-commentator voice with blunt humor, conclusion-first structure, reusable templates, and safety-aware refusals for relationship, work, and life-confusion scenarios.

create-parents helps turn chat logs, memories, photos, and voice notes into a reusable parent persona skill for Claude Code, with guided intake, WeChat parsing, memory and persona generation, and updateable files under ./parents/{slug}/.

Use the prompt-engineering skill to write clearer, more controllable prompts for agents, tools, sub-agents, and production workflows. It covers practical prompt-engineering patterns for Prompt Writing, including few-shot examples, constraints, formatting, and prompt optimization to improve output reliability.

detecting-ai-model-prompt-injection-attacks is a cybersecurity skill for screening untrusted text before it reaches an LLM. It uses layered regex, heuristic scoring, and DeBERTa-based classification to flag direct and indirect prompt injection attacks. Useful for chatbot input validation, document ingestion, and Threat Modeling.

The yes skill is a supportive, praise-forward coaching mode from tanweai/pua. It keeps the repo’s discipline while shifting delivery to warm encouragement, gentle critique, and light teasing. Useful for prompt writing, debugging, and revision when you want motivation without losing standards.