276 skills
Audits WordPress plugin or theme PHP code for internationalization (i18n) correctness — text-domain consistency, use of escaped translation helpers (esc_html__, esc_attr__, esc_html_e), correct placeholder helpers (sprintf with translator comments, _n for plurals, _x for context), no variable text-…
Generate comprehensive Functional Specification Documents (FSDs) that translate PRD requirements into implementation-ready specifications. Use when the user needs to create an FSD, functional spec, system specification, or detailed feature specification. Triggers on requests like "create an FSD", "…
Use when writing in a creator's voice, analyzing a creator's style, or maintaining consistency across content.
Use when writing Go benchmarks or when asked to measure/optimize/improve the performance of a function — establishes correct benchmarks, measures with -benchmem and pprof, optimizes hot paths, and proves the gain (and no regression) with benchstat.
Access 30+ AI agent essays, CLAUDE.md generator, and readiness assessments.
Translate text, localize images, and manage glossaries from your IDE.
AI agent tools: translation, crypto research, compliance analysis, summarization, and more.
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Design, analyze, and optimize cold outbound email campaigns on Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and an implementation/strategy doc for human review. Use when asked to build cold outb…
Use when developing Lua plugins for Neovim, including user commands, keymaps, lazy loading, health checks, or help documentation. Apply best practices for <Plug> mappings, deferred require, proper structure, even when user requests shortcuts or quick solutions.
自媒体写作交互式助手。帮助完成从选题到发布的完整流程。适用于：开始写新文章、检查草稿质量、诊断发布后数据不佳的原因。
Shell script style and safety rules. Use when writing, editing, or reviewing bash or shell scripts.
Email sequences, newsletters, automation, and deliverability strategies. Use when the user requests 'email sequence', 'newsletter', 'drip campaign', 'welcome email', 'lifecycle email', 'cold email', 'email automation', or 'email copywriting'.
针对希望掌握ChatGPT的用户，设计一份侧重于实际应用（如营销SEO、创意写作、游戏开发）而非纯理论的学习课程大纲，要求章节具体且具有实操性。
Writes LinkedIn posts that sound like a real person, not a content mill
當你有明確需求或設計方案時，在動手改代碼前，用來撰寫多步驟的詳細實作計畫。
Blog/newsletter/content writing skill
当用户需要将一段文字翻译成另一种语言（中译英、英译中或其他语言互译）时使用本技能。适用于「翻译」「译成英文/中文」「用英文说」等请求。
Use when the user wants to generate marketing copy, ad headlines, taglines, product descriptions, or brand messaging using Gemini CLI. Trigger phrases: write copy with Gemini CLI, generate ad copy via terminal, Gemini CLI copywriting, bulk product descriptions. For email copy see gemini-cli-cold-em…
Use when writing posts for any platform (LinkedIn, Substack, internal team shares, any social network) - whether starting from raw material like transcripts, screenshots, or voice memos, or just a vague idea that needs conversation to flesh out.
Curate, refresh, and summarize the Weixin album `` from `` that is about tumor immunology paper notes, single-cell and multi-omics interpretation, lineage tracing, and literature-oriented method reading. Use when Codex needs the current article catalog for this specific Weixin album, wants a concis…
Expert in User-Centered Design (UCD), user journey mapping, and design reviews. Use when executing design reviews, writing user journey documents, and providing design guidance for developers.
分章节创作引人入胜的中文小说。支持各种题材（悬疑/言情/奇幻/科幻/历史等），支持10-50章长篇创作，每章3000-5000字，结尾设置悬念钩子。强调深度润色去除AI痕迹，确保文字自然流畅。 当用户要求：写小说、创作故事、分章节写作、连续剧情、章节悬念、长篇小说时使用。
Write survey prose into per-section files under `sections/` so each unit can be QA'd independently before merging. **Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作. **Use when**: `Approve C2` is recorded and writer packs exist (`outline/writer_context_pa…
Use when the user wants to create, generate, build, update, refresh, or improve their personal writing style guide from their own sent writing (Generate mode), OR when they ask the agent to write, draft, reply, rewrite, edit, polish, or humanize something in their voice (Use mode). Teach your agent…
Applies Strunk's Elements of Style principles when writing or editing prose. Triggers on "write clearly," "edit for style," "improve writing," or tasks requiring clear, vigorous English — documents, emails, reviews.
Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke with /edge-cases <problem> <checkpoint>.
Evaluates fundamental lexical comprehension and generation capabilities of multilingual LLMs across thousands of languages. It probes word-level translation, context-aware translation, translation-conditioned language modeling, and bag-of-words machine translation tasks to measure basic linguistic …
Evaluates large language models on Moroccan Arabic (Darija) across multiple-choice reasoning, instruction following, translation, summarization, and sentiment analysis. It probes dialect-specific linguistic features, script variability (Arabic vs. Arabizi), and real-world instruction-following capa…
Guide for writing effective technical documentation, specs, and markdown files. Use when creating or editing specs, documentation, READMEs, AGENTS.md files, or any markdown content in the codebase.