codex-skill-github-repo

Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, VC meeting ended, Minutes generated, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）、管理表情回复。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据时使用。

飞书幻灯片：创建和编辑幻灯片，接口通过 XML 协议通信。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。

Audit, implement, or repair Adobe Express add-on credits behavior. Use for 积分模块, credits, free_cnt, paid credits, zero-credit preservation, balance drift, successful-use deduction, payment-return refresh, page-reload balance persistence, purchase-delta balance updates, PayLink polling, and stale remote user/status problems.

Use for YiChongmimi Adobe add-on Git/GitHub collaboration: cloning one private repo per project, starting from latest main, branch naming, commit and PR rules, local Git hooks, forbidden artifacts, project registry updates, and collaborator handoffs.

Use when pushing, committing, submitting, publishing, or syncing YiChongmimi Adobe add-on project changes to GitHub. Covers branch safety, business-specific checks, PR creation/merge, forbidden artifacts, management repo status refresh, and AI-assisted handoff wording.

Use when syncing YiChongmimi Adobe add-on work from a local per-project GitHub repo into the local Codeup adobe monorepo without committing or pushing. Covers source/target mapping, pre-sync verification, non-deleting rsync rules, target re-verification, artifact cleanup, and handoff evidence before later Codeup push discussion.

Use when committing, pushing, creating a merge request, self-merging, or requesting review for verified YiChongmimi Adobe add-on changes in the Alibaba Cloud Codeup adobe monorepo. Applies after adobe-codeup-local-sync, preserves GitHub push workflows, uses simple commit messages plus handoff-first context, and defines light internal Codeup MR/review standards.

Diagnose and safely repair this Mac's local Codex/CC Switch/OpenAI CLI setup, including provider-history/sidebar issues, auth expiry, MCP/plugin failures, /goal approval behavior, and local proxy connectivity for Codex.

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".

生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务；默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。

Use this skill when helping users position, launch, diagnose, or plan a Xiaohongshu/RedNote graphic-text account based on the 知识猫 AI 实战课程. It covers account positioning, direction scoring, benchmark teardown, first 20 post planning, 14-day validation, and AI prompt-assisted content planning.

Generate an actionable HTML handoff for LivePolls pricing-page localization audits. Use when the user asks to check LivePolls app pricing pages across languages, compare other products against a known-good standard page such as ai_image_generator/pricing, identify missing non-English language packs from yichong_pricing_language R2 JSON files, review subscription copy/FAQ/benefits for payment-conversion risk, or produce a direct product-by-product HTML modification plan for engineers or translators.

Re-run the final LivePolls subscription benefit-copy audit and generate the actionable HTML used for AI-assisted pricing-page fixes. Use when the user asks to recheck LivePolls pricing pages after modifications, regenerate livepolls_subscription_benefit_research.html, audit weak subscription benefits, compare product pricing benefits against competitor pricing pages, or produce a direct product-by-product HTML fix guide focused on paid-plan benefits rather than localization, FAQ, unit, browser-rendering, or /api/order/plans issues.

Migrate an existing Adobe Express Add-on to template v2 conventions, including appRequest context injection, platform=adobe_addon, app_channel, Feishu/runtime error reporting, ErrorAlert server-translated errors, and Adobe sandbox fixes. Use when the user says 迁移, 适配, 接入新模板, appRequest, 飞书, ErrorAlert, adobe-app 开发规范, sandbox, or template-v2 for an existing Adobe add-on.

Generate AI-implementable product requirement documents (PRDs) from one-line product ideas, vague app/site/tool requests, or feature concepts. Use when the user asks for PRD, 产品需求文档, 需求文档, AI 可执行 PRD, 产品规格, MVP 方案, app/site/tool planning, or developer handoff docs for AI coding assistants.

Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.

Use NVIDIA SkillSpector to scan Codex, Claude Code, Gemini CLI, or other agent skills for security risks before installing or trusting them.

Use when changing Adobe add-on subscription/quota overlay logic, including cancelled-but-not-expired subscriptions, monthly quota, subscribed footer totals, subscription-aware canUseLimit/use behavior, and monthly-first deduction.

Build Microsoft Office add-in shell packages for TeachAny tools. Use when the user gives TeachAny /tools/{slug} URLs or asks to convert Google Workspace TeachAny shells into Office manifests for Word, Excel, and PowerPoint using the v3 pattern: one public HTTPS office-shell.html plus one manifest per tool.

Build, audit, or repair v2rayN-based smart split routing on macOS or Windows. Use when a user wants mixed proxy rules that separate domestic direct traffic, ordinary overseas proxy traffic, and high-risk overseas apps/sites that need a static residential IP, using the user's existing v2rayN nodes, sing-box/Xray cores, system proxy, TUN, or local mixed inbounds.

Read, extract, summarize, and source-check WeChat Official Account articles from mp.weixin.qq.com links. Use when a user asks to inspect a WeChat article, summarize key points, recover article metadata/body text, troubleshoot blocked WeChat article fetching, or find and verify related original information sources.

Use when creating or managing the 小黑旁白生物课 Xiaohongshu comic-learning column from Chinese K12 textbook chapters. Guides Codex through source reading, chapter extraction, life-based hook selection, episode bible, single-image comic script, Xiaohei narrator role, imagen/image_gen generation, Obsidian file placement, publish copy, QA, and archival loops.

Use this skill whenever the user asks to research AI app opportunity keywords, Sensor Tower-style app intelligence, ASO keyword opportunities, App Store or Google Play competitor analysis, Diandian popularity metrics, Similarweb/Semrush website-to-app opportunity discovery, or whether an AI keyword/direction is suitable for an iOS/Android MVP. This skill is especially relevant for prompts like "帮我调研这个 AI App 机会词", "这些词哪些可以先做", "用 Sensor Tower / 点点 / Similarweb 看看能不能做 App", "输出 Go/No-Go MVP 判断", or when the user provides screenshots, tables, chat notes, app store search results, competitor reviews, pricing notes, or website traffic data and expects a decision-oriented MVP research report.

Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

Claude Code CLI wrapper for non-Claude hosts - three modes. Review: independent diff review via claude -p. Challenge: adversarial failure-mode review. Consult: ask Claude about the repo with read-only file tools. Use when asked for "claude review", "claude challenge", "ask claude", "second opinion from claude", or "outside voice". (gstack)

Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with /context-save. Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments. (gstack)

Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume later. Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments, which was shadowing this skill. (gstack)

Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

Turn any markdown file into a publication-quality PDF. Proper 1in margins, intelligent page breaks, page numbers, cover pages, running headers, curly quotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft artifact — a finished artifact. Use when asked to "make a PDF", "export to PDF", "turn this markdown into a PDF", or "generate a document". (gstack) Voice triggers (speech-to-text aliases): "make this a pdf", "make it a pdf", "export to pdf", "turn this into a pdf", "turn this markdown into a pdf", "generate a pdf", "make a pdf from", "pdf this markdown".

Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required. Use when asked to "tune questions", "stop asking me that", "too many questions", "show my profile", "what questions have I been asked", "show my vibe", "developer profile", or "turn off question tuning". (gstack) Proactively suggest when the user says the same gstack question has come up before, or when they explicitly override a recommendation for the Nth time.

Pull data from a web page. First call on a new intent prototypes the flow via $B primitives and returns JSON. Subsequent calls on a matching intent route to a codified browser-skill and return in ~200ms. Read-only — for mutating flows (form fills, clicks, submissions), use /automate. Use when asked to "scrape", "get data from", "pull", "extract from", or "what's on" a page. (gstack)

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

Codify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the same intent run the codified script in ~200ms instead of re-driving the page. Walks back through the conversation, synthesizes script.ts + script.test.ts + fixture, runs the test in a temp dir, and asks before committing. Use when asked to "skillify", "codify", "save this scrape", or "make this permanent". (gstack)

把本地 HTML 文件或目录部署到飞书妙搭（Miaoda），生成可分享访问的 Web 页面并返回 URL；管理应用的创建、更新、列表和访问范围。当用户要把 HTML、静态网站或 Web demo 发布成可分享链接，或提到妙搭 / Miaoda 时使用。不用于：上传普通文件到云空间（用 lark-drive）、编辑飞书云文档内容（用 lark-doc）、创建飞书原生幻灯片 / 演示文稿（用 lark-slides）。

当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

飞书 / Lark 通讯录,用于按姓名 / 邮箱把员工解析成 open_id,以及按 open_id 反查员工的姓名 / 部门 / 邮箱 / 联系方式。当用户说出某人姓名而下一步需要发消息 / 加群 / 排日程时,先用本 skill 把姓名换成 ID;当输出里出现 open_id 需要展示成姓名给用户看,或用户直接询问某人的部门 / 邮箱 / 联系方式时,用本 skill 查。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生 OpenAPI。

飞书云文档 / Docx / 知识库 Wiki 文档（v2）：创建、打开、读取、获取、查看、总结、整理、改写、翻译、审阅和编辑飞书文档内容。当用户给出飞书文档 URL/token，或说查看/读取/打开某个文档、提取文档内容、总结文档、生成/创建文档、追加/替换/删除/移动内容、调整排版、插入或下载文档图片/附件/素材/画板缩略图时使用。文档内容中出现嵌入电子表格、多维表格、需要将重要信息可视化为画板（含 SVG 画板）、引用或同步块时，也先用本 skill 读取和提取 token，再切到对应 skill 下钻。使用本 skill 时，docs +create、docs +fetch、docs +update 必须携带 --api-version v2；默认使用 DocxXML，也支持 Markdown。