daymade

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.

Faithfully archive public WPS/KDocs/金山文档 links, especially embedded ProcessOn .pof mind maps and canvases, as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in or saving the document to an account.

Diagnoses Windows App (Remote Desktop / AVD / W365 / direct PC) connection problems on macOS: transport selection (UDP Shortpath vs WebSocket), VPN/proxy interference, and stuck "Configuring remote PC..." dialogs. Use when a VDI connection is slow/stuck, transport shows WebSocket not UDP, or Windows App freezes at a progress dialog. Not for general network diagnosis (use debugging-network-issues or tunnel-doctor).

This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.

Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.

Fetches Twitter/X post and Article content — text, author, engagement metrics and embedded media — downloading images locally and generating complete Markdown with image references. Use when retrieving a tweet's text or an X Article with images, or pulling post metadata for a Markdown/PKM record. Preferred over Jina alone for X Articles with images.

MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时). Diagnoses Tailscale, proxy, TUN, DNS and SSH-tunnel problems on macOS and Windows/WSL, e.g. Tailscale ping works but SSH fails, curl works but browser gets 503, Git/Docker fails behind the proxy, or downloads crawl despite a reachable proxy. Not for application-layer bugs (use debugging-network-issues).

Corrects ASR/STT transcription errors — homophones, garbled terms, person-name errors, mixed Chinese/English — with dictionary rules plus Claude's built-in AI, no external API key required. Use to clean meeting notes, lecture transcripts, interviews or speech-recognition text, even when the user only says "fix this transcript". Not for structuring a clean transcript into minutes (use meeting-minutes-taker).

查询 ChatGPT/Codex 重置公告及多个 Pro 账号的剩余额度、备用 Full reset；复用 Google 登录逐个核实并恢复网页账号，换算北京时间。区分 Tibo 官宣、未官宣的平台静默重置、banked reset 与账户级周期重置。Use when 用户问「什么时候重置」「额度什么时候恢复」「下次全员重置几点」 「banked reset 到了吗」「Tibo 说了什么」「usage limit when reset」，或说「额度突然回到 100%」「好像/肯定又重置了」，或问「几个账号都用完了吗」「哪个还满额」。必须用实时产品状态、独立用户实测与公告交叉核验；禁止因 Tibo Radar 没有新条目就否定已经发生的重置，并须把太平洋时间当场换算为北京时间。

Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fresh-host bootstrap. Use when writing or reviewing plan/apply wrappers or provisioners; when staging/production config may differ; when a rollout can mutate a shared gateway; or debugging drift, TLS, container restarts, DNS duplication, or snapshot contamination.

MUST be used right after changing any CLI color config (delta/bat/themes/lazygit pager) — renders the terminal's colored output to a PNG so Claude can actually SEE contrast, alignment, and highlighting instead of raw ANSI codes. Use for delta git diff colors, bat syntax highlighting, starship prompt, eza/ls colors, or ripgrep matches. Trigger phrases: 看终端效果, 终端截图, 验证配色, terminal screenshot.

Gated checklist for choosing a technology (library, framework, storage, data format, model, build-vs-buy, architecture) or reviewing a proposed one. If favorites-search is installed, MUST run it before external research. Returns surviving candidates with trade-offs, not a single pick. Use for 用哪个 / 选什么框架 / 要不要自建 / A 还是 B / 这个方案行不行, and before the agent commits to one. Not for research reports (use deep-research).

Writes educational Teams channel posts about Claude Code features and best practices, using templates emphasizing concrete examples and underlying principles (e.g. context engineering). Use when writing a Teams post or announcement to teach colleagues Claude Code usage, announce a feature, share a tip, or document a lesson learned.

Generates Chinese/Japanese speech with StepFun's Contextual TTS — default stepaudio-2.5-tts, stepaudio-3-tts for whisper/inline-() prosody. Replaces step-tts-2's voice_label with natural-language instruction. Use for emotional/prosody-controlled synthesis, batch voice lines, migrating from step-tts-2, or cloned voices (2.5/step-tts-2, not v3). Triggers on 阶跃 TTS, 语音合成, 配音. Not for transcription (use stepfun-asr).

Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking. Use when migrating from step-asr/stepaudio-2.5-asr, or hitting the misleading "model not supported" error (actually wrong endpoint). Triggers on 阶跃 ASR, 语音识别. Not for TTS with the sibling model (use stepfun-tts).

Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts). Use when the user wants to set up or change the statusline, switch minimal vs full layouts, show absolute token counts instead of a percentage, add cost via ccusage, or fix a statusline that is blank, silent, stuck, or stopped updating. Trigger phrases: 状态栏, 状态栏不显示, 状态栏空白, "statusline blank", "statusline broken".

已废弃的叙事型 PPT/幻灯片生成器（2026-08-07 起停止维护，不再接收更新）。做新 deck 请用 deck-creator：本 skill 的方法论（First Law 用户原话优先 / ABCDEFG 叙事框架 / baoyu-slide-deck 委托协议 / 四层目录治理）已整体并入 deck-creator 的 Route A · narrative，装有 deck-creator 的环境不要调用本 skill。外部用户：这是保留安装兼容的最终版本，将在后续大版本中物理移除。

This skill should be used when users want to search, discover, install, or manage Claude Code skills from the CCPM registry. Triggers include requests like "find skills for PDF", "search for code review skills", "install cloudflare-troubleshooting", "list my installed skills", "what does skill-creator do", or any mention of finding/installing/managing Claude Code skills or plugins.

Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.

Governs the Claude Code/Codex Skill surface: reconciles source/install/catalog-visibility drift without losing cold capability. Use when users ask how many Skills load, why the catalog is truncated, want routers visible while other bundles stay cold, or need duplicate/superseded-Skill or old-cache cleanup. Not for building a marketplace manifest (use marketplace-dev) or repo audits (use marketplace-health-check).

Creates, edits and benchmarks skills; supersedes the official skill-creator plugin, so when both are listed, use this one. Use when the user wants to create or improve a skill or run skill evals, or to distill work into a skill even without saying "skill": 把这次 session 做成一个 skill / 把以前的对话沉淀到 skill 里 / 从我认可的样例里提炼我的喜好.

Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.

Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages. Use this skill whenever the user mentions Scrapling, `uv tool install scrapling`, `scrapling extract`, WeChat/mp.weixin articles, browser-backed page fetching, or needs help deciding between static and dynamic extraction.

Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified. Use when the deliverable IS a visual HTML report, or the user asks for an HTML/web presentation. Load data-visualization-discipline for chart judgment. Not for chat status or Markdown prose unless asked to become a report; not for PowerPoint (deck-creator Route C).

Extracts files from repomix-packed repositories, restoring original directory structures from XML/Markdown/JSON formats. Activates when users need to unmix repomix files, extract packed repositories, restore file structures from repomix output, or reverse the repomix packing process.

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix.

读取 Word/WPS 审阅后的 docx，把批注（comments）与修订（track changes）提取成可逐条裁决的 markdown 对账表或 JSON。触发场景：对方批注完的合同/协议/书稿/报告回来了要读意见；「提取 docx 批注」「审阅意见对账」「读一下修订」「谁批了什么、批在哪」；WPS 云文档/Word 在线协作 导出的审阅稿；收到带修订模式改动的回稿要看对方改了什么。核心保证：修订感知——python-docx 裸读会漏掉修订插入（w:ins）的内容、认不出整段删除（w:del），本 skill 走 OpenXML SDK 引擎 不漏。只读，不改对方文件。边界：生成/排版 docx → docx-creator 或 minimax-docx；PDF 批注不在范围。

Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and rollout identity/fork lineage. Use when the user asks what they told Codex, wants a Session ID, or evidence of what a run did. Not for Claude Code (use read-claude-code-history); with no platform named, start at local-conversation-history.

Reads or exports the COMPLETE transcript of a Claude.ai web conversation — private /chat/... and public /share/... links — via Claude.ai's internal API in the user's logged-in Chrome, plus its files. Use when the user pastes a claude.ai link and asks to read, summarize, export, archive, or extract it — "读这个对话", "导出网页版对话", "拉到本地". Local sessions: read-claude-code-history; exported files: claude-export-txt-better.

Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts. Use when the user asks what was said, wants a session ID or original context, or needs proof of what a session contained. Not for Codex (use read-codex-history); with no platform or several named, start at local-conversation-history.

Sets up QA testing processes: test strategies, Google Testing Standards test cases, P0-P4 bug tracking, quality metrics, progress reports, autonomous execution via master prompts, and OWASP security testing, with third-party QA handoff docs. Use when establishing QA infrastructure, writing test cases, executing test plans, or tracking bugs. Not for auditing an already-rendered UI (use frontend-visual-qa).

Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".

Transforms vague prompts or feature requests into precise, testable specifications using EARS (Easy Approach to Requirements Syntax) grounded in relevant domain theories (GTD, BJ Fogg, Gestalt). Use when requirements lack triggers or measurable outcomes, or the user asks to "optimize my prompt" / "improve this requirement" / "make this more specific".

Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".

Only for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse is plausible. Use when the user explicitly references earlier work, existing code, history, or prior decisions, or says 以前做过, 已有代码, 别重复造轮子. Not for current tests, files, bug fixes, or mechanical verification. Produces a reuse/adapt/reject receipt; zero hits never prove absence.

【DEPRECATED · 已废弃】本 skill 已于 2026-08-07 停止维护。对作者本机环境：其方法论已整体并入 deck-creator（私有仓 daymade-skills-pro 的 Route B · draft），装有 deck-creator 的环境不要调用本 skill。 对外部用户：这是最终版本，保留安装兼容，不再接收更新——你可以继续按本文档使用， 但请知悉上游已冻结。将在 daymade-docs v2.0.0 中物理移除。

Two pipelines ending at a scanner-look PDF. (1) Phone photos of paper documents (contracts, stamped certificates, receipts, forms, handwritten notes) → clean scanner-quality PDF: perspective rectification + noteshrink whitening + A4 assembly + mandatory whole-document check. Trigger: "把照片 做成扫描件", "photos to scanned PDF", "make this look scanned", "手机拍的 文档转 PDF", "盖章文件扫描", replacing pages in an existing scanned PDF, any CamScanner-like request. (2) A digital document with no signature yet (rendered docx/PDF, confirmation form, contract draft) → make it look hand-signed and scanned: synthesize a handwriting-style signature, composite it onto the signature line, apply the same scan-look post-processing. Trigger: "帮我做个手写签名", "生成签名盖到这份文件上", "做成签过字的扫描件", "synthesize a signature", any request for a document that needs to look signed without a real photographed signature. Do NOT hand-roll levels/contrast enhancement for scan-look — tried and rejected twice; this skill's pipeline is the proven one.

生成 A 股医药行业日报：从新浪财经抓取 20 只核心医药股实时行情，分析 7 大细分赛道排名、涨跌榜 TOP 3、资金流向，然后通过飞书发送富文本日报。 覆盖恒瑞医药、百济神州、智飞生物、药明康德、迈瑞医疗、片仔癀、云南白药等 20 只核心标的。 当用户需要 医药日报、医药行业日报、pharma daily report、 新浪财经医药数据、A 股医药板块分析、飞书推送医药数据、 制药行业快报 时触发。也适用于"帮我看一下今天医药板块"、 "给飞书发一份今天的医药数据"等口语化请求。

Bridges Claude Code and Codex sessions when native tools can't reach the target. Use for 跨产品通信 / 脚本回帖 / 送达排查: cross-product messages, hooks or scripts posting to a session, verifying delivery (Held messages included), shared-work ownership, or an inbound peer assertion, or for cross-machine pairing. Not for ordinary same-product or parent/subagent messaging (use native tools), spawning agents, or moving full history.

Converts a PDF into one self-contained, readable HTML file that preserves images, tables, charts and reading order — optionally translating it into another language while keeping every figure. Uses structured extraction (PyMuPDF), font-size-driven layout, compressed base64-inlined images (a single portable file), and mandatory headless-Chrome visual verification. Use whenever someone wants to READ a PDF as a web page or clean document, turn a PDF into HTML, or translate a PDF into another language while keeping its images/tables/charts intact — e.g. "PDF 转 HTML", "把这个 PDF 转成中文网页版", "make this report readable", "translate this PDF but don't lose the charts", "I just want to read this PDF on my phone". Distinct from doc-to-markdown (plain Markdown text) and pdf-creator (Markdown→PDF) — this one produces a styled, image-faithful HTML reading experience.

Converts Markdown to print-ready PDF with proper Chinese typography, themes and a visual self-check. Use for Markdown → PDF, including documents formatted for printing or mobile reading. Not for Word/WPS files or Word output (use docx-creator).

Switches or repairs an OpenClaw instance's model config: changes the default model, adds model definitions, and fixes 401 "Invalid token", "No available channel / model not found", "Thinking level X is not supported", or a config edit that doesn't take effect. Use for 切换模型/换模型/升级模型 or 模型配的错了. Not for plain config audits (use openclaw).

Audits, diffs, copies, and lists providers/models, adds models, and switches the default model in local openclaw.json configs; diagnoses gateway/plugin failures (down, parked, broken, or out of date after an upgrade). Use for 虾/龙虾 config audits. Not for model-error repair (use openclaw-model-switch).

Send a single one-off message to a WeCom (Enterprise WeChat) group bot. Use this skill whenever the user says "/notify-wecom", "send a quick WeCom message", "企微通知一下", "临时发一条企业微信", or any one-shot notification that does not need a reusable template or setup workflow.

Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.

Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.

Transforms raw meeting transcripts into structured, evidence-based meeting minutes — merges multiple versions without losing content, reviews existing minutes against the transcript for missing items, and identifies anonymous speakers (Speaker 1/2/3, 发言人1). Triggers on 会议纪要, 会议记录, 整理纪要, 妙记转纪要, "write meeting minutes", "merge these minutes". Not for fixing ASR/STT errors first (use transcript-fixer).

Runs a 6-dimension evidence-based health audit of this skills marketplace repo — code safety, docs/SSOT, security/PII, PR/issue triage, manifest integrity — via a parallel workflow, then verifies findings by priority. Use for 全面体检 / 检查仓库状态 / 审计一下仓库, a pre-release sweep, or "is this repo OK" even without saying "workflow". Not for building marketplace.json (use marketplace-dev) or cache drift (use skill-governance).

Builds and maintains Claude Code plugin marketplaces: converts a skills repo to spec-valid marketplace.json, adds/updates plugin entries, and migrates skills into or between suites. Use for marketplace.json, plugin distribution, one-click install, or "put these skills in a suite". Not for repo health audits (use marketplace-health-check) or cache reconciliation (use skill-governance).

Designs and audits macOS launchd watchdogs. Use for LaunchAgent/LaunchDaemon setup, plist changes, scheduled self-healing, repeated notifications, apps reopening after quit, crash or repair loops hammering the Mac, or a watchdog alert shown as Script Editor. Covers stop/disable/restart, cooldown/backoff, notification throttling and alert decisions. 中文：launchd 守护进程、常驻任务、开机自启、后台监控、定时自愈、通知来源排查。

Diagnoses and repairs macOS TCC dialogs and silent denials: Full Disk Access, Screen Recording, Microphone, Camera, Accessibility, Automation. Use for recurring prompts, LaunchAgent/uv jobs that fail only in background, broken grants, or automating Full Disk Access (权限弹窗 / 授权了没用 / 完全磁盘访问). Checks requester and grants first. Not for launchd design (macos-watchdog) or app permission UX (developing-ios-apps).

Diagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign clones, developer caches. Use when a Mac is low on storage, shows “Caching needs more space”, or before deleting anything to avoid data loss. Not for Windows/Linux or permission issues (use macos-permissions).

Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory. Use when the platform is unknown or plural ("what was I working on", "we discussed this once") and for any Kimi CLI history. When platform and action are already clear, load that skill directly.

Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT Pro OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'.

Co-creates a personal investment-research LLM Wiki (Karpathy's pattern) by interviewing the user for THEIR OWN analysis framework, not a template — a living CLAUDE.md of pure markdown + wikilinks, no RAG in place of compilation. Use to build a compounding 投研第二大脑 / 投研知识库 / 个人投研 wiki, ingest research reports / earnings calls into an existing wiki, or run post-earnings prediction→fulfillment reviews.

Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.

Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).

Routes any Feishu/Lark/Doubao operation through the version-matched lark-cli domain guide embedded in the installed CLI, then executes and verifies the task. Use for 飞书/Lark/Doubao docs, drive, sheets, Base, wiki, minutes, meetings, calendar, IM, mail, tasks, approval, apps, auth/scope, resource URLs or tokens, and lark-cli troubleshooting. This is the single Lark entry point; use ima-copilot instead for Tencent IMA.

Drives the Kimi desktop app (Kimi.app) via computer-use to query its built-in data plugins — 天眼查、同花顺 iFinD、SEC、IMF and more — through the user's own logged-in session, no API keys needed. Use for "用 Kimi 查" / "操作 Kimi 客户端" / "Kimi 插件", or fetching company, financial, academic, or legal records with no dedicated API. Not for kimi.com browser automation (use kimi-webbridge) or direct iFinD API access.

Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation. Use for multiple UI versions, interaction alternatives, progressive-disclosure options, or when styling is fine but hierarchy/workflow/interaction feels off. Not for static visual-style calibration (use design-style-picker) or a settled CSS tweak.

Installs, diagnoses, repairs, and personalizes the official Tencent IMA skill (a wrapper around upstream ima-skill, not a replacement), including fan-out search across IMA knowledge bases with priority boosting. Use when the user mentions IMA / 腾讯 IMA / ima-skill, needs IMA API key setup, 知识库搜索 / 笔记搜索, or hits "Skipped loading skill(s) due to invalid SKILL.md" (ima-skill's missing-YAML-frontmatter bug).

This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.

Scans and removes sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history, then verifies and force-pushes safely. Use for 清理敏感数据 / 历史重写 / 泄露, "scan sensitive data", "clean git history", "remove secrets from repo", or before any force push to a public repo. Not for local-only Git recovery (use git-safety-net) or ordinary repository setup (use auto-repo-setup).

Reviews or re-reviews a contributor PR as repository maintainer — a closed PR reconsidered, or a sweep of open PRs — against the live base with immutable snapshots and three-way merges. Use for a PR URL/number, "main changed, review again", "review all open PRs", "fix the rest ourselves?", or merge readiness. Not for GitHub CRUD (use github-ops), your own PR (use github-contributor), or merging without fresh review.

Operates GitHub via gh CLI and REST/GraphQL — PRs, issues, Actions, repos, collaborators, org permissions, 2FA — with explicit target, authorization, and independent readback. Use when a write reports success but state didn't change, or choosing gh/REST/GraphQL/UI-only. Not for local Git recovery (use git-safety-net), maintainer PR review (use github-review-pr), or upstream contribution (use github-contributor).

Ships pull requests to open-source projects you don't maintain — CONTRIBUTING compliance, PR-size/scope checks, minimal-diff implementation, AI-disclosure PR descriptions, and rebase or bot-review replies. Use for 提 PR / 上游 PR / 贡献代码, "open a PR", "fix this upstream", "rebase against main", "respond to the bot review". Not for reviewing PRs as maintainer (use github-review-pr) or general GitHub CRUD (use github-ops).

Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commits, squash-merge uncertainty. Use when the user fears lost work, wants to recover a commit, asks if a branch is actually merged, asks whether a branch, worktree or clone is safe to delete, or wants one clean main (误删分支 / 还有没有丢的东西). Not for GitHub PR operations.

Analyze Google Takeout exports of Gemini conversation history. Use when the user mentions Gemini takeout, Gemini export, Gemini history, Gemini conversation analysis, Google Takeout zip analysis, or drags a takeout zip into the project. Also use when the user asks to "analyze my Gemini data", "what did I talk to Gemini about", or wants to extract insights from Gemini chat logs.

Gangtise (岗底斯投研) OpenAPI skill suite installer and diagnostic tool. One-click install 19 official skills (data, research, utility), configure accessKey/secretAccessKey, run health diagnostics. Trigger when user mentions Gangtise, 岗底斯, any gangtise-* skill, credential setup, or reports errors like 'token is invalid' / '接口地址错误'.

Audits already-rendered UI — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI implementation to find typography, overflow, responsive, routing, data-viz, browser-output, or native-shell defects, or to compare a render against a reference. Not for greenfield UI design (use ui-designer) or QA-program setup (use qa-expert).

Fixes broken line wrapping in Claude Code exported .txt conversation files — rebuilds tables, paragraphs, paths and tool calls hard-wrapped at a fixed width. Use for an export (YYYY-MM-DD-HHMMSS-*.txt) with broken tables, split paths, or mangled tool output, or "fix export" / "make export readable". Not for a live web conversation (use read-claude-web-conversation) or session history (use read-claude-code-history).

Routes finance: Bigdata/RavenPack, US fundamentals/yfinance, A-share news/policy, sector Top N/公告, Gangtise/岗底斯 setup. Reads one bundled specialist. Pharma reporting and general argument review keep their own direct entries.

Collects real financial data for any US publicly traded company from free public sources (yfinance) and outputs structured JSON for downstream skills (DCF modeling, comps analysis, earnings review): market data, historical financials, WACC inputs, analyst estimates — never fabricated fallback values. Use to collect or pull financial/market data, or gather DCF inputs, for a ticker.

Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API — no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection — even if the user just says "save this". Also covers owner-exported .docx → Markdown.

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.

Create, parse, and control Excel files on macOS. Professional formatting with openpyxl, complex xlsm parsing with stdlib zipfile+xml for investment bank financial models, and Excel window control via AppleScript. Use when creating formatted Excel reports, parsing financial models that openpyxl cannot handle, or automating Excel on macOS.

Places existing images onto an Excalidraw whiteboard, turns a slide deck into clean per-slide images, and inspects a .excalidraw file. Use whenever someone mentions Excalidraw, a whiteboard/canvas, .excalidraw, 白板 or 画板 — e.g. "put these screenshots on my board" — or a workshop delivered by hand-drawing over screenshots on a shared canvas. Not for generating a diagram from a text description.

Download, export, save, or package images from a Google Gemini conversation/chat/app page, especially uploaded images or generated image previews visible in a Gemini thread. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed image files, renaming them in order, and producing a ZIP archive.

Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files via Frodo API. Supports full export (all history) and RSS incremental sync (recent items). Use when the user wants to export Douban reading/watching/listening/gaming history, back up their Douban data, set up incremental sync, or mentions 豆瓣/douban collections. Triggers on: 豆瓣, douban, 读书记录, 观影记录, 书影音, 导出豆瓣.

Produces Word (.docx) and exports existing Word/WPS manuscripts to PDF, preserving revisions, tables and images, especially Chinese formal documents via a verified OpenXML generator with mandatory visual verification. Use for 生成 Word 文档 / 写合同 docx / 把 markdown 转成 Word / 中文排版. Not for Markdown → PDF (use daymade-docs:pdf-creator).

Routes docs: Word/PDF/PPTX→Markdown; MD/Word→PDF; create Word; PDF HTML/translate; Excel/xlsm/macOS; photo/signed scans; Mermaid; DOCX review; post-change docs. Reads one bundled Daymade specialist. New slide decks use deck-creator when installed; generic PDF reading/editing and spreadsheet analysis stay with their own Skills. Retired ppt-creator stays manual-only.

Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change. Modes: (1) POST-CHANGE GOVERNANCE — when code, scripts, config, env vars, ports, paths, deployment, auth, tests, or a documented procedure changed; also "which docs are now wrong", "check docs for inconsistencies", "过时的命令/路径", "文档同步". Use it even when the user mentions only the change and never the docs — updating them is part of the change, not optional cleanup. (2) CONSOLIDATION — "clean up docs", "documentation bloat", "reduce documentation sprawl", "consolidate documentation", "too many doc files", "merge redundant docs", "merge these docs", "文档太多/太乱", multiple files covering the same topic, or documentation exceeding 500 lines across multiple files on similar topics. Finds stale copies of a fact changed in only one place, values that should never have been persisted (counts, totals, "N items", restated summaries), rival definitions that drift apart, and orphaned cross-references.

Converts DOCX/PDF/PPTX to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJK bold spacing, attribute noise, and code blocks; for PDFs also strips OCR garbage blocks, repeated headers/footers/watermarks, and absolute image paths from pymupdf4llm output. Benchmarked best-in-class (7.6/10) against Docling, MarkItDown, Pandoc raw, and Mammoth. Trigger on "convert document", "docx to markdown", "parse word", "doc to markdown", "解析word", "转换文档".

结构化压力测试一个论点（devil's advocate / 魔鬼代言人）：把论点拆成显性断言与隐性假设（A1/A2 编号）， 逐条在用户给定的证据材料里检索带出处的反方论证，标 High/Medium/Low 风险等级，补基础比率外部视角， 最后给出「可监测的证伪信号」清单；输出结构化 findings + 人读叙事双层结果。找不到反证时如实声明「未找到」， 绝不编造。复刻自 LinqAlpha（对冲基金 AI 产品）公开的 Devil's Advocate 架构，叠加 CIA 结构化分析技术与 RAND 假设规划。当用户要「压力测试 / 唱反调 / 找盲点 / 拆假设 / 挑战这个论点 / bear case / 红队这个方案 / 上投委会前过一遍 / pressure test my thesis」，或拿着投资论点、IC memo、研究结论、商业决策要人挑刺时， 用本 skill——即使用户没说出"魔鬼代言人"这个词。

Builds and ships iOS/macOS apps with XcodeGen, SwiftUI and SPM: Xcode build fixes, device deployment, Apple Developer signing/notarization, CI/CD pipelines. Use for XcodeGen project.yml setup, "Library not loaded @rpath" crashes, code-signing errors (Error -25294, adhoc fallback), or Electron notarization failures. Not for TCC permission dialogs (use macos-permissions) or disk cleanup (use macos-cleaner).

Batch-generate and compare visual design directions so a user can choose the style they actually want. Use when the user says they cannot describe an abstract visual style, asks for many style options, wants to choose from generated UI/design-system images, rejects outputs as too colorful/too dead/too generic, or needs an existing UI/design system evolved without discarding current assets.

Generates evidence-tracked research reports with citations, source governance, and multi-pass synthesis. Use for a research report, literature review, market/industry analysis, or competitive landscape: 帮我调研一下 / 深度研究 / 综述报告 / research this topic / write a report on. Not for choosing between options (use tech-selection) or code-based competitor analysis (use competitors-analysis).

Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for ECONNRESET / RST_STREAM / SSE stalls, CDN/CGNAT timeouts or certificate errors, throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Not for known Tailscale/TUN/DNS/proxy-path conflicts (use tunnel-doctor).

A-share sector research: computes board-wide Top N gainers, cross-checks week/month announcement windows across two sources, and grades market-sentiment evidence (L1–L3), via parallel Agent Team execution with fresh-context adversarial verification. Use for 「XX 行业 Top N/Top 10 标的」, 「这些标的最近一周/一个月发过哪些公告」, 「判断 XX 行业/板块现在的市场情绪」, or 「用 Agent Team 做行业投研」/对抗验证行业研究结论。

数据可视化的判断层 SSOT——画任何图表、dashboard、看板之前先加载它，不是画完之后。管"该不该这么画"：这张图想让读者得出什么结论、用均值还是中位数、能不能聚合、堆叠还是折线、能不能上双轴、配色与颜色数量、同一实体跨图是否同色同位、表格该留几列。介质无关：HTML 报告页、React/Vue dashboard、PPT 原生图表、matplotlib/plotly/ECharts/D3、渲染成 PNG 的图，一律适用。Use when 动手画图之前，或评审既有图表（"这几张图有什么问题"、"图例为什么不一致"）。Not for 报告页的排版/组件/交互（用 report-with-html:report-with-html）或 PPT 原生图表的实现与渲染陷阱（用 deck-creator:deck-creator）。

Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.

Continues interrupted Claude Code work after local history is read and reconciled — reconstructs the original outcome, unfulfilled requests, and the next action. Use when given a Claude Code Session ID, asked to pick up prior Claude work, told a run was interrupted or compacted, or asked to take over without `claude --resume`. Not for Codex sessions (use continue-codex-work).

Clones and audits competitor repositories into evidence-based intelligence with file:line citations. Use to track competitors, add a competitor repo, review competitor code, compare capabilities, build a competitor landscape, or check for code updates: 竞品分析 / 竞品 / competitor scan / analyze competitor / compare with X / latest competitor code. Not for market research without code (use deep-research).

Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex generated images, open a local image gallery, inspect ~/.codex/generated_images, view a Codex image output folder, or browse image files produced by Codex.

Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. Use when Codex shows ~258K context, you want 500K or 1M tokens, auto-compaction fires too often, or model_context_window/model_auto_compact_token_limit needs repair. Not for changing the selected model or other Codex settings.

Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems. Focus on systematic investigation using Cloudflare API to examine actual configuration rather than making assumptions.

Generates professional animated CLI demos as GIFs using VHS terminal recordings. Use to create terminal demos, record CLI workflows as GIFs, generate animated documentation, build demo tapes for README files, or showcase any command-line tool visually: record terminal / VHS tape / demo GIF / animate my CLI.

Analyze Claude Code and Claude Desktop Code token usage, cost, quota burn, model mix, cache read/write, and 5-hour block consumption using ccusage evidence. Use when the user asks why Claude quota was exhausted, whether a model such as fable/opus/sonnet is unusually expensive, how many tokens were spent today or historically, or needs a human-friendly explanation of local Claude Code CLI/Desktop usage.

Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows. Use for multi-provider setup, switching models, csk/csd/csg aliases, CLAUDE_CONFIG_DIR, or ~/.claude-profiles. Owns profile-drift troubleshooting (missing skills/hooks, symlink drift, settings drift) and context-window setup ([1m] marker vs CLAUDE_CODE_MAX_CONTEXT_TOKENS).

Diagnose and resolve Claude Code plugin and skill issues. This skill should be used when plugins are installed but not showing in available skills list, skills are not activating as expected, or when troubleshooting enabledPlugins configuration in settings.json. Triggers include "plugin not working", "skill not showing", "installed but disabled", or "enabledPlugins" issues.

Migrates Claude Code personal memory (the per-project memory/ directory) into tool-agnostic reference docs so other AI CLIs that auto-load AGENTS.md (Codex primarily) can read the same user profile and preferences. Use when the user says "migrate my memory", "my memory is locked to Claude Code", "make Codex/Cursor read my profile", or reports memory has grown bloated with content that should be shared across tools. Also use it to retire a project's auto memory entirely (turn it off, move everything into documents, archive the directory).

Optimizes or restructures CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user asks to optimize, audit, 精简/瘦身/重构, or split instruction files, asks for their best practices (最佳实践), sees Memory files taking a large share of /context, reports rules in instruction files being ignored, or a task starts moving instruction sections. Not for generic task drift unless instruction files are in scope; not for moving memory entries into docs (use claude-code-ops-router).

睡前/离开前额度耗尽时，设置一次性本机定时器，在 Claude 订阅额度重置后自动发一条极简 claude -p 消息，立刻开启新的 5 小时用量窗口——用户睡醒时新窗口已跑掉大半，等于白赚一个 冷却期。Use when 用户说「还有 X 小时重置额度，帮我定时戳一下 Claude」「我去睡觉了， 到点 ping 一下开启新窗口」「额度用完了，重置后帮我踩个点」「设个定时器开启新的 5 小时 冷却期」，或提到 定时戳、戳 Claude、quota ping、开窗、额度重置后自动发消息。 仅限一次性定时任务与 macOS 本机（caffeinate/BSD date）；周期性任务用 /loop 或 cron， 查询 ChatGPT/Codex 何时重置用 tibo-reset-codex，分析额度为什么烧完用 claude-usage-analyst。

Routes Claude Code: plugin/Skill repair, marketplace, statusline, model profiles/source sync, 1M/[1m] context, usage/quota reset ping, memory→docs, .txt repair, turning auto memory off. Reads one bundled specialist; history, hooks, and Lark keep their own entries.

Writes, tests, registers and debugs Claude Code hooks (PreToolUse, PostToolUse, SessionStart, Stop) that turn a rule the model keeps breaking into a hard gate. Use when the user wants to block or intercept a tool call, add a guard rail, fix a misfiring hook, or says 拦截 / 守卫 / 钩子 — including "make it stop doing X".

Programmatic screenshot capture on macOS. Find window IDs with Swift CGWindowListCopyWindowInfo, control application windows via AppleScript (zoom, scroll, select), and capture with screencapture. Use when automating screenshots, capturing application windows for documentation, or building multi-shot visual workflows.

Fetches real, citable Bilibili (B站) video data — stats, metadata, tags, and full danmaku text — via login-free API calls, never hand-typed or estimated. Use when citing view/like/favorite counts, analyzing why a video performed, or archiving a Bilibili source into a knowledge base. Accepts BVID, av numbers, b23.tv links, or full URLs; subtitles and 收藏夹 (favorites) enumeration need the user's Bilibili login.

Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/* REST endpoints — structured financials, prices, analyst estimates, entity-sentiment series, annotated chunk search, screener. Use when the Bigdata MCP's tearsheets/search feel thin and you need the machine-readable substrate: mentions of Bigdata.com, RavenPack, a bd_v2_ key, rp_entity_id, or chunk/query_unit cost.

Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company, or product whose success looks inflated — splitting marketing bubble from real signal, then mapping the validated playbook onto the user's own resources. Use for 尽调/对标/拆解 a competitor, 抄/偷师 their playbook, or suspecting 水分/泡沫 in claims. Prefer over deep-research when debunking inflated claims, not a neutral briefing.

Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator handoff. Use when a repo won't run, a teammate onboards, hook output duplicates, or commit/push/conflict needs guarding. Not for lost-commit recovery (use git-safety-net), GitHub ops (use github-ops), or history scrubbing (use github-sensitive-data-cleanup).

Routes audio: StepFun ASR/语音识别, StepFun TTS/配音, transcript/妙记→会议纪要, merge/review minutes. Reads one bundled specialist; generic ASR and correction stay direct.

Transcribes audio or video to speaker-labeled, timestamped text, locally with MLX on Apple Silicon or remotely. Use for 转录 / 录音转文字 / 说话人分离 / 字幕, and also for preparing audio for ASR without transcribing: 转格式, 降采样到 16kHz, merging recorder segments, or compressing and speeding up audio before 飞书妙记 — even when it looks like a one-line ffmpeg job.

抓取 A 股消息面情报：从财联社、华尔街见闻、金十、新浪 7x24、东财快讯、 证监会/央行/上交所/财政部政策公告、东方财富股吧等公开来源抓取与股票相关的 新闻、政策、情绪，输出结构化 JSON 或 Markdown。 当用户提到“A 股消息面”、“抓新闻”、“个股消息”、“政策监管”、“股吧情绪”、 “财联社”、“东财快讯”、“市场情绪”或需要把某只股票相关的公开情报聚合出来时 触发。也适用于“帮我看看 000001 最近有什么消息”这类口语化请求。

Fixes web search on an agent whose model backend can't run it: a relay/reseller proxying Claude or Codex returns empty instead of failing. Use when web search returns nothing, a model insists a shipped product doesn't exist, someone wants to give an agent internet access, or the user is on a third-party base URL, relay, or 中转站. Diagnoses which built-in tools are dead, removes them, and installs a working replacement.