daymade-skills

Fetch comprehensive, login-free data for any Bilibili (B站) video — title, UP name and follower count, publish date, partition, tags, per-part cids, live stats (view, like, coin, favorite, share, reply, danmaku), and full danmaku (bullet-comment) text. Use this skill whenever working with a Bilibili video and needing real, citable numbers or metadata — ingesting a Bilibili source into a knowledge base, analyzing why a video performed, verifying a creator's claimed metrics, building a case study, or any time a Bilibili view/like/favorite count is about to be written into a document — fetch it, never hand-type or estimate it. Accepts BVID, av numbers, b23.tv short links, or full URLs. Subtitles are also covered but require the user's Bilibili login.

Programmatic screenshot capture on macOS. Get window IDs via Swift CGWindowListCopyWindowInfo, capture specific windows with screencapture -l, and control application windows via AppleScript. Supports multi-shot workflows for capturing different sections of the same window. Use when taking automated screenshots, capturing application windows, or creating visual documentation

Generate professional animated CLI demos and terminal recordings with VHS. Supports automated generation, batch processing, and interactive recording for documentation and tutorials

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

Discover, clone, update, and analyze competitor repositories with evidence-based competitive intelligence. Use when tracking competitors, reviewing competitor source code, adding a competitor repository, comparing product capabilities, building a competitor landscape, checking latest competitor code, or when the user says 竞品分析, competitor scan, analyze competitor, or compare with X. Repository-backed findings must come from local cloned code with file:line citations; market-landscape claims must cite their source and volatility.

Claude Code operations suite that bundles archive-aware local conversation discovery across Claude Code and Codex, internal-timestamp full-event session search and recovery, interrupted-work continuation, plugin/skill troubleshooting, CLAUDE.md progressive disclosure optimization, statusline configuration, exported .txt repair, full claude.ai conversation extraction with tool-call rendering and file download, plugin marketplace development, multi-provider profile isolation for running Kimi/GLM/DeepSeek/StepFun/Anthropic in separate windows, local source sync for Claude/Codex skill installs, and terminal-output-to-PNG rendering for visual CLI verification under one shared namespace. Install once to get the full Claude Code power-user toolkit.

Documentation suite plugin that exposes document conversion, Mermaid diagram generation, PDF/PPT creation, and documentation cleanup skills under one shared namespace

Financial data and investment-research suite covering the full China A-share and global equity data pipeline: Bigdata.com (RavenPack) structured financials and news sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite installation and orchestration, A-share news and policy aggregation, and A-share pharmaceutical sector daily reporting. Install once for the complete financial data workflow.

Audio processing suite covering the full speech pipeline: ASR transcription (Qwen3, StepFun) with batch-mode guards against music-only repetition-loop hallucinations, speaker diarization and CAM++ voiceprint identification for multi-speaker recordings, transcript error correction, structured meeting minutes generation, and TTS voice synthesis (StepFun). Install once for the complete audio workflow.

Daymade skills core suite. Bundles skill creation, quality review, governance, and marketplace development tooling under one shared namespace. Existing-skill edits use an old-vs-new capability audit and content-bound packaging attestation so prompt compression cannot silently delete runtime contracts. When the official skill-creator plugin is also installed, skill-creator detects the coexistence and offers a consent-based, reversible SessionStart routing hook so the daymade edition wins deterministically; on machines without the official plugin nothing is ever installed.

Generate format-controlled research reports with evidence tracking, source governance, and multi-pass synthesis. V6.1 adds: source accessibility (circular verification forbidden, exclusive advantage encouraged). Enterprise Research Mode: six-dimension data collection, SWOT/barrier/risk frameworks, and three-level quality control for company research

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, export, backup, sync, collection.

Create, parse, and control Excel files on macOS. Professional formatting with openpyxl (font colors, fills, borders, conditional formatting), complex xlsm parsing with stdlib zipfile+xml for investment bank financial models, and Excel window control via AppleScript (zoom, scroll, select). Use when creating formatted Excel reports, parsing financial models, or automating Excel on macOS

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

Extract Feishu (Lark) Docs, Wiki pages, Wiki collections/hubs, spreadsheets, and Minutes (妙记) transcripts into clean high-fidelity local Markdown. The primary path is the lark-cli API — programmatic extraction with no LLM rewriting of the body — which recursively follows a collection's reference graph (mention-doc / sheet / cross-tenant links) and uses error codes to resolve permission boundaries precisely; a browser-DOM path is the fallback only when lark-cli cannot reach the content. Use this whenever the source is a Feishu/Lark URL and fidelity matters — including 导出飞书文档/合集/妙记转写, 把飞书 wiki/知识库转 markdown, scraping or archiving a Feishu collection, exporting a Feishu Minutes/妙记 transcript, or saving a Feishu page locally — even if the user only says clipping, archiving, converting, or "save this". Also covers the permission-denied path (owner-exported .docx → faithful Markdown with heading/highlight restoration).

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating, editing, or pushing a PR to a third-party GitHub repo — submit a PR, open a PR, fix this upstream, rebase against main, respond to the bot review, an owner/repo target, or 提 PR / 上游 PR / 贡献代码 / rebase 冲突 / 回应维护者.

Comprehensive GitHub operations using gh CLI and GitHub API for pull requests, issues, repositories, workflows, and API interactions

Complete internationalization/localization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting. Use when setting up i18n for React/Next.js/Vue apps, auditing existing implementations, replacing hard-coded strings, ensuring proper error code mapping, or validating pluralization and date/time/number formatting across locales

Develops iOS applications with XcodeGen, SwiftUI, and SPM. Use when configuring XcodeGen project.yml, resolving SPM dependency issues, deploying to devices, handling code signing, debugging camera/AVFoundation, iOS version compatibility issues, or fixing Library not loaded @rpath framework errors. Includes state machine testing patterns for @MainActor classes

One-stop companion and installer for the official Tencent IMA skill (ima.qq.com). Installs upstream ima-skill to Claude Code/Codex/OpenClaw via npx skills add, guides API key setup, detects and fixes known issues (including the missing-YAML-frontmatter bug in submodule SKILL.md files) with user consent, and implements a personalized fan-out search strategy with priority-based knowledge base boosting and silent truncation detection

Evaluate any LLM behind an OpenAI- or Anthropic-compatible endpoint across four dimensions — speed (TTFT + thinking-aware tokens/sec), concurrency/stability (success rate, p50/p90, breaking point), Anthropic protocol compliance (thinking-block trigger rate), and quality regression against your own accumulated use cases (blind-judge precision). Use to benchmark a model, verify a tokens-per-second claim, compare models head-to-head, or vet a newly released model before adopting it.

Find and access AI/LLM model brand icons from lobe-icons library in SVG/PNG/WEBP formats

Intelligent macOS disk space analysis and cleanup with safety-first philosophy. Use when users report disk space issues, need to clean their Mac, or want to understand storage consumption. Analyzes system caches, application remnants, large files, and development environments (Docker, Homebrew, npm, pip) with risk categorization (Safe/Caution/Keep) and requires explicit user confirmation before any deletions. Includes Mole visual tool integration for hybrid workflow

Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code + Codex CLI) for multi-perspective exploration, then synthesizes findings into actionable optimization plans. Supports self-audit, UX audit, API audit, architecture review, and competitive benchmarking via competitors-analysis skill

Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. Use when users provide loose requirements, ambiguous feature descriptions, need to enhance prompts for AI-generated code/products/documents, request prompt optimization, or want to improve requirements engineering. Applies domain theories (GTD, BJ Fogg, Gestalt, AIDA, Zero Trust) and structured Role/Skills/Workflows/Examples/Formats framework

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

Comprehensive QA testing infrastructure with autonomous LLM execution, Google Testing Standards (AAA pattern), and OWASP security testing. Use when establishing QA processes, writing test cases, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, enforcing quality gates, or preparing third-party QA handoffs. Enables 100x faster test execution via master prompts

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

Extract files from repomix packaged formats (XML, Markdown, JSON) with automatic format detection and validation

Install, troubleshoot, and use Scrapling CLI for extracting HTML, Markdown, or text from webpages. Diagnoses missing extras, Playwright browser runtime issues, TLS verification failures, and WeChat public article extraction patterns. Use when users mention Scrapling, `scrapling extract`, `uv tool install scrapling`, or need to decide between static and browser-backed fetching

Narrative-first slide deck creation. Guides users through structured narrative design (ABCDEFG model), then delegates visual generation to baoyu-slide-deck. Triggers on create slides, make a presentation, generate deck, slide deck, PPT, or when user needs to turn content into visual slides.

Create professional Microsoft Teams channel posts with Adaptive Cards, formatted announcements, and corporate communication standards

Operational traps for Terraform provisioners, multi-environment isolation, and zero-to-deployment reliability. Covers provisioner timing races, SSH connection conflicts, DNS record duplication, volume permissions, database bootstrap gaps, snapshot cross-contamination, Cloudflare credential format errors, hardcoded domains in Caddyfiles/compose, and init-data-only-on-first-boot pitfalls. Activate when writing null_resource provisioners, creating multi-environment Terraform setups, debugging containers that are Restarting/unhealthy after terraform apply, setting up fresh instances with cloud-init, or any IaC code that SSHs into remote hosts. Also activate when the user mentions terraform plan/apply errors, provisioner failures, infrastructure drift, TLS certificate errors, or Caddy/gateway configuration.

Diagnoses and fixes conflicts between Tailscale and proxy/VPN tools (Shadowrocket, Clash, Surge) on macOS. Covers the core conflict layers — route hijacking, HTTP proxy env var interception, system proxy bypass, SSH ProxyCommand double tunneling, VM/container proxy propagation — plus stalled DNS resolver in macOS getaddrinfo chain (dead VPN daemon leaves zombie utun + DNS injection). Includes an automated quick-diagnose script plus SOP for remote development via SSH tunnels with proxy-safe Makefile patterns. Use when Tailscale ping works but SSH/HTTP times out, when browser returns 503 but curl works, when local vanity domains fail behind proxy, when git push fails with failed to begin relaying via HTTP, when Docker pull times out behind TUN/VPN, when setting up Tailscale SSH to WSL instances, when bootstrapping remote dev environments over Tailscale, when ssh/curl/git hang ~60s before resolving a hostname while nslookup returns instantly, or when raw probes give impossibly-fast results under a TUN proxy (nc -z 0.00s or sub-ms ping to overseas nodes, or an IP-geo lookup reporting your proxy exit IP instead of your real home/ISP) — the TUN fabricates them locally. Also covers TUN DIRECT split-brain: all domestic/DIRECT-routed sites fail at once (TLS handshake EOF, UNKNOWN_CERTIFICATE_VERIFICATION_ERROR, proxy CONNECT 503) while proxied sites keep working.

Fetch Twitter/X post content including long-form Articles with full images and metadata. Use when Claude needs to retrieve tweet/article content, author info, engagement metrics (likes, retweets, bookmarks), and embedded media. Supports individual posts and X Articles (long-form content). Automatically downloads all images to local attachments folder and generates complete Markdown with proper image references. Preferred over Jina for X Articles with images.

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

Compare two videos and generate interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Use when analyzing compression results, evaluating codec performance, or assessing video quality differences

Diagnose Windows App (Microsoft Remote Desktop / Azure Virtual Desktop / W365 / direct PC) connection issues on macOS. Analyze transport protocol selection (UDP Shortpath vs WebSocket), detect VPN/proxy interference, parse Windows App logs for Shortpath failures, and resolve stuck "Configuring remote PC..." dialogs caused by expired Microsoft accounts, server reboots, or client-side auth poisoning. Use when VDI connections are slow or stuck, when direct PC connections fail to connect, when transport shows WebSocket instead of UDP, when RDP Shortpath fails, or when Windows App is frozen at a progress dialog.

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use 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

Evidence-driven investigation for network, streaming, and protocol-layer bugs. Use when debugging connection resets, SSE or long-polling stalls, fixed-time connection drops, CDN/proxy/CGNAT idle timeouts, client-side proxy/VPN/TUN misrouting, CNAME-based rule overrides, or any incident where symptoms do not match the obvious cause. Applies falsification-first methodology with layered isolation experiments, env-gated runtime instrumentation, and counter-review agent teams. Cognitive-trap catalog includes reverse-path / directional asymmetry and proxy-node DNS ≠ client DNS.

Evidence-driven repository setup, repair, handoff, and safe Git workflow for Claude Code or Codex. Detects the actual stack from project instructions and manifests instead of assuming Python, ffmpeg, uv, or .env; preserves local work during sync/conflict handling; diagnoses repeated SessionStart output before editing config; and defaults routine startup behavior to AGENTS.md/CLAUDE.md or a normal Agent request. Lifecycle hooks are an explicit pre-prompt exception with guarded, idempotent Claude Code setup and runtime-specific Codex verification.

Adversarial due-diligence on a benchmark you envy (a founder, KOL, company, or product whose claimed success you suspect is inflated). Inline four-phase orchestration: fan-out collection, adversarial verification grading every claim L1-L4 to separate marketing bubble from real signal, attribution weighting (product vs timing vs personal-IP vs luck, and which parts are replicable), then mapping the validated playbook onto the commissioner's own resources with concrete next moves. Use whenever the user wants to 尽调/对标/拆解 a competitor or role-model, suspects 水分/泡沫 in someone's claims (Product Hunt #1, 0-to-1M-users, funding rounds), asks what they can actually steal from a benchmark, or wants to know if a benchmark's wins are real and copyable before betting on the same strategy. Prefer over deep-research when the goal is debunking inflated claims and extracting a replicable playbook, not a neutral briefing.

Co-create a personal investment-research LLM Wiki (Andrej Karpathy's pattern) where the user's OWN analysis framework becomes a living CLAUDE.md — by interviewing them, NOT by handing them a template. Use whenever the user wants to build a compounding research knowledge base, 投研第二大脑, 投研知识库, or 个人投研 wiki; instantiate Karpathy's LLM Wiki gist for finance/investing; turn their stock-picking, analyst-tracking, or earnings-watching workflow into a structured markdown vault; or build a wiki tracking companies / industries / macro / analysts over time. Pure markdown + wikilinks, NO RAG / vector DB (Karpathy's core idea — do not over-engineer). Also triggers for ingesting research reports / earnings calls / expert notes into an existing wiki, and for post-earnings prediction→fulfillment reviews. Core value = extracting the user's personal investment preferences into THEIR OWN schema, never imposing a standard one.

Run a full 6-dimension health check of this Claude Code skills marketplace repo — code/script safety, documentation/SSOT consistency, security/PII leaks, open-PR triage, open-issue triage, and marketplace-manifest integrity — via a parallel fan-out Dynamic Workflow, then verify the serious findings and report by priority. Use this whenever the user asks to check the repo, run a health check, do a full sweep/audit before a release, 全面体检, 检查仓库状态, 看看仓库健康吗, 审计一下仓库, or asks whether the PRs / issues / docs / versions / PII are in good shape across the board — even if they never say workflow. Reach for it for any broad is-this-whole-repo-OK request, not just one-file checks.

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.

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.

Scan and remove sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history. Use this skill whenever the user says scan sensitive data, clean git history, remove secrets from repo, sanitize GitHub history, 清理敏感数据, 历史重写, force push, 泄露, or needs to repair a public repo after accidental secret/private context leakage. Also use before any force push to a public repository to verify visibility, backup, and scan results.

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.

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs with real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a Playwright sweep. Use after implementation to find typography, wrapping, overlap, overflow, responsive, route, authorization-state, overlay, map, transient-state, data-visualization, runtime-label, browser-output, file-dialog, PDF/print, or Electron-shell defects. Not for greenfield UI design, design-system extraction, general QA-program setup, or nonvisual debugging.

Manage OpenClaw (龙虾 / lobster) instance configurations — audit, diff, copy, add-model, list, and switch models across openclaw.json files. Use when juggling multiple OpenClaw / Claude Code wrapper instances, applying DeepSeek model patches, managing default models and aliases, or validating config.

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

Analyze Google Takeout exports of Gemini conversation history — extract, categorize, and mine transcripts and attachments for insights, then optionally distill them into a personal knowledge base. Use when the user mentions Gemini Takeout, Gemini export, Gemini history, analyzing Gemini conversation data, or drags a takeout zip into the project.

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.

Delegate coding tasks to the local OpenAI Codex CLI agent using ChatGPT Pro OAuth flat-rate subscription. Wraps `codex exec` and `codex review` for code generation, refactoring, and review without per-token API charges. Use when the user wants to run coding tasks through Codex, generate or refactor code, or run code reviews via the local Codex CLI.

Switch or repair the model configuration of an OpenClaw instance (e.g., Kimi k2p6 → k3): change the default model, add model definitions, and fix model-config failures — 401 "Invalid token", "No available channel / model not found", thinking-level rejections, and config edits that don't take effect. Ships a config-discovering switch script with backup + mirror sync, an endpoint probe protocol, and a field-tested trap catalog (env-var key hijack, provider-plugin thinking restrictions, relay availability).