@skills · Owner

Agent skills by daymade

129 skills indexed from github.com/daymade. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• ashare-news-fetcher · Skill · 1,320 stars

  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

• asr-transcribe-to-text · Skill · 1,320 stars

  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 f

• auto-repo-setup · Skill · 1,320 stars

  Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator h

• bigdata-skill · Skill · 1,320 stars

  Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/* REST endpoints — structured financials, prices, analyst

• bilibili-source · Skill · 1,320 stars

  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. Us

• claude-code-hooks · Skill · 1,320 stars

  Writes, tests, registers and debugs Claude Code hooks (PreToolUse, PostToolUse, SessionStart, Stop) that turn a rule the model keeps breaking into a hard g

• claude-code-skills · Collection · 1,320 stars
• claude-md-progressive-disclosurer · Skill · 1,320 stars

  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, o

• claude-migrate-memory-to-doc · Skill · 1,320 stars

  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

• claude-skills-troubleshooting · Skill · 1,320 stars

  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, sk

• claude-switch-models-setup · Skill · 1,320 stars

  Isolates profiles for multi-provider setup and switching models in separate terminal windows (Kimi, MiniMax, DeepSeek, GLM, StepFun, Anthropic). Use for pr

• claude-usage-analyst · Skill · 1,320 stars

  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

• cli-demo-generator · Skill · 1,320 stars

  Generates professional animated CLI demos as GIFs using VHS terminal recordings. Use to create terminal demos, record CLI workflows as GIFs, generate anima

• cloudflare-troubleshooting · Skill · 1,320 stars

  Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, D

• competitors-analysis · Skill · 1,320 stars

  Clones and audits competitor repositories into evidence-based intelligence with file:line citations. Use to track competitors, add a competitor repo, revie

• continue-codex-work · Skill · 1,320 stars

  Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unful

• daymade-audio · Collection · 1,320 stars
• daymade-claude-code · Collection · 1,320 stars
• daymade-docs · Collection · 1,320 stars
• daymade-financial · Collection · 1,320 stars
• daymade-skill · Collection · 1,320 stars
• debugging-network-issues · Skill · 1,320 stars

  Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for E

• deep-research · Skill · 1,320 stars

  Creates reusable, source-traced research reports and coordinates provider/mode lanes with original exports. Use for 深度研究, 调研报告, literature reviews, market

• doc-to-markdown · Skill · 1,320 stars

  Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJ

• docs-cleaner · Skill · 1,320 stars

  Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change. Modes: (1) POST-CHANGE GOVERNANCE

• docx-creator · Skill · 1,320 stars

  Produces Word (.docx) and exports existing Word/WPS manuscripts to PDF, preserving revisions, tables and images, especially Chinese formal documents via a

• douban-skill · Skill · 1,320 stars

  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

• download-gemini-images · Skill · 1,320 stars

  Download, export, save, or package images from a Google Gemini conversation/chat/app page, especially uploaded images or generated image previews visible i

• fact-checker · Skill · 1,320 stars

  Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fac

• feishu-doc-scraper · Skill · 1,320 stars

  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

• financial-data-collector · Skill · 1,320 stars

  Collects real financial data for any US publicly traded company from free public sources (yfinance) and outputs structured JSON for downstream skills (DCF

• fixing-claude-export-conversations · Skill · 1,320 stars

  Fixes broken line wrapping in Claude Code exported .txt conversation files — rebuilds tables, paragraphs, paths and tool calls hard-wrapped at a fixed widt

• frontend-visual-qa · Skill · 1,320 stars

  Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image

• gangtise-copilot · Skill · 1,320 stars

  Gangtise (岗底斯投研) OpenAPI skill suite installer and diagnostic tool. One-click install 19 official skills (data, research, utility), configure accessKey/sec

• gemini-history-analyzer · Skill · 1,320 stars

  Analyze Google Takeout exports of Gemini conversation history. Use when the user mentions Gemini takeout, Gemini export, Gemini history, Gemini conversatio

• git-safety-net · Skill · 1,320 stars

  Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commi

• github-contributor · Skill · 1,320 stars

  Ships pull requests to open-source projects you don't maintain — CONTRIBUTING compliance, PR-size/scope checks, minimal-diff implementation, AI-disclosure

• github-ops · Skill · 1,320 stars

  Operates GitHub via gh CLI and REST/GraphQL — PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org permissions, 2FA — wit

• github-review-pr · Skill · 1,320 stars

  Reviews PRs against the live base with immutable objects and three-way merges. Use for PR review/merge readiness, main changed, closed-PR reconsideration,

• github-sensitive-data-cleanup · Skill · 1,320 stars

  Scans and removes sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history, then verifies and force-pushes safely. Use f

• i18n-expert · Skill · 1,320 stars

  This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON loc

• ima-copilot · Skill · 1,320 stars

  Installs, diagnoses, repairs, and personalizes the official Tencent IMA skill (a wrapper around upstream ima-skill, not a replacement), including fan-out s

• llm-eval-harness · Skill · 1,320 stars

  Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality reg

• llm-icon-finder · Skill · 1,320 stars

  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

• llm-wiki-setup · Skill · 1,320 stars

  Co-creates a personal investment-research LLM Wiki (Karpathy's pattern) by interviewing the user for THEIR OWN analysis framework, not a template — a livin

• local-conversation-history · Skill · 1,320 stars

  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

• marketplace-dev · Skill · 1,320 stars

  Builds and maintains Claude Code plugin marketplaces: converts a skills repo to spec-valid marketplace.json, adds/updates plugin entries, and migrates skil

• marketplace-health-check · Skill · 1,320 stars

  Runs an evidence-based health audit of this skills marketplace repo — code safety, docs/SSOT, security/PII, PR/issue triage, manifest integrity — via a par

• meeting-minutes-taker · Skill · 1,320 stars

  Transforms raw meeting transcripts into structured, evidence-based meeting minutes — merges multiple versions without losing content, reviews existing minu

• mermaid-tools · Skill · 1,320 stars

  Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, co

• notify-wecom · Skill · 1,320 stars

  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"

• openclaw · Skill · 1,320 stars

  Audits, diffs, copies, and lists providers/models, adds models, and switches the default model in local openclaw.json configs; diagnoses gateway/plugin fai

• openclaw-model-switch · Skill · 1,320 stars

  Switches or repairs an OpenClaw instance's model config: changes the default model, adds model definitions, and fixes 401 "Invalid token", "No available ch

• pdf-creator · Skill · 1,320 stars

  Converts Markdown to print-ready PDF with proper Chinese typography, themes and a visual self-check. Use for Markdown → PDF, including documents formatted

• pdf-to-html · Skill · 1,320 stars

  Converts a PDF into one self-contained, readable HTML file that preserves images, tables, charts and reading order — optionally translating it into another

• pharma-daily-report · Skill · 1,320 stars

  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

• photo-to-scanned-pdf · Skill · 1,320 stars

  Two pipelines ending at a scanner-look PDF. (1) Phone photos of paper documents (contracts, stamped certificates, receipts, forms, handwritten notes) → cle

• ppt-creator · Skill · 1,320 stars

  Deprecated presentation entry retained as a compatibility notice. Use to check the retirement status of ppt-creator or identify a legacy installation. This

• product-analysis · Skill · 1,320 stars

  Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore pr

• prompt-optimizer · Skill · 1,320 stars

  Transforms vague prompts or feature requests into precise, testable specifications using EARS (Easy Approach to Requirements Syntax) grounded in relevant d

• promptfoo-evaluation · Skill · 1,320 stars

  Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writi

• qa-expert · Skill · 1,320 stars

  Sets up QA testing processes: test strategies, Google Testing Standards test cases, P0-P4 bug tracking, quality metrics, progress reports, autonomous execu

• read-claude-web-conversation · Skill · 1,320 stars

  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

• repomix-safe-mixer · Skill · 1,320 stars

  Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distributio

• repomix-unmixer · Skill · 1,320 stars

  Extracts files from repomix-packed repositories, restoring original directory structures from XML/Markdown/JSON formats. Activates when users need to unmix

• scrapling-skill · Skill · 1,320 stars

  Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages. Use this skill whenever the user mentions Scrapling, `uv too

• setup-notifications-via-wecom · Skill · 1,320 stars

  Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, al

• skill-creator · Skill · 1,320 stars

  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 creat

• skill-governance · Skill · 1,320 stars

  Governs the Claude Code/Codex Skill surface: reconciles source/install/catalog-visibility drift without losing cold capability. Use when users ask how many

• skill-reviewer · Skill · 1,320 stars

  Reviews skill quality with evidence-based design rubrics and read-only batch inventories. Use for self-review, external skill or repository audits, and aut

• skills-search · Skill · 1,320 stars

  Finds Skills in configured local repositories before searching CCPM. Use when discovering or reusing a Skill, finding PDF/code-review tools, inspecting a S

• slides-creator · Skill · 1,320 stars

  Deprecated slide-creation entry retained as a compatibility notice. Use to check the retirement status of slides-creator or identify a legacy installation.

• statusline-generator · Skill · 1,320 stars

  Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts). Use when the user wants to set up or change the s

• stepfun-asr · Skill · 1,320 stars

  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

• stepfun-tts · Skill · 1,320 stars

  Generates speech with StepFun contextual TTS, including Chinese/Japanese speech, emotional delivery, inline natural-language directions, cloned voices and

• teams-channel-post-writer · Skill · 1,320 stars

  Writes educational Teams channel posts about Claude Code features and best practices, using templates emphasizing concrete examples and underlying principl

• terminal-screenshot · Skill · 1,320 stars

  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 actu

• terraform-skill · Skill · 1,320 stars

  Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fre

• transcript-fixer · Skill · 1,320 stars

  Corrects ASR/STT transcription errors — homophones, garbled terms, person-name errors, mixed Chinese/English — with dictionary rules plus Claude's built-in

• tunnel-doctor · Skill · 1,320 stars

  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-t

• twitter-reader · Skill · 1,320 stars

  Fetches Twitter/X post and Article content — text, author, engagement metrics and embedded media — downloading images locally and generating complete Markd

• ui-designer · Skill · 1,320 stars

  Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want

• video-comparer · Skill · 1,320 stars

  This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality

• windows-remote-desktop-connection-doctor · Skill · 1,320 stars

  Diagnoses Windows App (Remote Desktop / AVD / W365 / direct PC) connection problems on macOS: transport selection (UDP Shortpath vs WebSocket), VPN/proxy i

• wps-doc-scraper · Skill · 1,320 stars

  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 Markdo

• youtube-downloader · Skill · 1,320 stars

  Fetch existing YouTube transcripts/subtitles or archive spoken video content as text, and download YouTube videos/audio or HLS streams (m3u8) with yt-dlp a

• agent-web-search-setup · Skill

  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 sea

• app-evolver · Skill

  Improves an existing application using its code, product contract, authorized work history and competitor evidence. Use for 取长补短、取其精华去其糟粕、参考竞品优化应用 or evolv

• audio-router · Skill

  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 dir

• benchmark-due-diligence · Skill

  Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company, or product whose success looks inflated — splitting marketing bubb

• capture-screen · Skill

  Programmatic screenshot capture on macOS. Find window IDs with Swift CGWindowListCopyWindowInfo, control application windows via AppleScript (zoom, scroll,

• claude-code-ops-router · Skill

  plugin/Skill repair, marketplace, statusline, model profiles/source sync, 1M/[1m] context, usage/quota reset ping, memory→docs, .txt repair, MCP startup co

• claude-code-ping-start-5h-quota · Skill

  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 pi

• codex-1m-context-window-setup · Skill

  Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. Use to inspect local context settings, lower or set the a

• codex-image-gallery · Skill

  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 loca

• continue-claude-code-work · Skill

  Continues interrupted Claude Code work after local history is read and reconciled — reconstructs the original outcome, unfulfilled requests, and the next a

• cookie-copy · Skill

  Copies selected-site cookies between local profiles of the same macOS Chrome. Use for cookie copy, 复制 Cookie, 搬登录态 or reusing an existing ChatGPT session i

• data-visualization-discipline · Skill

  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 da

• daymade-codex · Collection
• daymade-macos · Collection
• daymade-sector-research · Skill

  A-share sector research: computes board-wide Top N gainers, cross-checks week/month announcement windows across two sources, and grades market-sentiment ev

• design-style-picker · Skill

  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 abstr

• developing-ios-apps · Skill

  Builds and ships iOS/macOS apps with XcodeGen, SwiftUI and SPM: Xcode build fixes, device deployment, Apple Developer signing/notarization, CI/CD pipelines

• devils-advocate · Skill

  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 +

• docs-router · Skill

  Word/PDF/PPTX/HTML→MD;MD/Word→PDF;new Word;PDF HTML/translate;Excel/xlsm/Mac;photo/signed scan;Mermaid;DOCX review;doc cleanup Reads one bundled Daymade sp

• excalidraw-use · Skill

  Places existing images onto an Excalidraw whiteboard, turns a slide deck into clean per-slide images, and inspects a .excalidraw file. Use whenever someone

• excel-automation · Skill

  Creates formatted Excel reports with openpyxl, parses complex xlsm financial models with stdlib zipfile+xml when openpyxl fails, and controls Excel windows

• financial-router · Skill

  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

• floorplan-finder · Skill

  Finds existing residential floor plans online and checks layout, entrance orientation, and source identity. Use for 找户型图、按楼栋房号找原图、核对同款或镜像户型. Not for design

• ghostty-use · Skill

  Snapshots local Codex/Claude CLI sessions across terminals and restores IDs in Ghostty after reboot (保存会话/重启前备份/恢复窗口), audits survivors, and makes change-o

• interaction-design-board · Skill

  Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before

• kimi-use · Skill

  Two scopes: (1) drives Kimi.app via computer-use for Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chat's built-in 深度研究 report; (2) kimi-

• lark-cli-router · Skill

  Routes any Feishu/Lark/Doubao operation, including recording lookup by date (按日期找会议录音), through the version-matched lark-cli domain guide embedded in the i

• local-codex · Skill

  Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate coding tasks to Co

• macos-cleaner · Skill

  Diagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign clones, developer ca

• macos-load-doctor · Skill

  Diagnoses macOS system-level slowness, heat and fleet-wide timeouts: high load average, leaked per-session child processes (MCP servers, helpers), fork sto

• macos-permissions · Skill

  Diagnoses TCC denials, Local Network access and stuck Keychain dialogs: Full Disk Access, Screen Recording, Microphone, Camera, Accessibility, Automation.

• macos-watchdog · Skill

  Designs and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications, apps reopening aft

• meme-creator · Skill

  Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF.

• peer-message · Skill

  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 post

• prior-work-retrieval · Skill

  Only for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse is plausible. Use

• product-growth · Skill

  Diagnoses product growth using business data and actively discovered customer feedback, separates attribution from causal effects, and turns findings into

• read-claude-code-history · Skill

  Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file rec

• read-codex-history · Skill

  Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and roll

• read-docx-review · Skill

  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

• report-with-html · Skill

  Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified. Use

• skill-evolver · Skill

  Researches and improves a specified existing Skill using successful/failed work and competitor evidence. Use for 优化这个Skill, 从成功和失败经验改进Skill, or 研究竞品后优化指定技能

• tech-selection · Skill

  Gated checklist to choose or review a library, framework, storage, data format, model, build-vs-buy or architecture. Run favorites-search before external r

• tibo-reset-codex · Skill

  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

Browse the @skills marketplace