Productivity

crrristang726 Bundle

Safe Windows C: drive space analysis and cleanup workflow. Use when a user asks Codex to scan, diagnose, clean, free space, remove large files, identify uninstall candidates, or troubleshoot low disk space on a Windows system drive, especially C:\. Emphasizes read-only analysis first, risk classification, explicit user approval before deletion or uninstalling, privacy-preserving local-only scans, and safe handling of Windows Installer, WinSxS, AppData, ProgramData, caches, personal files, and large application data.

cskwork Bundle

Prepare a durable specification and handoff for a bounded engineering workflow the user wants Codex to pursue as a persistent goal. Use for Codex goal delegation, not ordinary long-running work or a request merely to save session state.

cskwork Bundle

Apply the cskwork 10-rules reference sets when the user asks for them or names a rule set. Route to the relevant domain and load only rules that affect the task; ordinary work in a listed domain does not require this router.

cth9191 Bundle

Interview-driven loop-engineering architect. Grills the user one question at a time about a task they want to automate, diagnoses where it sits on the maturity ladder (manual run → codified skill → automated → self-improving loop), forces the success-criteria decision through a 5-tier verification ladder, then BUILDS the complete runnable loop construct for their task right then: execution skill, trigger config, state store, verification block, stop rule, and README — with a validation gate baked in as the first run when the task is unproven. Then it offers a test run and, once they're happy, asks whether to wire it up to run on its own — cron, a Claude Code routine, an OS scheduled task, or left manual — and sets up that trigger so the loop is actually live and hands-off, not just a folder of files. Use this whenever the user wants to "loop engineer" something, build a self-improving / agentic loop, set up a recurring AI task that gets better over time, turn a manual workflow into an automated loop, build a

cursor Skill

Adds Cursor Directory ambassador badges by name or email via Supabase. Resolves the person and sets users.is_ambassador. Use when the user asks to add, grant, or promote an ambassador, ambassador badge, or Cursor Ambassador.

cy-chenyue Bundle

通过飞书发送加急消息提醒用户。支持应用内加急和电话加急（真正打电话到手机）。

atian-create Bundle

Turn one week of creator conversations, notes, drafts, screenshots, transcripts, and content-library material into five mother topics, then adapt each mother topic into platform-ready content packages for RedNote/Xiaohongshu, WeChat articles, podcasts, short scripts, newsletters, or other creator channels. Use for weekly content batching, Sunday planning, content-calendar generation, mother-topic planning, cross-platform distribution, and creator publishing review.

axelfreeman Bundle

Find and verify B2B business contacts without buying a database — mine fresh leads from Google, Telegram and Discord, then SMTP-validate every email for a 2–5% bounce rate. Use when the user wants to find business emails or phone numbers, build a cold-outreach lead list, scrape contacts from a company website or a Discord/Telegram community, replace Apollo/ZoomInfo/Hunter, or verify an email address is real — "find b2b contacts", "cold outreach leads", "email finder", "apollo alternative".

axelfreeman Bundle

Find and verify B2B business contacts in real time — source prospects from public company websites, Discord and Telegram, with instant email verification (2–5% bounce vs 10–35% for static databases). Use when the user wants to find business emails or phone numbers, build a cold-outreach lead list, source prospects from a company website or a Discord/Telegram community, replace Apollo/ZoomInfo/Hunter, or check whether an email address is real.

backnotprop Bundle

Explicit-only router for ADR workflow commands. A dead simple engineering skill framework that works reliably.

banjtheman Bundle

Plan trips, search flights/hotels on Expedia, discover destinations via TikTok, Instagram, and Google Maps, check weather, and email itineraries. Uses the OpenClaw-managed browser. Use when users want travel planning help, destination recommendations, flight/hotel searches, or trip itineraries.

leechael Bundle

Check, read, label, archive, and manage emails across multiple accounts. Use when asked to check inbox, read emails, clean up mail, or handle email-related tasks.

leonardobringel Skill

Captura e organiza conhecimento no vault "second brain" do Obsidian do usuário — de sessões de código, estudos, projetos e ideias — como notas atômicas, interligadas e recuperáveis, seguindo uma estrutura fixa de pastas (dump, daily, projects, lessons, knowledge, resources, archives). Use esta skill sempre que o usuário quiser salvar, capturar, registrar, anotar ou arquivar algo no vault / segundo cérebro / Obsidian — por exemplo "anota isso", "salva no meu vault", "registra essa decisão do projeto", "abre uma task pra isso", "transforma isso numa nota de conhecimento", "adiciona ao meu segundo cérebro", ou ao final de uma sessão de código/estudo que valha a pena preservar. Também vale quando se está trabalhando diretamente dentro de um diretório de vault do Obsidian. Dispare mesmo que o usuário não diga "Obsidian" explicitamente, desde que a intenção seja claramente persistir conhecimento nas notas dele.

lethechen Bundle

Generate CLAUDE.md / AGENTS.md + TODO.md for the current project, following the minimal HumanLayer pattern and Karpathy 4 rules. Bakes a Session Maintenance Protocol into the root file so future agents auto-update rules and TODO when they load the file. Use when user mentions CLAUDE.md, AGENTS.md, project rules, init / set up / generate / split / refactor AI coding guidelines, or needs a TODO board. 中文触发词：生成 / 初始化 / 拆细 CLAUDE.md 或 AGENTS.md、补一份 TODO.md、规则文件按目录拆分、规则太多要整理。

liquidflow-configurator Skill

Attiva questa skill quando l'utente avvia o menziona un progetto che continuerà su più sessioni future (parole chiave come "progetto", "continuiamo la prossima volta", "riprendiamo questo lavoro", "nuovo progetto", ecc.), oppure quando l'utente segnala un progetto esistente con documentazione disorganizzata (file sparsi, note incoerenti, nessuna struttura chiara). In questi casi, applica di default una struttura standard di 4 file di documentazione: CLAUDE.md (comportamento), AGENTS.md (architettura/regole stabili), summary_for_new_chat.md (cronaca sessione per sessione) e README.md (presentazione esterna). Attiva questa skill SEMPRE anche quando l'utente usa frasi esplicite come "impostami i 4 file", "creami i 4 file di documentazione", "sistemami la documentazione del progetto", "riorganizzami i file di progetto", o nomina direttamente la skill "gestione-progetti-multi-sessione". NON usare per task singoli, una tantum, senza continuità futura.

lucaszh7 Bundle

Use when a user wants OpenClaw to manage several interleaved conversation threads inside one chat, keep a primary mission in focus, classify side topics, assign weights or priorities, reduce distraction, and periodically steer attention back to the main task. Also fits the Chinese concept "任务权重管理器".

m97chahboun Bundle

Use this skill whenever you need to read, understand, navigate, edit, refactor, or reason about a codebase written in Dart, Python, or TypeScript — especially before reading any source files directly. This skill runs `code-parser` to build a lightweight structural index (classes, methods, line ranges) of the codebase first, then uses that index to read only the specific lines that matter. This drastically reduces token consumption and prevents context window overflow. Trigger this skill when the user says things like: "read this codebase", "understand my project", "refactor this class", "find where X is defined", "explain how Y works", "add a method to Z", "what does this file do", "help me debug", "review my code", or any task that would otherwise require loading entire source files. Always use this skill before reading .dart, .py, or .ts/.tsx files — even for single-file tasks. Do NOT skip this skill just because the request seems simple; the index step is always cheaper than full file reads.

mangouart Bundle

Manages AI motion comic production projects with YAML assets and storyboards. Use when users need to initialize Mangou projects, edit storyboard or asset YAML, generate images or videos, split grid shots, stitch final videos, or debug task backfill.

ferryhe Bundle

Resolve one or more named GitHub Issues end to end through sequential per-Issue tasks, isolated branches, delegated implementation, bounded review, PR feedback handling, merge, task closure, and cleanup. Use only when the user explicitly authorizes taking those Issues through merge; do not use for advisory-only discussion or review-only work.

fishjar Bundle

Safely automate a complete KISS Translator release using the repository's version scripts, Chinese CHANGELOG convention, dev-to-master pull request flow, annotated version tags, and GitHub Actions release workflow. Use when asked to bump the project version, prepare a release, update release notes, create and merge the release PR, publish a version tag, or complete the end-to-end KISS Translator release process without intermediate confirmations.

floatpane Skill

Use when the user wants to send an email, compose a message, or email someone. Triggers: send email, email someone, compose email, write email, mail to, message to, send a message, draft and send. Works with multiple accounts and recipients.

fradser Bundle

Use this skill whenever the user wants to manage their Apple Notes using the `note` CLI tool. It covers listing, reading, creating, editing, moving, searching, and deleting notes and folders, and end-to-end-encrypted syncing to a Cloudflare backend. Works on macOS (via AppleScript) and on Linux (via a local SQLite database synced from the Cloudflare backend). Complements the `apple-events` skill (Reminders/Calendar).

henriquepb22 Bundle

Teach.ai — turns AI-assisted coding into active learning. Instead of writing explanatory comments, ask the engineer to explain what was just implemented, grade the answer, and award XP toward levels, streaks, and per-concept mastery. Use this skill on any task where you write, edit, refactor, or debug code for the user, even if they never mention learning, teaching, quizzes, or XP — it changes how you document and hand off code by default. Also use it when the user asks about their progress, XP, level, streak, learning journal, progress card, weak concepts, or wants a review session, or when they invoke the skill directly (e.g. /teach-ai status).

raahimb6 Bundle

Turn a YouTube tutorial into a tested Codex skill, preserving transcript and frame evidence and adding guarded persistent learning through the local Obsidian Skill Brain vault. Use when the user wants to learn, reconstruct, or operationalize a workflow demonstrated in a YouTube video; do not use for ordinary video summaries.

raymondhou0917 Bundle

「說人話」：繁體中文的去 AI 味改寫 skill。審查與改寫文字，去除 AI 味道、校正中國用語與半形標點，讓文字讀起來像真人寫的。 觸發時機：用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對一下再發」，或要求檢查電子報、社群貼文、銷售頁、課程文案、客服回信、簡報、公告、Email 等對外文字的語感。 不要觸發：逐字翻譯、模仿特定品牌 voice、事實查核（非風格問題）、程式碼／log／設定檔、要求「潤成雷蒙的語氣」（那是 content-writing skill 的事，本 skill 只去 AI 味、不加個人風格）。

regychang Bundle

Scan a repo scope for actionable work items (bugs, TODO/FIXME, doc inconsistencies, performance/maintainability risks) and emit Jira-ready issues in a strict JSON schema. Use when asked to scan a specific module/path/page/route and produce evidence-backed Jira tickets.

renn-labs Bundle

Looptimal — turns an objective into a delivered, VERIFIED OUTCOME by designing, war-gaming, and running the right loop or mission route. Use on 'looptimal', '/looptimal', 'run an outcome loop', 'orchestrate this objective to done', 'plan and ship this goal', or any non-trivial objective that needs a sealed acceptance suite, the right execution driver, and independent verification before you call it done. ALSO handles loop-design wizard requests ('design a loop', 'build a loop', 'new loop', 'loop wizard', or a vague recurring task to automate) via the 'design' fast-path (Stage 2 only, no outcome orchestration). For a single, non-recurring deliverable you still want proven — not trivial, just not a reusable loop — it routes to mission / goal-run when bounded iteration is useful, or degrades to 'single-pass' mode when one pass is enough: Frame → (Analyze if multi-domain) → light pre-mortem → Execute → Verify-outcome → Persist, skipping reusable-loop scaffolding. When the objective's shape is ambiguous, asks one

spxros Bundle

Write code comments that explain why, not what, and clean up comments that don't. Use whenever writing, reviewing, refactoring, or documenting code, and proactively before emitting any non-trivial code block (more than a few lines, or any public function, class, or exported type) even when comments were never mentioned - over-commenting is the default failure and this prevents it. Also use whenever comments, docstrings, JSDoc, Javadoc, XML doc comments, rustdoc, godoc, header comments, or TODO/FIXME/HACK/XXX/NOTE tags come up, and for requests like "document this function", "add comments", "too many comments here", or "clean up the comments". Covers doc-comment contracts for public APIs, inline why-comments for maintainers, per-language conventions (Python, JS/TS, Go, Rust, Java, C#, C/C++, Swift, Ruby, PHP, shell), task-tag quality standards, and a flag-and-ask workflow for removing redundant comments without ever deleting them unasked.

saleemnijim Bundle

Always-on request orchestrator: analyze every user task from multiple angles, pick the best skill lane, and split large work across parallel agents. Use at the start of ANY user request (simple or complex); when routing skills; when the user mentions router, توجيه, تحليل الطلب, تقسيم المهام, router-feedback, or روتر-تعليق.

serennity007 Bundle

A trading journal that records the decision, not just the trade — the user reports a trade in plain language (e.g. "bought 500 NVDA at 135", "closed my TSLA position"), you parse it and write it to their Notion database, capturing the entry thesis, the plan, and the emotion; closing a trade updates the matching open row; review compares thesis vs outcome vs execution. Use when the user reports a trade, says log a trade / trading ledger, or asks to review my trades.

shino-zzz Bundle

Find the best Claude Code Skills for your goals. Searches 117,000+ skills from SkillsMP using keyword and AI semantic search via Skill Curator Actor on Apify. Returns optimized workflow plans with quality-scored skill recommendations. Use when the user wants to find skills, discover skills, recommend skills, search for skills, curate skills, or asks "what skills should I use?", "find me a skill for...", "which skill can...", "suggest skills for...", "help me find tools/skills for my project". 「スキルを見繕って」「〜したいのに使えるSkillは？」「おすすめのSkillを教えて」 「〜に使えるスキルを探して」「Skillを検索して」で発動。

snehit70 Bundle

Safely inspect and manage the authenticated user's Pravah v2 tasks, goals, operations, and compact planning context through the Pravah CLI. Use for current planning context, local CLI diagnosis, and explicitly requested task, goal, or undo mutations.

spe1977 Bundle

Use when multiple CLI agents or assistants alternate on the same repository or explicit shared handoff workflow — especially with AGENT_HANDOFF.md, side-by-side AGENTS.md/CLAUDE.md/GEMINI.md, dirty worktrees, ownership notes, red tests, resume/continue requests, or /cli-collaboration in Grok Build.

swiftyjourney Bundle

Use this skill for non-obvious Swift LANGUAGE and standard-library techniques -- features that make code clearer, safer, or faster but that developers routinely miss. Covers pattern matching (if/guard-case, switch over tuples); functions, closures, and key paths (variadics, autoclosures, rethrows); value semantics and custom types (copy-on-write, ~Copyable, callAsFunction, recursive enums, property wrappers); protocols and generics (associated types, opaque some vs existential any, phantom types, hand-rolled type erasure); collections (lazy, RangeSet, InlineArray, sorting); strings and Unicode (grapheme-correct iteration, custom interpolation); concurrency and errors (async/await, task groups, AsyncStream, typed throws, custom global actors, Mutex and the Synchronization framework, and the nonisolated(unsafe)/assumeIsolated/@preconcurrency escape hatches); and debugging and code organization (assertions, dump, enum namespaces, directives). Trigger for "how do I do X in Swift" and idiomatic refactors. Do NOT u

zenoxzx Bundle

Notion workspace management via CLI. Activate when user mentions "Notion", "notion page", "notion database", or wants to search/create/update content in their Notion workspace.

zhangyanbo Bundle

Guide for integrating user-provided materials (chat logs, documents, citations) into academic papers with proper scholarly style. Use when the user wants to incorporate chat/email threads, personal documents, or references into a LaTeX paper, or asks for academic writing assistance that requires careful source attribution and style preservation.