Productivity

danielpan12 Bundle

A reusable job application workflow for Codex and other AI agents. Use when a user wants to set up or run an AI-assisted job search system: collecting a candidate profile, creating an application dashboard, defining screening and resume-routing rules, finding and ranking job leads, applying to jobs within explicit safety boundaries, recording outcomes, triaging blockers, or iterating a job application workflow.

dannymac180 Bundle

Plan, route, implement, verify, and review substantial work with GPT-6 Astra and dynamically selected native Codex subagents.

dapi Bundle

Manage configured email accounts with the Himalaya CLI. Use when the user asks to check, search, read, draft, send, reply to, forward, move, copy, or delete email; to list mailboxes or accounts; or refers to inbox, unread messages, or mail folders. Always obtain explicit confirmation before sending, moving, copying, or deleting mail.

daralthus Bundle

Create new Claude Code skills following best practices. Use when the user asks to create a new skill, make a skill, or automate a workflow as a skill.

dash0hq Bundle

Wire up or debug a source repository's docs sync to the Dash0 website via the dash0hq/sync-docs-action composite action. Use when adding a sync-docs-to-website workflow, authoring or editing a transformations.yaml (files/common/nav/coverage), configuring the dry-run vs full-sync modes, migrating a caller across action versions, or diagnosing a failing sync run (missing inputs, coverage failures, no-op PRs, PAT/token errors).

dastoyan Bundle

User-invoked dashboard critique, concept, redesign, spec, and grill workflow.

dtsola Bundle

OpenClaw task & project progress tracking. Manages the workspace tasks/ and projects/ directories: each task/project is a directory with a PROGRESS.md card (status + progress log + document index). Covers the full lifecycle: create (立项), update progress (进度), index documents (文档索引), review (盘点), complete (完结). Lightweight, file-based, no CLI, no external services. Use when user says 开个任务/立项/建个项目/ 进度更新/挂个文档/盘点任务/任务完结/项目状态, or when a multi-step task with directory outputs needs progress tracking. 中文：OpenClaw 任务与项目 进度管理工具。管理工作区 tasks/（短期任务）与 projects/（长期项目）目录： 每个任务/项目一个目录 + PROGRESS.md 进度卡（状态 + 进度日志 + 文档索引）。 覆盖全生命周期：立项、进度更新、文档索引、盘点、完结。轻量纯文件， 无 CLI、无外部服务依赖。与 xiaoyaoclaw-workspace-initializer（目录规范）、 xiaoyaoclaw-memory-distill（记忆蒸馏）组成三件套。

dvcrn Bundle

Use this skill when a user explicitly wants WeWork actions through the installed `wework` CLI, such as "book a WeWork desk", "list WeWork desks in Tokyo tomorrow", "show my WeWork bookings", "list WeWork locations", or "generate a WeWork calendar export". Do not use it for generic coworking, travel planning, or unrelated calendar requests.

dwdestiny Bundle

Apply SuperDesign design rules, template library, and stepwise workflow to deliver prototypes, UI mockups, and website/tool/app designs. Use when users say they want to design a website/tool/app, create a prototype, produce a visual mockup, or request a high-quality UI style.

echennells Bundle

Manage Luma events: discover local events, view your calendar, check guest lists, RSVP, and create events. Use when: user asks about events, meetups, RSVPs, or anything related to luma.com / lu.ma / Luma.

eden2f Bundle

Install, configure, and operate CronCopilot — a Python-based scheduled task management system for cron jobs, scripts, monitoring, and alerts.

edimuj Skill

Fire-and-forget async Codex delegation. This skill should be used when delegating debugging, implementation, refactoring, or code review to OpenAI Codex without blocking the current conversation. Trigger when: (1) implementation or refactoring touching 3+ files — do not attempt yourself, delegate, (2) debugging after 1-2 failed root-cause attempts — stop spinning and hand it off, (3) user says 'delegate to codex', 'send to codex', or 'use codex', (4) conserving Claude Max quota — delegate coding/debugging to Codex, reserve Claude for architecture/design/narrative, (5) any task you would spawn a haiku subagent for — use gpt-5.4-mini instead, it is cheaper and smarter. IMPORTANT: Err on the side of delegating. If the task involves writing or debugging 50+ lines of code, delegate it. The context and quota spent attempting it yourself almost always exceeds the cost of a Codex delegation. Do NOT delegate: architecture decisions, creative/narrative work, trivial 1-3 line fixes.

catoncat Bundle

Use in Codex App when a complex task needs coordinated Codex Sessions, long-running milestones, cross-session state, worktrees, verification sessions, heartbeat continuation, project-specific constraints, or durable workflow artifacts. Assumes Codex Goal support; optional lifecycle capabilities and project profiles are discovered at runtime.

catoncat Bundle

Prepare and troubleshoot masks for OpenAI image edits. Use when a user needs help selecting an edit region, creating or converting an arbitrary raster selection, validating an existing mask, learning a software-specific workflow, or diagnosing an edit that changed the wrong area.

celestiaorg Skill

Implement a celestia-app code change with the safety workflow - triage, align, implement, invariant review loop, verify. Use when the engineer confirms the invariant workflow at the interactive gate or invokes /implement directly.

centminmod Skill

Use TTS to speak notifications, alerts, and important messages to the user. Invoke when the user requests audio feedback, task completion announcements, or error notifications that should be spoken aloud.

cerbug45 Bundle

Turn incoming text (email/newsletter) into a short TTS podcast with chunking + ffmpeg concat.

chang-l19 Skill

Compact operational boundary policy for durable red-team workflows. It does not route domains or decide workflow completion.

chang416 Bundle

台灣繁體中文與英文的語態控制與去 AI 味編輯技能，兩種模式。語態模式：使用者說「我是人」「開啟我是人」「說人話模式」或要 Claude「用我是人講話」時啟動，之後 Claude 自己的每一句輸出都改用台灣人日常的繁體中文（英文則像母語者隨手寫的），禁用 AI 常見的開場白、路標詞、空泛拔高、翻譯腔與簡報式排版，直到使用者說關閉。編輯模式：使用者說「去 AI 味」「說人話」「改自然」「不要像模板」「幫我審稿」，或要改寫貼文、文案、Email、文章、技術文件、小說時啟動，在不更動事實、數字、引用與作者立場的前提下清掉模板感。Also handles English requests to strip AI writing style or make text read like a human wrote it. 只做台灣繁體中文與英文，不支援簡體中文。不用於翻譯、事實查核、憑空創作，也不用於規避 AI 偵測器。

charlesdove977 Bundle

Interview-driven compliance guardrail framework for Claude Code. Makes the AI aware of compliance rules (HIPAA, SOC 2, GDPR, PCI-DSS) BEFORE it builds, so every website, workflow, automation, and system is designed with those principles baked in — protected data never routed through uncovered servers or non-compliant flows. Use when the user says "compliance ops", "/compliance-ops", "is this HIPAA compliant", "build this HIPAA safe", "SOC 2", "GDPR", "PCI", "is this PCI compliant", "compliance", "BAA", "DPA", "PHI", "personal data", "cardholder data", "is it safe to put patient/customer/card data through this", or is building anything in a regulated industry (healthcare, behavioral health, finance, legal, SaaS handling customer data, EU users, payments). NOT legal advice. Does NOT make a Claude consumer subscription able to process protected data.

charleshan7 Bundle

Use when turning a meeting recording or local video clips (腾讯会议/飞书录制、DJI/手机/相机素材) into a highlight video — auto-selecting the good parts, adding a title card and subtitles, and rendering a finished MP4. Also use to insert or append extra highlights into an already-rendered cut, or to add background music. Adapts to the local environment instead of assuming fixed paths, tools, or fonts. The finished MP4 (and the cut clips) can be manually imported into any editor afterward.

charpup Bundle

TRIGGER: task scheduling, dependency analysis, DAG scheduling, batch ordering, task dependencies, complexity scoring, multi-task project. Intelligent task scheduling with DAG-based dependency resolution, complexity scoring, and batch ordering. Reads tasks from task_plan.md (planning-with-files output), builds a dependency graph, and produces an optimal execution schedule. Use when managing 5+ interdependent tasks. NOT for simple sequential task lists.

chatmaterials Bundle

Use when the task is to analyze completed or partially completed ABINIT results, including extracting total energies, convergence or restart status, comparing multiple ABINIT runs, and summarizing .abo outputs.

chatmaterials Bundle

Use when the task is to analyze completed or failed LAMMPS simulations, including thermo extraction, run-status interpretation, comparing multiple log.lammps outputs, and summarizing restart or force-field issues from finished runs.

chatmaterials Bundle

Use when the task involves LAMMPS atomistic simulation workflows, including input script creation, minimize, NVT, NPT, and restart setups, force-field and data-file checks, log.lammps review, restart handling, and scheduler scripts.

chatmaterials Bundle

Use when the task is to analyze completed or partially completed Quantum ESPRESSO results, including extracting total energies, convergence status, force summaries, comparing multiple QE runs, and summarizing pw.x output directories.

chatmaterials Bundle

Use when the task involves Quantum ESPRESSO workflows, including pw.x input preparation, scf, relax, dos.x, projwfc.x, and bands.x setups, pseudopotential and scratch layout checks, restart handling, pw.x output review, convergence checks, and Slurm or PBS job scripts.

chatmaterials Bundle

Use when the task is to analyze completed or partially completed VASP results, including energy extraction, convergence interpretation, structure or force summaries, comparing multiple VASP runs, and writing compact reports from OUTCAR, OSZICAR, INCAR, or POSCAR.

chatmaterials Bundle

Use when the task involves VASP density-functional theory workflows, including INCAR, POSCAR, KPOINTS, and POTCAR preparation, relax, static, DOS, band, and optics setups, OUTCAR or OSZICAR review, restart handling, convergence checks, and Slurm or PBS job scripts.

chatmaterials Bundle

Use when the task is to analyze completed or incomplete Wannier90 outputs, including spread summaries, convergence interpretation, comparing multiple Wannier models, and summarizing .wout results.

chatmaterials Bundle

Use when the task involves Wannier90 workflows, including .win input design for isolated or disentangled manifolds, projection choices, disentanglement windows, parent DFT handoff from VASP, QE, or ABINIT, localization review, and diagnosis of .wout, .amn, .mmn, .eig, or .chk issues.

chigyel Bundle

Guide users through building a custom customer support automation skill for their company. Walks through planning integrations, writing scripts for their support stack (Zendesk, HelpScout, Intercom, etc.), creating response templates, and setting up an automated triage workflow. Use when users want to create their own support automation.

china-qijizhifeng Bundle

Build a zero-data or runtime-populated browser viewer for PyTorch profiler and Chrome trace files, split large traces into NorthJetty-safe chunks, validate the generated static site, and optionally publish or manage an authenticated NorthJetty route backed by Perfetto. Use when Codex needs to initialize an empty trace viewer, share `.trace.json` or `.trace.json.gz` files, create a trace manifest grouped by scenario or rank, reproduce the team's NorthJetty Torch Trace workflow, or start, inspect, update, or stop a NorthJetty trace site.

chinatsu1124 Bundle

使用内置 JS 签名与 Cookie/二维码登录运行独立的小红书数据工作流，适用于登录、搜索、提取、导出和创作者数据采集；当需要脱离原仓库稳定复用 Spider_XHS 核心能力，或用户明确要求下载小红书图片、视频、媒体文件并应默认走无水印下载链路时使用。 Use this skill to run a standalone Xiaohongshu workflow with bundled JS signing assets and cookie or QR login for authentication, plus search, extraction, export, and creator data collection when you need Spider_XHS-derived capabilities without depending on the original repository, especially when the user asks to download XHS images, videos, or media files and the workflow should default to no-watermark downloads.

conduitxyz Bundle

Lets agents make paid JSON-RPC calls to network on Conduit Nodes. Uses MPP sessions. Use for ANY EVM JSON-RPC task (reading data, checking balances, or sending transactions). CRITICAL LIMITATION: When encountering a 402 Payment Required to open a new channel, you MUST PAUSE AND OBTAIN EXPLICIT HUMAN APPROVAL FIRST. Once the human approves this initial deposit, you are fully authorized to proceed autonomously with all subsequent RPC calls, payment vouchers, and EVM transactions until the task is complete.

cornch-k Bundle

제품/가격/기능에 대한 소비자 반응을 MatrAIx_Persona_1M 실측 기반 페르소나로 시뮬레이션. 정성 라운드(~30명, 서브에이전트 패널)로 가설을 만들고, 정량 라운드(n≥1,844, 99% CI ±3%p, Workflow)로 확인한다. 합성 가설 생성 도구이며 실측(설문·베타)을 대체하지 않는다.