Productivity
Productivity agent skills automate everyday work: task management, email drafting, calendars, note-taking systems, and personal workflows. Each is a small SKILL.md file your AI agent applies automatically when your request matches what the skill does.
-
andersonamaral2 Skill Claude Code SampleSkill: Python FastAPI Todo App
-
unim0cha Bundle Work Self Improvement ReviewReview the current ChatGPT Work conversation and files made available in the chat for durable corrections, preferences, and workflow lessons, then propose updates as project guidance, an instruction overlay, a patch to a provided SKILL.md, or a new skill candidate. Use when the user asks to review, learn from, distill, or preserve lessons from the current task, especially after corrections, repeated friction, or a non-obvious recovery. Always propose before exporting or applying any change.
-
unim0cha Bundle Self Improving Skills ReviewReview a completed Codex turn for durable skill improvements, using the chatgpt-codex-self-improving-skills plugin's skill-manager tools or scripts. Use after user corrections, repeated workflow friction, non-trivial debugging techniques, or when the Stop hook requests a self-improvement pass.
-
ory Skill Ory Auth Setup 2Set up a complete authentication system using Ory Network with Ory Elements as the UI layer. Use whenever the user wants to add login, registration, account recovery, email verification, account settings, or session management to a web app — even if they only mention "auth", "sign-in", or "users". Ory Elements is the default UI; only fall back to custom rendering when Ory Elements cannot be used.
-
zaxbyhub Skill Swarm 5Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.
-
ferueda Bundle Create Plan 2Create a scoped, code-backed implementation plan from a todo, spec, issue, review notes, or raw user instructions. Use when the user asks to convert requirements into a proper plan, phased implementation plan, executor handoff plan, or reviewable planning artifact before coding.
-
vxcozy Skill Analyst 2Senior engineering analyst for code review, plan review, and automation review. Use when: (1) "review this", "analyze the code", "check this plan", (2) After implementation to verify quality, (3) "is this good enough?", (4) Before marking a task complete, (5) Reviewing a blueprint from /architect, (6) Reviewing output from /refinery. Four-lens review: architecture, code quality, reliability, performance. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
-
bandersnatch0x Skill Amber 2Route an Amber task to the right governed journey.
-
bandersnatch0x Skill Amber Context Continuity 2Distill provenance-backed context, verify task Loadouts, and preserve resumable handoff state.
-
rodri-oliveira-dev Skill Authoring Github Workflows 2Author and review GitHub Actions workflow YAML safely so syntactically-valid YAML can't ship a workflow that GitHub Actions refuses to run. USE FOR: editing, adding, or reviewing any file under .github/workflows/, writing run-name/name/if/env/run values that contain ${{ }} expressions, diagnosing a run that fails with 'This run likely failed because of a workflow file issue' and no jobs starting, deciding when a workflow scalar must be quoted, validating workflows with actionlint. DO NOT USE FOR: authoring application YAML unrelated to GitHub Actions, Azure Pipelines, GitLab CI, or non-workflow YAML. SCOPE: syntactic/structural workflow correctness; pair with ci-release-governance for semantic CI/release design. INVOKES: actionlint plus git/grep for inspection.
-
mshadmanrahman Bundle Meeting Prep 2Pre-meeting context gathering across all connected systems. Pulls recent interactions, open items, and suggested talking points for any person or topic. Triggers on: "meeting prep", "prep for my meeting", "meeting with X", "prep for 1:1", "before my meeting", "get ready for sync", "/meeting-prep".
-
mshadmanrahman Skill Session Init 2Lightweight session initialization. Reads latest manifests and handoffs to resume context. Loads only what the current task needs. Trigger on session start, "resume", "pick up where I left off", "continue from last session", "init".
-
haksolot Skill Ank TddDrive an implementation test-first, red before green, against a claimed task's frozen criterion. Use when implementing a task in a repository with a .ank/ directory.
-
haksolot Skill Ank DiagnoseWork a defect back to its cause before changing anything, and close it with a regression test. Use when a claimed task's criterion names a defect in a repository with a .ank/ directory.
-
lekeopen Bundle Social Distribution SetupUse when setting up, reusing, or debugging RSS-driven multi-platform social distribution for websites, especially Make.com scenarios that read RSS or publish queues and post to Facebook Pages, LinkedIn, Email, and X through Buffer. Also use when checking why new website content was not automatically shared, why only one RSS item was posted, whether Make.com limits paused a scenario, or how to make this workflow reusable across projects.
-
lekeopen Bundle Gaoyuanwai Short Video EditingUse when editing or re-editing Gaoyuanwai vertical short videos for Douyin or WeChat Channels, especially talking-head, workflow, technology-story, screen-recording, and mixed real-footage content that needs a consistent premium style, stable captions, continuous narration, recognizable cover, background music, branded end card, or pre-publication media QA.
-
ly0o0o Bundle Nodejs Code StyleUse when writing, reviewing, or refactoring Node.js/TypeScript backend code and the task needs strict code style, concise implementation, naming discipline, type-driven design, discriminated unions, runtime validation, error modeling, async control, refactoring judgment, readable main flow, and senior-engineer code cleanliness independent of any specific framework.
-
mozilla-ai Bundle CalendarGoogle Calendar
-
poteto Skill Brain 2Read/write brain files (Obsidian vault at brain/). Use for any task that persists knowledge — reflection, planning, or direct edits. Triggers: brain/ modifications, "add to brain".
-
riktar Bundle Theoneloop InitInitialize or recheck TheOneLoop in a project by assessing prerequisites, the baseline, and development workflow configuration. Use before actionable planning or when the environment changes; does not automatically implement features.
-
riktar Bundle Theoneloop ImplementExecute all or selected stories from an approved TheOneLoop sprint, coordinating implementation, separate review, corrections, and verification. Manage branches and PRs within the agreed workflow without performing merges.
-
ruhedanghaoyigexuesheng Bundle Log Analysis Workflow按七步工作流对测试/生产日志做结构化第一轮分析,输出可执行排查建议(关键词、异常类型、调用链、模块定位、历史规律、风险等级)。 证据不足时输出缺失信息清单,禁止无依据猜测根因。 当用户要求分析日志、排查报错、解读 traceId、日志排查时使用。 触发词:分析日志、日志排查、报错分析、traceId、ELK 日志、ERROR 排查。
-
ruhedanghaoyigexuesheng Bundle Regression Test Workflow根据版本改动、历史 Bug、业务链路生成可执行回归测试清单(7 步工作流)。 当用户提及版本改动、回归范围、影响分析、发布前测试范围、hotfix 后测什么时使用。 触发词:回归测试、回归范围、影响分析、Release Note、发布前测什么。
-
dragoon0x Skill Notification Design 2Communicate without annoying. Patterns for in-app alerts, email triggers, push notification copy, and frequency capping. Use when designing notification systems or any touchpoint that competes for attention.
-
zhaoxuya520 Bundle Reverse Engineering 2Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.
12.8k -
rayekry777 Bundle Java Backend Dev Workflow规范设计、开发、修复、审查和验证 Java/Spring Boot 后端,并维护项目根目录的后端开发与设计契约及数据库表结构文档。覆盖 IDEA 工作流、架构与接口状态、依赖兼容性、SLF4J 日志、JavaDoc、DTO/VO、Service/Repository、OpenAPI/Knife4j、配置分层、数据库迁移、数据表文档和交付验证。用于后端方案设计、初始化、接口与持久化开发、数据库表总结或维护、依赖升级、问题排查、代码规范整理、本地联调、发布和部署准备。
-
wayne2wang Bundle Zilin Cat HatcherGuide a user through a multi-step intake to create realistic Codex v2 animated pet assets from their cat photo: first ask for the pet name, then present default user-facing actions by trigger/state, ask whether to change actions or constraints, then request the cat photo, then use the hatch-pet workflow for generation, QA, and packaging. Use when a user asks to generate a Codex pet, realistic cat pet, cat-photo pet, pet spritesheet, pet.json package, or wants a template-driven pet skill with editable actions such as idle, waving, waiting, running-left, running-right, failed, active working, or review.
-
signalpilot-labs Skill Dbt Testing 3Load when task involves adding, writing, or fixing dbt unit tests. Covers unit_tests YAML format, given/expect blocks, edge-case coverage, and the difference between unit tests and schema tests.
-
signalpilot-labs Skill Dbt Snapshots 3Load when task involves dbt snapshots, SCD Type 2, or tracking data changes over time. Covers strategy selection, column casing, verification, and common pitfalls.
-
ryoppippi Skill Create Pr 3Runs the full PR workflow — creates a feature branch, commits, pushes, and opens the pull request. Use when the user asks to create or open a PR ("create a PR", "push this up and open a PR").
-
terryyin Skill Dough Slice Planning 3Plans one understood, bounded story as an executable sequence of Behavior/Structure slices with outside-in proof and safe stopping points. Use when a selected story is ready for implementation planning or an execution retrospective has one bounded correction to plan. Stays within the triggering instruction's execution authority: finish after writing and reporting the plan unless that instruction explicitly also requests execution. Reports remaining slice-specific concerns or a limited no-concerns finding; does not prescribe the next workflow action or certify execution readiness. Concern evidence does not authorize execution.
-
cdeistopened Bundle Podcast Production 2Complete workflow for producing podcast episodes from raw transcript to publishable YouTube and social media assets. Four-checkpoint system for strategic decision-making plus final polished assets.
-
cdeistopened Skill Youtube Clip Extractor 2Download YouTube videos, identify compelling clips from transcripts, cut clips with ffmpeg, and generate platform-optimized on-screen text and captions. Complete workflow from URL to publishable clips.
-
florian101010 Skill Hotfix 3Fast but controlled hotfix workflow for urgent production incidents. Use when a critical bug needs an immediate targeted fix.
-
florian101010 Skill Architecture Change 3Architecture change workflow with mandatory ADR and controlled rollout. Use when proposing or implementing a structural/architectural change to the codebase.
-
mehdi-benhariz Skill PonytailForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
Frequently asked questions
What are Productivity agent skills?
Productivity agent skills automate everyday work: task management, email drafting, calendars, note-taking systems, and personal workflows. Each is a small SKILL.md file your AI agent applies automatically when your request matches what the skill does.
Which Productivity skills are most installed?
Popular Productivity skills on SkillMD right now include claude-code-sample, work-self-improvement-review, self-improving-skills-review. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Productivity skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.