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.
-
nealepetrillo Bundle RetejsThis skill should be used when the user asks to "create a node editor", "build a visual workflow", "create a node-based interface", "add rete.js", "build a node graph", "create a dataflow editor", "build a visual programming interface", "connect nodes", or needs to implement visual node editors, workflow builders, or dataflow/control-flow processing using Rete.js v2 with Lit or vanilla JavaScript.
-
nestorrd Skill Tdd PythonTest-Driven Development (TDD) workflow for Python. Use when asked to add a new feature, function, class, or module to a Python codebase. Enforces the Red-Green-Refactor cycle: write a failing test first, then write the minimum production code to pass it, then refactor. Activates when the user mentions TDD, test-first, red-green-refactor, write tests before code, or asks to implement new functionality in Python.
-
next-1688 Bundle 1688 Item Image Optimizer商品图片制作统一入口:主图优化、轮播图、详情图、背景替换、数字模特。 核心能力:verify_permission(高级版权限校验)、build_tool_url(构建工具页 URL)、configure(AK 配置)。 触发词:做一套图、做图、出图、优化主图、主图优化、轮播图、详情图、背景替换、数字模特、商品图片、改图、图片优化。 不应触发:新品发布/批量上架(走发品 skill)、品牌VI/海报/店铺装修、图片规范问答。 本 Skill 的图片制作流程已由 workflow 编排覆盖,命中触发词时直接执行 workflow。如果 workflow 无法完成任务(如纯能力问答、单命令调用、探索性使用),加载本 SKILL.md 进行推理。
-
nibzard Bundle AgentlabTask-focused command bundles for AgentLab operations in Claude workflows.
-
notque Bundle Example SkillA reusable workflow template. Customize phases for your use case.
-
observerw Bundle Skill ContainerGuide for creating effective skills with a Containerfile-first workflow. Use this when creating a new skill, updating a containerized skill, or migrating a legacy skill that still depends on scripts/ to a containerized runtime.
-
obsfx Bundle Feedback ProtocolProtocol for @feedback annotations in source code. Use when user mentions @feedback, address feedbacks, inline feedback, or when encountering @feedback markers during any task.
-
oceanbase Bundle Build Seekdb Python WheelBuild and verify seekdb Python wheels from seekdb source on remote Linux x86_64 or macOS arm64 hosts. Use when a user asks to package seekdb from a commit, tag, or branch; the workflow fetches source through GitHub SSH, runs the seekdb-bindings build, applies release-only compiler policy, handles known remote failures, verifies both supported Python ABI wheels, and returns checksums and artifact paths.
-
octaviantocan Bundle ReconBuild verified, section-by-section understanding of a project BEFORE creating or modifying anything in it. Dispatches a read-only subagent workflow that maps every convention, reads README/AGENTS.md/CLAUDE.md and the docs in full, finds and reads relevant in-project skills, surveys structure and build/test/CI, and explores the focus subsystem — with no assumptions allowed. Use when starting work in an unfamiliar repo or subsystem, onboarding to a codebase, before any non-trivial change, or when the user says "understand this project", "explore the codebase", "learn the conventions", "recon", "get oriented", or "what are the conventions here".
-
octaviantocan Bundle RouterRoute between your installed Codex skills and chain them into back-to-back workflows. Use when the user asks which skill to use, wants to pick or compare skills, asks for their most-used or top skills / skill usage stats, says "route this", "what skill should I use", "run the <name> workflow", or wants to define or run a multi-skill sequence like brainstorming → writing-plans → executing-plans.
-
olakunlevpn Bundle Olakunlevpn Git SkillsUse when creating git commits, writing commit messages, branching, pushing, or any git operation. Enforces concise commit messages, conventional commits, atomic changes, no AI attribution, and professional git workflow. Auto-triggers on any git activity.
-
olimxonuz0-lab Bundle RigorUse for any non-trivial coding, engineering, or deliverable-producing task — building a feature, fixing a bug, refactoring, designing an architecture, writing a script someone will run, or drafting a document someone will use. Enforces upfront planning before acting, rejects placeholder/stub/TODO code and unhandled edge cases, and cuts filler from responses so the final answer is dense and useful. Trigger whenever the user asks to build, implement, fix, refactor, design, migrate, optimize, or ship something — even without words like "production-ready" or "thorough." Also trigger when a task has enough moving parts that diving straight into output risks missing something (multi-file changes, unclear requirements, several edge cases, sub-steps). Do NOT trigger for single-line answers, quick lookups, casual conversation, or an explicitly requested rough/quick/throwaway draft.
-
ombulabs Bundle Rails Load DefaultsIncrementally upgrade Rails `config.load_defaults` by walking through each new_framework_defaults config one at a time. Use this skill whenever the user mentions load_defaults upgrade, new_framework_defaults, framework defaults, or wants to bring their Rails app's default configuration up to match their Rails version. Also trigger when the user mentions a gap between their Rails version and their load_defaults version (e.g., "app is on Rails 7.2 but load_defaults is 6.1"). This skill handles the iterative uncomment-test-commit workflow and the final consolidation into config/application.rb.
-
open-telemetry Bundle Database Build ReviewReview the PR produced by the Build Explorer Database workflow (.github/workflows/build-explorer-database.yml) and decide whether the generated diff is correct. Use after a nightly or manual explorer-db-builder run when a new registry release lands and the automated "[automated] Update explorer database (<ecosystem>)" PR needs sign-off, when a build produced an unexpectedly large diff, when files were/weren't deleted as expected, or when deciding whether a change needs a corrections overlay.
-
opensuse Bundle Opensuse PackagingAuthoring, modifying, reviewing, or building openSUSE RPM packages — spec files, .changes files, osc / OBS and Git (src.opensuse.org / Gitea) workflows. Use whenever the working directory has a .osc/ folder or a *.spec file, when the user mentions osc, OBS, rpmbuild, openSUSE Build Service, src.opensuse.org, the Git packaging workflow, tea, git-obs, osc fork, spec file, .changes file, rpmlint, or asks to build/submit/review/fork a package, check if packages are out of date, or open a package pull request. Covers Specfile guidelines, the Git packaging workflow, Shared library policy, Systemd packaging, Patches, Changelog format, and language-specific packaging (Python, Perl, Ruby, Go, Rust, Java, PHP, Haskell, Lua, R, Meson, Vala).
-
onekeyhq Skill 1k Git WorkflowGit workflow and conventions for OneKey development. Use when creating branches, committing code, or creating PRs. Triggers on git, branch, commit, PR, pull request, merge, workflow.
-
onevcat Bundle XinUse xin CLI to manage JMAP email (Fastmail-first). Covers search, read, send, drafts, labels, and automation.
-
openghz Bundle Anchored InstallUse this skill for checkpointed retries of substantial, multi-step shell install/setup/provisioning workflows: cache successful steps and resume after failure or interruption without repeating completed work. Trigger when the user asks for checkpoint/layer caching or resume-after-failure, names `anchored-install`, the `ai` command, or `#ai`, asks to author, edit, convert, plan, run, or debug an `#ai` manifest, or reports frequent/repeated installation failures or interruptions, especially when reruns redo completed work. Also trigger proactively when the user's task is to author a new install/setup/provisioning script whose planned side-effecting steps are costly, slow, or risky to repeat, even if caching is unstated. Initial execution of an existing vendor/third-party script, package command, or one-off installer error stays native; generic setup, idempotency, or rerun wording and a cheap or merely long/flaky script are not enough.
-
orzcls Bundle Win Disk CleanerWindows C: drive disk cleanup using free/open-source tools and PowerShell scripts. Replaces paid 'system optimizer' software. Use when users ask to: clean C drive, free disk space, clean up Windows, delete temp files, clean browser cache, clean system junk, reduce disk usage, clean WinSxS, disable hibernation, find large files, remove bloatware, or any Windows disk space recovery task. Also trigger for Chinese equivalents: C盘清理, 磁盘清理, 清理垃圾, 系统瘦身, 释放空间, 临时文件清理. Covers: temp files, browser caches, Windows Update cache, system logs, app caches (WeChat/QQ/DingTalk/Teams/Discord), developer caches (npm/pip/yarn/Gradle/JetBrains), hibernation, WinSxS, restore points, recycle bin, and recommendations for free disk analysis tools.
-
paladini Skill Add Calculation CaseUse when adding or changing a Meeting Cost calculation rule, validation edge case, or domain formula in src/meeting-cost.js.
-
openxla Bundle XprofCentral entry point for ALL XProf operations and analyses. Use this skill first for any task involving XProf traces, performance, memory, HLO ops, collecting/triggering XProf profiles, or numerical correctness verification.
-
oxc-project Skill Tsgolint Update Typescript GoUpdate the `typescript-go` submodule in the `oxc-project/tsgolint` repository, refresh the local `patches/*.patch` stack against the new upstream base, regenerate shims, open a PR, and watch CI to completion. Use when working on routine `typescript-go` bump PRs for TSGolint or when repeating the same workflow as prior submodule update PRs.
-
perhapsspy Bundle Codex Project DirectorInvoke explicitly with $codex-project-director to act as an active, non-implementing control plane that drives multiple Codex tasks or sessions toward one verified project outcome. Use only for a user-designated director or supervisor session, not a single local task, ordinary implementation, one-off review, or status summary.
-
piercelamb Bundle Deep ImplementImplements code from /deep-plan section files with TDD methodology, code review, and git workflow. Use when implementing plans created by /deep-plan.
-
pipelex Skill ReleaseAutomates the kajson release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a release", "ship it", "create release branch", or any variation of shipping a new version of kajson. The user can optionally provide changelog content inline when invoking the skill (e.g. "/release Added new encoder feature"), which will be used as the changelog entry for this version.
-
polodb Bundle Polodb ReleasePrepare, publish, resume, or verify a PoloDB release across GitHub and crates.io. Use when Codex needs to bump PoloDB versions, create a release PR, wait for protected-branch checks and approval, tag a merged release, publish the Rust crates in dependency order, trigger the repository's release workflow, add GitHub Release notes, or diagnose a partially completed PoloDB release.
-
ponylang Skill Update Ssl BuildersTwice-yearly workflow for bumping SSL builder images (OpenSSL, LibreSSL) to their latest series releases. Invoked via /update-ssl-builders.
-
proftrader Bundle Self Learning FeedbackAsks for user feedback after each task or cron job completion and runs a recursive learning flow. If output is good, asks what was good until 10 approvals; if needs improvement, asks why/how/what via multiple choice plus optional examples, uses web search and iterative thinking to resolve, and caps iterations by severity (slight 5, medium 10, severe 20). Keeps feedback non-intrusive. Use when completing discrete tasks or cron jobs for the user.
-
psacc Skill Hey EmailInteract with Hey.com email. Use when the user mentions email, inbox, checking mail, reading email, searching email, screening, reply later, set aside, or Hey.com. Trigger phrases: "check my email", "what's in my inbox", "read email", "search email", "show my feed", "what's screened out", "screen this sender", "reply later", "set aside", "mark as read", "approve sender", "reject sender", "hey inbox".
-
python-zeroconf Skill Pr WorkflowCreate pull requests for python-zeroconf/python-zeroconf. Use when creating PRs, submitting changes, or preparing contributions.
-
quickchange-frog81 Bundle Kdna LoaderDiscover and load KDNA judgment frameworks from ~/.kdna/domains/ when the task requires domain-specific judgment (review, diagnosis, critique, classification, strategy) where the same input could legitimately be interpreted multiple ways. Skip for pure formatting, factual lookup, code execution, or mechanical transformations. This skill is the entire interface to KDNA — domains themselves are not separate skills.
-
recollective-genuseptatretus377 Bundle AskproofUse this skill when a non-engineer needs to ask AI agents for proof, check whether “done” is actually verified, rewrite vague feedback such as “still broken” into actionable prompts, request minimum evidence, prevent task drift, or create handoff memory.
-
respawn-llc Skill Firefox CLIControl the user's Firefox from a terminal. Use when your task needs the user's browser or authenticated session, page navigation, tab/window control, screenshots, DOM reads, waits, or page interactions in Firefox. Do not use it as a web search replacement.
-
redclawww Bundle SavethetokensReduce Claude Code token burn with proactive compacting, task-scoped sessions, checkpoint files, tiered docs, and relevance-based context pruning. Use when a user explicitly asks to reduce context usage/cost, run token benchmarks, or optimize CLAUDE.md. Do not use to expand product scope or skip correctness checks.
-
rediumvex Bundle Social CaptionsWrite algorithm-optimized captions/descriptions for social media posts and reels. Supports Instagram (Reels, Feed, Carousel), TikTok, Threads, Facebook, and YouTube Shorts. The user sends material (text, image, script, competitor post, screenshot) and gets ready-to-use captions for ALL platforms at once, in English. Use when asked to "write a caption", "write a description", "caption for instagram", "описание к посту", "подпись для рилса", "описание для тикток", "caption for reels", "social media post", or any caption/description writing task. Also triggers when user sends an image, screenshot, or text and says something like "сделай описание", "напиши подпись", "caption this", "описание для этого".
-
raskrebs Skill SonarManaging localhost ports and dev servers: starting services, freeing ports, picking free ports, cleaning up. Use whenever a task starts a server, hits 'address already in use', or needs to know what is running.
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 retejs, tdd-python, 1688-item-image-optimizer. 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.