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.
-
niftymonkey Bundle Work RouterUse when deciding, for a unit of work (an assignment with a definable done-state), whether to keep it in the main thread or route it off-thread, and by which mechanism. Fires at plan/decomposition time over each unit of the work-list, and reactively when a sub-task reveals itself as routable. Produces a keep-or-route decision carrying lane, mechanism, autonomy posture, done-contract, and return path. Triggers on "should I delegate this," decomposing a plan into units, a verbose/parallel/long-running sub-task surfacing mid-work, and any "keep this in the conversation or push it off-thread" moment.
-
xiaolai Skill WorkflowOrchestrate strict TDD implementation across planner, test designer, spec adversary, implementer, coverage auditor, mutation auditor, and reviewer subagents.
-
xiaoweidotnet Bundle Planning And Task Breakdown将 spec 或需求拆解为有序、可执行的任务列表。当用户有一份 spec 需要落地、感觉任务太大无从下手、需要评估工作量、或需要编排并行工作时使用。触发词:拆任务、任务拆解、出计划、实施计划、排期、task list、plan。
-
y-a-v-a Bundle AttributionUse this skill when the user wants to add author attribution to a project, for example to a README.md or as a footer on a website. Handles bare invocation (falls back to git config), explicit name/email/website arguments, and free-form placement instructions.
-
y-a-v-a Bundle CodexDelegate a coding task to OpenAI Codex CLI for implementation. Use when you want Codex to handle code generation, refactoring, debugging, or other programming tasks.
-
yanhua1010 Bundle Self Media Content Workflow通用自媒体内容生产与经营工作流。用于自媒体内容创作、选题策划、热点或竞品研究、多平台改写、短视频脚本、数字人视频、发布包、公众号草稿、内容数据分析、周复盘、月复盘和继续未完成任务。负责识别请求类型,调用创作简报、内容策略、热点竞品、平台文案、短视频、数据复盘和交付归档模块,并管理方向确认、标题确认、终稿确认和发布授权。
-
yasserstudio Skill Perfex EmailUse whenever the user is sending, rendering, or debugging transactional email in a Perfex CRM module — `$this->emails_model->send_simple_email`, `send_mail_template`, email template files under `views/emails/`, admin-recipient fallback chains (`my_module_admin_email` → `contact_form_notification_email` → `smtp_email`), retry queues with exponential backoff stored in `tbl<module>_email_retries`, or cron-driven retry processing via `after_cron_run`. Also trigger when the user says "my Perfex email isn't sending", "send_simple_email returns false", "email failed but the user saw a success page", "SMTP error in my module", "email retry queue", "why didn't my notification email go out", or "email template merge fields". Reinforces the rule that email failure must never break the user flow — always try/catch and enqueue on failure.
Audited -
yaxeen Bundle Email HooksUse when writing email or newsletter subject lines, preview text, opening lines, or full emails (value newsletters, launches, outreach) for any niche or business, or when diagnosing low open or click rates.
-
0xnyk Skill Va PrepUse when triaging inbox or calendar into a review packet. Do not send or book.
Audited -
astarlab-s Skill Scope CutterUse when a task is growing beyond one session: split it into the smallest landable slice and an explicit deferred list.
-
astarlab-s Skill Plan Then ExecuteUse when starting any non-trivial coding task: produce a spec and a step-ordered plan, get approval, then execute step by step with checkpoints.
-
architektapx Bundle Vdd SetupEnvironment check for the Vibe Driven Development workflow.
-
arcticfox2029 Skill CaptureWrite down a procedure worth keeping — a multi-step process, a trap that cost real time, or something that has now come up three times. Use it the moment you finish such a task, while the details are still exact.
-
avinava Bundle Mule OpsAnalyze MuleSoft runtime health across one or more applications using Anypoint logs, metrics, deployment state, and cross-system correlation. Use for production or non-production health checks, incident windows, error spikes, latency or memory investigations, deployment-impact checks, and recurring operational reviews. Use the available Anypoint connector when configured, or apply the same evidence workflow to exported telemetry. Do not use for source-code changes unless the user also requests a fix.
-
cadasto Skill Aql AuthoringThis skill should be used when the user asks to "write an AQL query", "optimize an AQL query", "review AQL", or "query openEHR data" — the multi-step authoring/optimization workflow for AQL (Archetype Query Language) over openEHR clinical data. For a one-off explanation of an existing query or a single AQL keyword/operator (no authoring), the `/openehr-explain` command suffices.
-
cadasto Bundle Openehr AssistantThis skill should be used when a conversation touches openEHR outside a task owned by a dedicated skill — e.g. "what is an archetype?", "how do openEHR templates work?", "which composition category fits this data?", "find me a guide on X", "where do I start with openEHR modeling?" — or names openEHR concepts (ADL, CKM, RM types, OPT, terminology bindings, CGEM). Provides general openEHR awareness, guide browsing (`guide_search` / `guide_get`), clinical modeling guidance, and tool/skill routing. Not for focused tasks owned by a dedicated skill — archetype authoring/linting, template authoring, composition building, AQL authoring, artefact diffing, or demographic modeling — route those to the matching skill; this skill is the awareness and routing layer.
-
ed3design Skill Bom Validation WorkflowUse when validating a Bill of Materials (BOM) for a Maker-3D project — an embedded controller project, a speaker/audio build, a smart-home build, or any other physical build with more than 5 components. Trigger on phrases like "check the BOM", "validate the parts list", "review the parts list", "missing components", "reconcile parts inventory", "check hardware stock", "what still needs to be ordered", "check BOM against stock", "audio build BOM", "BOM review". Do NOT load for software dependency lists (use package.json/requirements.txt tooling), for pure schematic checks without physical components, or when the project has only 1-2 components (cost/benefit ratio too low). Encodes the end-to-end-builder pattern: before ordering, check against the hardware stock; do not forget connections + consumables.
-
erionis Bundle Jarvis MemoryUse when a user asks Jarvis to remember, forget, correct, or consult durable context, or when a Jarvis workflow surfaces a stable candidate.
-
ex-imanity Bundle Case Design Strategy SkillTest design strategy and coverage-review guidance for requirement-based cases. Use when the user asks for 用例设计策略, 覆盖度补充, 用例评审, 边界/异常/权限/状态/埋点覆盖, telemetry/cross-end risk analysis, or when no end-to-end case generator is responsible. Also use during `case-lite` self-review when the active workflow explicitly enters coverage review / boundary-exception review. Do not trigger for `case-lite` document ingestion, chapter selection, full generation, or writeback steps.
-
hanzephyr Bundle Record Browser GifRecord and verify a GIF demonstrating a browser workflow, preserving the requested live or fixture conditions and publishing it only when requested.
-
haruki1090 Bundle PlumbThe entry point to plumb - an index of named principles that puts discipline on non-trivial work. Use when asked to "use plumb", "follow the principles", "get a plumb line on this first", or whenever a task needs real rigor.
-
defold Bundle Defold Project SetupDownloads Defold project dependencies into .deps/ folder. Also provides recommended game.project settings. Use FIRST before any other task when .deps/ folder is missing or empty, or after editing dependency URLs in game.project. Also use when creating a new project, configuring game.project, or asking about recommended project settings.
-
flying3615 Bundle Weread Text DownloaderUse when downloading purchased WeRead books into chapter-based plain text for AI reading, using a CLI workflow that logs into the WeRead web reader and writes metadata, table of contents, and chapter txt files.
-
input-output-hk Skill Speckit PlanExecute the implementation planning workflow using the plan template to generate design artifacts.
-
ipea Skill CommitStage, verify, commit, and push geobr changes. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the touched-package test gate first; never force-pushes, never skips hooks, never auto-merges.
-
maddada Bundle Ghostex Computer UseUse this skill when the user asks for Ghostex Computer Use, Desktop Control, or native macOS app automation. It wraps the CLI-first Trycua workflow so agents can drive the computer and desktop apps without the user needing to remember `$cua-driver`.
-
maddada Bundle Ghostex Manage BeadsUse this skill whenever you are asked to work, tackle, pick up, or fix a Ghostex project board bead or card by id, and when managing beads with the normal machine-installed `bd` CLI: creating, updating, commenting on, reviewing, closing, or linking the session you are working in to a card. It covers linking this session to the bead, the project swimlane workflow, external refs, and safe examples for making review beads.
-
mnttnm Bundle Designing DashboardsDesign modern, actionable dashboards through collaborative workflow. Use for any dashboard task—creating new dashboards, revamping existing ones, choosing layouts, selecting charts, designing widgets, or validating designs. Coordinates requirements, strategy, design, and validation phases with user checkpoints. Never assumes preferences; always collaborates.
-
zavora-ai Skill Email OperationsSearch, read, organize, draft, and send email through connected email services. Use for inbox triage, threaded correspondence, attachments, reply drafting, or sending messages; treat sending, deleting, moving, and changing labels as external writes.
-
zenstackhq Bundle Zenstack Access ControlAdd access control to a ZenStack V3 schema. Use when writing access policies (@@allow / @@deny), the auth() function, field-level rules, post-update rules, or setting up the policy plugin and $setAuth runtime. (For data validation — @email/@length/@@validate — see zenstack-querying.)
-
zhuozhuocrayon Skill Git WorkflowGit 提交规范。 用户要求提交、commit、拆分提交、起草 commit message、整理待提交范围或处理暂存区时必须使用。 用于区分工作区知识库提交与非工作区项目提交:默认按工作区规范,用户明确要求提交其他项目时遵循项目自身规范。
-
ztnkv Skill ListsWorks with the user's lists in lists/ — tasks, films, books, games, workouts, etc. Detects the intent to operate on a list ("add a task", "add to films-to-watch", "mark as done", "show my book list") and picks the right list using the descriptions and trigger patterns in lists/index.md. Supports — add (append item), check (mark done), uncheck, remove, show (display the list), create (create a new list, only after confirming with the user). If the requested list is not in lists/index.md, never creates it silently — always confirms creation with the user.
-
smith-horn Bundle Wave PlannerTransform project issues into execution-ready implementation plans with risk prediction, wave-based organization, specialist agents, and TDD workflow
-
akiselev Bundle DeepthinkInvoke IMMEDIATELY via python script when user requests structured reasoning for open-ended analytical questions. Do NOT explore first - the script orchestrates the thinking workflow.
-
akiselev Bundle Decision CriticInvoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.
-
akiselev Bundle Solution DesignInvoke IMMEDIATELY via python script when user has a defined problem or root cause and needs solution options. Generates diverse solutions from multiple reasoning perspectives. Do NOT explore first - the script orchestrates the solution generation workflow.
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 zenstack-access-control, work-router, workflow. 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.