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.
-
ailyproject Skill Blockly Project PlanningBlockly project planning and creation workflow for no-project hardware requests. Trigger words: create project, new Blockly project, board selection, library selection, hardware plan, LED blink, sensor, actuator
Audited -
ironlint Bundle Cleanup Build ArtifactsRemoves transient build artifacts this task produced in the ironlint repo before declaring work done. Use at the end of any task that ran `cargo build --release`, `cargo mutants`, `cargo llvm-cov`, generated a one-off binary, wrote a scratch file like `pr.diff` or an ad-hoc tarball, or any other throwaway output. Do NOT use to wipe the actively-iterating `target/` directory.
-
jppuche Skill Advance PhaseAdvance the project to the next workflow phase. Validates exit conditions, updates STATUS.md and CHANGELOG-DEV.md, runs doc validation. Use when: "advance phase", "next phase", "close phase", "phase complete", "mark phase done".
Audited -
liorvainer Bundle TurborepoTurborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
-
pax-k Bundle Build Right ExecutionExecute one bounded task using baseline evidence, narrow implementation, verification, evidence capture, and tracker updates. Use when the user invokes /build-right-execution, wants to work the next issue, run an evidence-driven implementation loop, verify a task, update task state, or continue execution from a prepared task queue.
-
pax-k Bundle Build Right PreflightGuide founder/product pre-execution setup before AI implementation. Use when the user invokes /build-right-preflight, wants to bootstrap a blank or existing project, capture founder intent, validate assumptions, create product truth, define MVP scope, create operating docs, create Sprint 0 tasks, or prepare the first executable AI task.
-
hades-hy-li Bundle Founders Playbook RouterDiagnose the current stage of an AI-native startup and route founders to the right stage skill. Use when a founder asks where to start, is unsure whether they are in Idea, MVP, Launch, or Scale, wants a stage assessment, wants a practical founder playbook workflow, or provides company context and asks what to do next.
-
henryzhang-zhy Skill Three Level Note TakingDistilling information into three levels of notes. Use when taking notes on a given text.
Audited -
jkamsker Bundle Forgejo OpsWork with Forgejo instances (self-hosted, Codeberg) through the fj and fj-ex CLIs instead of hand-rolled curl — PRs, issues, releases, Actions runs, full CI log download, artifacts, cancel/rerun, workflow dispatch, and secrets. Use for any repo whose remote is a Forgejo host, when CI fails on Forgejo Actions, or when fj argument-order errors appear ("unexpected argument found"). Not for Gitea (use gitea-ops) or GitHub (use gh).
-
kylinmountain Skill Meeting SchedulerProfessional meeting scheduling and coordination assistant
-
nightnzh Bundle Android Strings Localized TranslateUse when the task is to fill missing translations for `app/src/main/res/values/strings_localized.xml` into the 9 non-English `values-*` locale files, while preserving existing translations and forcing all 10 `strings_localized.xml` files to match the base file's line layout exactly.
-
ootto-ai Skill Reply In Your VoiceDraft a reply to any message that sounds like you, learned from your own past emails. Use when the user says "reply in my voice", "write this like me", "draft a reply that sounds like me", "respond to this email", "match my tone", or "answer this in my style".
Audited -
ootto-ai Skill Meeting Notes To Action ItemsTurn raw meeting notes into owners, deadlines, and follow-up emails. Use when the user says "turn my notes into action items", "meeting follow-up", "who owns what from this meeting", "action items from these notes", "send meeting follow-ups", or "what did we decide".
Audited -
ootto-ai Skill First Touch Follow UpWrite the opening reply to a brand-new lead in a warm, human tone. Use when the user says "reply to this lead", "first follow-up", "respond to an enquiry", "answer a new lead", "write a first-touch email", or "new lead reply".
Audited -
ootto-ai Skill Dormant Client ReactivationWrite a warm "let's reconnect" note to a past client, built from real history. Use when the user says "reconnect with an old client", "win back a past client", "reactivate a dormant client", "reach out to a former customer", "re-engage a lapsed client", or "warm reconnection email".
Audited -
ootto-ai Skill Calendar CleanupDecide what to keep, move, shorten, delegate, or decline on an overloaded week so your real priorities get done. Use when the user says "calendar cleanup", "too many meetings", "clean up my week", "what should I decline", "free up focus time", or "review my schedule".
Audited -
ootto-ai Skill Meeting Scheduler ReplyPropose and confirm meeting times without the back-and-forth — read a request thread and draft a reply that locks in a time. Use when the user says "schedule a meeting", "propose times", "find a time to meet", "reply to schedule", "book a call", or "send my availability".
Audited -
rainzzzyyy Skill Add Task根据用户描述创建任务条目,自动判断归属(已有项目、新建项目、跨项目复制),插入到合适位置。当用户说"添加任务""新建任务""加一个任务""创建任务""我要学""我要做"时触发。
-
rokyytr2 Bundle BetterthinkEnforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's memory file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user wants more disciplined thinking, fewer assumptions, and higher-confidence execution.
-
sagargupta16 Skill Git WorkflowGit conventions covering branch naming, conventional commits, PR format, squash strategy, and protected branches. Use when committing, branching, opening PRs, or setting up a git workflow for a project.
-
tomasb2bc Bundle MonitorAutonomous watchdog for long-running processes. Three modes: standard (cron polling with delta ETAs), brief-driven (--brief, derives checks from a brief file for cross-session work), watch (--watch, event-driven with heartbeat fallback). Use when the user says /monitor, 'monitor this', 'watch this', 'track progress', 'keep an eye on', or wants to know when a running task will finish.
-
tomasb2bc Bundle PackageShape any deliverable for its specific audience. Loads an audience profile, then formats the output so the reader gets exactly what they need -- no jargon they don't know, no details they don't care about, in the format they prefer.
-
abpilot-cc Skill Graph World TSTypeScript implementation workflow for GraphOS world projects. Use after graph-world closes the graph design loop, then bootstrap npm/TypeScript, implement Systems and EventSystems, regenerate types, and wire runtime registration.
-
abpilot-cc Bundle Graph World BevyRust + Bevy (headless app/ecs/time only) implementation workflow for GraphOS world projects. Use after graph-world closes graph design, and use graph-management for graph reads/mutations before bootstrapping GraphOS project files and initializing a Rust runtime without Bevy rendering stack.
-
adamradek-ux Skill Session CaptureAt the end of a work session (or on demand) it sweeps the current session and extracts four categories — decisions, corrections/lessons, new references, pending tasks — and PROPOSES writes to the right places (decisions log, lessons + memory, memory references, inbox/notes). Writes nothing without an OK (propose → OK → write). Human-in-the-loop version of the self-evolving memory pattern. Run AFTER the task is finished; the completion gate before declaring done is verify-before-done, not this skill. Triggers: "capture session", "what should I remember from this session", "log this session", and Czech aliases "zapiš session", "ulož co jsme zjistili".
Audited -
adamradek-ux Skill Verify Before DoneCompletion-check gate to run BEFORE declaring a task done. Walks through success criteria, factual claims (numbers/URLs/features/processes), writing conventions (propose-then-write, frontmatter, naming, no leftover placeholders) and scope creep; explicitly admits what failed or was skipped. Use at the end of every multi-step task, especially before writing into a notes vault. Run BEFORE saying done; recording findings into persistent memory is session-capture's job (runs after completion). Triggers: "done?", "verify before done", "completion check", "before-done", and Czech aliases "hotovo?", "ověř než dokončíš".
Audited -
ai-native-camp Skill Git Onboarding Workflow현재 git 상태를 분석하고 GitHub Flow 기준으로 다음 단계를 안내합니다. "다음에 뭐 해야 돼?", "워크플로우", "git 흐름" 같은 질문에 사용됩니다.
Audited -
astronomer Skill Functional TestsUse when writing, editing, reviewing, or running functional (end-to-end) tests for the Astronomer APC repository. Covers scenario setup, testinfra patterns, kubeconfig helpers, fixture usage, flaky test handling, and test organization across unified/control/data installation scenarios.
-
azhi-ss Bundle Academic Figure WorkflowPlan, generate, inspect, and refine academic figures from repositories, papers, draft notes, paper URLs, PDFs, or reference images. Supports fast-track draft-to-figure generation and user passthrough mode.
-
bartwaardenburg Bundle Structured DataFixes structured data issues — adds and validates JSON-LD markup with Schema.org types including Organization, WebSite, Product, Article, FAQPage, BreadcrumbList, entity linking, and author attribution so AI search engines can understand and cite website content. Use when asked to "add JSON-LD", "fix structured data", "add schema markup", "improve structured data score", "add Organization schema", "add BreadcrumbList", "fix Schema.org", "add product markup", "add FAQ schema", "add author markup", or any JSON-LD or Schema.org task.
-
benedictking Bundle Upstream Check检查 Claude Code / Codex 上游版本变更,对比本地版本,识别协议/工具/用法相关更新并追加 TODO 提醒
-
berserkdisruptors Skill Context CommitWrite contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed. Validates scopes against the codegraph.
-
besty0728 Skill Subagy DispatchThis skill should be used when the user wants to dispatch / delegate / send a coding task to the sub-agy backend for asynchronous execution. Triggers on: "派发", "dispatch", "delegate", "派给 agy", "antigravity", "agy", "把任务交给 agy", "后台执行代码任务", "异步执行计划". It writes raw task text to the inbox, runs `sub-agy run`, then blocks with `sub-agy watch` and transitions to harvest.
-
betterthantomorrow Skill SquintSquint ClojureScript development — writing Squint code, compilation, REPL workflow, debugging, and tooling. Use when: working with Squint projects, planning, writing, or reviewing Squint code, .cljs files compiled to .mjs, Squint REPL sessions, debugging compiled output, checking whether clojure.core functions exist in Squint, or setting up Squint builds. Use whenever you are using Backseat Driver tools with Squint.
-
betterthantomorrow Bundle BabashkaWrite idiomatic Babashka (bb) scripts and modules. Covers babashka.fs, babashka.process, babashka.cli, babashka.http-client, and built-in namespaces. Use when: writing bb scripts, creating or modifying a task, REPL-driven Babashka development, editing .clj files in directories with bb.edn or scripts/ folders, using Backseat Driver tools with Babashka.
-
betterthantomorrow Bundle Babashka TasksWrite idiomatic bb.edn tasks: thin wrappers delegating to scripts/*.clj modules. Use when: creating or modifying a bb task, babashka tasks, editing bb.edn or {scripts,bb}/*.clj files, using Backseat Driver tools with Babashka.
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 blockly-project-planning, cleanup-build-artifacts, advance-phase. 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.