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.
-
malik-xae-12 Bundle Project ScaffoldProject Scaffold & Vibe Coding Workflow
-
danthamanvoiss Skill Appointment Setting PlaybookDraft appointment-setting sequences, qualification gates, and calendar handoff prompts using supplied lead context.
-
danthamanvoiss Skill Context First Workflow GuideDocument the simplest reliable order for resolving context, routing work, and handing outputs between skills.
-
megabadcoder Skill UverifyUse after execute to attack the change and demonstrate how it's broken. Default stance — the change is broken; prove and demonstrate it. Builds an attack checklist (happy-path / negative / invariant / interface hypotheses), runs each freshly, smokes the end-to-end, writes a short summary to the task file's Verify section, loops back to execute on any demonstrated break.
-
megabadcoder Skill HandsoffContract for hands-off mode — the ultrapack workflow variant that minimizes user prompts after Design, takes the safest reversible path, and logs every auto-choice for one end-of-task review. Referenced by the workflow entry point and child skills (udesign, uplan, uexecute, uverify, ureview). Read when the task file's **Mode:** header is `hands-off`.
-
megabadcoder Bundle Attack LoopRun a bounded implement-attack-repair loop for a user-specified task. Use when work needs repeated independent criticism: perform the task, dispatch a fresh attacker, verify significant findings, repair them, and stop on a clean attack or the user's round limit.
-
megabadcoder Skill Git WorktreesUse when a task needs isolation from the current workspace. Picks a worktree directory via a fixed priority order, verifies it's gitignored, creates the worktree, auto-detects project setup, runs baseline tests.
-
benjaminastera Bundle Workflow PatternsWorkflow Patterns
-
megabadcoder Skill MakeOrchestrate the full Ultrapack workflow in Codex: create or resume a task file, design, plan, execute, verify, review, and validate the observable goal. Use when the user asks to build, fix, or deliver a non-trivial change with the complete workflow.
-
megabadcoder Skill UplanUse after design to turn a validated spec into a lean implementation plan. Outputs the `## Plan` section of the task file — files, line numbers, class/method names, invariants, test strategy, order. Ends with a scope-creep / simpler-way check.
-
megabadcoder Skill SummaryProduce a compact, zero-context handoff for the current Codex work and, after user confirmation, save it to the active task conclusion or a new task summary file. Use when the user asks to preserve progress for a later session.
-
megabadcoder Skill UdesignUse before any creative work — features, components, behavior changes. Turns an idea into a validated spec with explicit tradeoffs and unknowns, and splits scope into multiple tasks if it's too large. Output is the `## Context` and `## Design` sections of the task file.
-
latticecast Bundle Developing ProgrammingPost-code workflow — test, format, lint, commit. Also handles versioning (CHANGELOG.md + package version bumps). Use after implementing code changes or when the user specifies a version.
-
huqy123 Skill Task EfficiencyUse when investigating, implementing, or reviewing a cross-project development task and the verification scope must match the risk.
-
liuliuliushifu Bundle Reme MemoryUse when the task depends on prior project decisions, recurring debugging patterns, user preferences, or multi-session continuity. This skill retrieves relevant local ReMe memories before work and stores durable new learnings after important tasks, using local file memory with hybrid vector plus FTS retrieval.
-
andersonlimahw Bundle OrchestrateFan a large task out across parallel AI agents. Planners scope and publish tasks, workers execute, and a script reconciles the tree from disk. Use when explicitly invoking /orchestrate with a large goal that benefits from parallel decomposition.
-
andersonlimahw Skill Gh WorkflowManage GitHub Actions workflows and runs via gh CLI.
-
andersonlimahw Skill New DB SchemaDatabase schema design workflow. Use when creating or modifying database schemas, coordinating between backend, data, and QA engineers.
-
andersonlimahw Bundle Opencode Subagent> Cross-harness skill that teaches Claude Code, Codex (OpenAI), and Antigravity (Agy) how to use OpenCode as a subagent. Covers delegation triggers, task formatting, provider routing, result handling, and the complete protocol for efficient subagent orchestration.
-
andersonlimahw Bundle Task InterrogatorInterrogatório implacável para planos e designs, uma pergunta por vez, até chegar a entendimento compartilhado. Estressa planos antes de implementar, sem produzir artefatos. Use quando o usuário disser "interroga", "grilla", "stressa esse plano", "me entrevista sobre", "vale a pena fazer isso?", "o que pode dar errado?". Se o objetivo também for gerar documentação (CONTEXT.md, glossário, ADRs) durante o interrogatório, use doc-driven-grilling. Baseado em grill-me/grilling de Matt Pocock.
-
givepro91 Bundle IOS Device AutomationUse when a task needs a physically connected iPhone or iPad driven without human hands — tapping, swiping, typing, granting system permission prompts, taking device screenshots, or recording the device screen (App Store review demo videos, real-device bug reproduction, verifying a build on hardware rather than a simulator). Also use when simulator automation (idb/simctl) is insufficient because the behavior only appears on real hardware.
-
john-walks-slow Skill Workflow Leader项目领导工作流。当用户给出愿景希望 AI 自主、持续推进项目方向时使用。
-
john-walks-slow Skill Workflow Manage Tasks任务分派工作流。当用户一次提出多条任务、需要批量派发子代理并跟踪进展时使用。
-
john-walks-slow Skill Workflow Troubleshoot根因分析工作流。排查复杂问题时必须遵守此流程分析原因。
-
john-walks-slow Skill Workflow Implement Review实施交付工作流。无论是需求开发还是问题修复,都必须遵守此流程完成实施、验证、检视与提交。
-
striderkein Skill Voice Proxy本人の声のクローン(合成音声)で引数で渡されたテキストを代読する。発言内容のテキストを話し言葉スクリプトに整形し、TTS で音声合成して仮想オーディオデバイス経由で会議アプリに流す。「ミーティングで音声流して」「合成音声で発言して」「代読して」「meeting voice」等で発動。
-
hstdt Skill Translation CoordinatorCoordinates translation of an Xcode project or its String Catalogs (.xcstrings) into other languages. This is the main skill to activate when asked to work on translating strings, adding languages or working with .xcstrings files. Handles the full workflow: preparing the project for a new language, fetching untranslated strings, delegating translation work, and verifying results.
-
royalmilkteamaster Bundle Milktea Skills Grill Me 2由使用者明確啟動的中文規劃流水線入口。先用一次選擇進入精簡規劃或完整規劃;局部新增、修改、刪除或 Bug 修正可沿用既有需求與架構時,快速確認本次成果後產生 Spec 與 Tickets;新專案、新功能或需要新決策時,依序確認需求與架構。最後產生新的 Implement Task 交接,不在本 Task 實作。
-
royalmilkteamaster Bundle Milktea Skills To Ticket 2將已核准的中文 Spec 拆成可獨立派工與驗證的垂直 Tickets,確認需求覆蓋、阻擋關係及必要寫入邊界,經使用者核准後固定寫入 docs/work/功能名稱/tickets/,並產生可貼到新 Implement Task 的交接文字。由 milktea-skills-grill-me 在拆票階段調用,或在使用者要求把已核准 Spec 拆成 Tickets 時使用;不決定模型、Reviewer、執行環境或實作方式,不開始實作。
-
royalmilkteamaster Bundle Milktea Skills Brownfield Refactor Implement 2執行 Brownfield Refactor Planner 已核准的重構方案、Spec 與 Tickets,沿用 Implement 的派工、雙 Reviewer、證據共識與驗收流程,並確認重構後原有功能仍然正常。使用者把 Brownfield Planner 的交接內容貼到新 Task 時使用;不重新規劃或擴大範圍。
-
ckodex-labs Bundle Email ValidatorValidates email address format and MX record reachability
-
laginho Skill ForemanRuns a sweatshop run with someone watching — launches the driver as a background task, checks in every 30 minutes, cleans up after a crash, and hands the human a summary at the end. Use when asked to "run the foreman", "supervise the sweatshop", "babysit the loop", or with /foreman.
-
laginho Skill StandupProject-state brief at the start of a work session: what was done recently, what is open, what to pick up next. Use when the user asks for a standup, "where were we", "what's the state of the project", or invokes /standup. Reads the repo's local issue tracker (.scratch/) and git; not a daily/calendar brief.
-
projetvs-pdi Bundle Email SenderEmail Sender Skill (SMTP + TLS)
-
chambear2809 Bundle Cisco Ucs Ta SetupUse when configuring Cisco UCS Manager records, task inputs, templates, or cisco:ucs data in Splunk.
-
chambear2809 Bundle Splunk Supported Addons SetupUse when the user asks for Splunk-supported add-on coverage, supported-addons gap analysis, Unix or Linux add-on setup, database add-ons, Microsoft Exchange, Microsoft SCOM, NetApp ONTAP, Carbon Black, Symantec Endpoint Protection, Splunk_TA_nix, Splunk_TA_Linux, Linux CollectD, auditd, *nix scripted inputs, or router guidance before using splunk-app-install. Resolve Splunk Supported Add-ons to the correct install, configuration, forwarder, ingest, and post-ingest readiness 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 project-scaffold, appointment-setting-playbook, context-first-workflow-guide. 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.