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.
-
bbrysonelite-max Bundle Doc KeeperThe project-agnostic Document Keeper. Use on ANY project when its living/dashboard docs have drifted from reality — after a PR merges, when a decision/convention is locked, at session close (after context-keeper), or when the user says "reconcile the docs" / "update the docs" / "the docs are stale". Runs the doc-keeper workflow directly; it DISCOVERS whatever living docs the project actually has (README, CHANGELOG, status/handoff docs, ADRs, docs/, a domain index, punch-lists) and reconciles them to current truth via ONE docs PR on the repo's default branch. Docs only — never code; never merges. For the Tiger Claw repo specifically, use the specialized `tiger-doc-keeper` instead (it knows that repo's SOTU/PROGRESS/CI guards).
-
bbrysonelite-max Bundle Ground TruthThe first move of every task, and the doctrine every other skill inherits. You never act on, or say, anything about code, data, or system state until you have seen with your own tools that it is true — right now, in the real place. Memory, docs, assumptions, and the shape of code are never the starting point and never proof. Use at the start of any task, before reporting anything as done, before writing to a canonical ledger (VERIFIED.md/SOTU), and any time you are about to state something you have not directly observed. When Brent says "ground truth", "ground this", "is that grounded", "prove it", "how do you know", or "verify don't assume", invoke this first.
-
bbrysonelite-max Bundle Gws WorkflowGoogle Workflow: Cross-service productivity workflows.
-
bbrysonelite-max Bundle Tiger Doc KeeperThe TIGER CLAW Document Keeper. Use when the Tiger Claw repo's living docs have drifted from reality — after a PR merges, when a decision/convention is locked, at session close, or when Brent asks to "reconcile the Tiger docs" / "update the Tiger docs". Runs the tiger-doc-keeper workflow directly to sync SOTU/NEXT_SESSION/PROGRESS/TO-DO/VERIFIED/ADRs/queues/Desktop punch-lists to current truth via ONE docs PR, respecting the repo's doc-CI guards. Docs only — never code. For ANY OTHER project, use the agnostic `doc-keeper` instead.
-
bbrysonelite-max Bundle Gws Workflow Meeting PrepGoogle Workflow: Prepare for your next meeting: agenda, attendees, and linked docs.
-
bbrysonelite-max Bundle Gws Workflow Email To TaskGoogle Workflow: Convert a Gmail message into a Google Tasks entry.
-
bbrysonelite-max Bundle Gws Workflow File AnnounceGoogle Workflow: Announce a Drive file in a Chat space.
-
bbrysonelite-max Bundle Gws Workflow Weekly DigestGoogle Workflow: Weekly summary: this week's meetings + unread email count.
-
wsxwj123 Bundle Task Flow非开发实质任务的统一流程:把数据处理/生信分析/机器学习/统计分析,各领域的分析/撰写/总结/文献综述/评估/决策评估这类任务,按 立项分诊→拆解计划→产出→迭代→交付 管起来;并统管跨技能混合任务(如"先做生信分析再写成投稿论文""分析完出一份带图的报告")的全局与接缝——这类没有任何单一专门技能管全局,必须由本技能接;也对既有产出做用户签字标准的独立验收。显式让位:开发任务(写代码、建工具、写脚本、做网页/App、开发skill、加功能、修bug、重构、发布部署)请走 dev-flow,task-flow 不接(例外:分析证据类一次性脚本归本技能硬验证轨);被单一专门技能完全覆盖的任务(纯写综述→review-writing、纯写论文→general-sci-writing、纯审稿→reviewer-simulator、纯出题→teacher-paper 等)优先让那个技能,task-flow 只在用户要时独立把一道关。微任务(一次性问答、单文档小改、解释一段内容/报错、查一个事实)不入流程、直接做完。
-
wsxwj123 Bundle Workflow GuardUse when you want Claude Code to enforce a mandatory edit workflow using PreToolUse hooks, activation markers, and stale-session blocking.
-
wsxwj123 Skill Meeting Insights AnalyzerAnalyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
-
mindgoblinstudios Bundle Grim Dev Tiramisu Task Decomp(grim:dev:tiramisu-task-decomp): (Tiramisu): Convert an imperative plan into a functional dependency diagram (DAG) and subagent-ready task packets. Use when the user wants to decompose a plan into parallelizable, dependency-safe execution steps.
-
mindgoblinstudios Bundle Grim Council Guild Ops Postmaster Email TriagePostmaster (Email Triage): Inbox shredder. Triage your mail. Keep what needs a reply, file what's waiting, and turn noise into confetti.
-
kevinaimonster Skill Email Writer邮件助手。写商务邮件、回复邮件、跟进邮件,中英文都支持。当用户说「帮我写邮件」「回复邮件」「写封邮件」「email」「跟进邮件」「催促邮件」「感谢邮件」「道歉邮件」「介绍邮件」「邀请邮件」「write an email」「reply email」「follow up email」「business email」时触发。关键词:邮件、email、写邮件、回复邮件、商务邮件、跟进邮件、催促邮件、感谢信、道歉邮件、介绍邮件、邀请函、cold email、开发信、询盘、报价、求职邮件、cover letter、推荐信、通知邮件、会议邀请、邮件模板、邮件签名、subject line、邮件主题
Audited -
kevinaimonster Skill Git WorkflowGit 工作流顾问。帮团队设计 Git 分支策略、PR 流程和发布规范。当用户说「Git分支策略」「Git工作流」「git workflow」「分支管理」「Git flow」「trunk based」「发布流程」「PR规范」「合并策略」「版本管理」「分支命名」时触发。关键词:Git工作流、分支策略、Git flow、trunk based、GitHub flow、分支命名、PR流程、合并策略、发布流程、版本号、语义化版本、hotfix、release branch、feature branch、代码合并、冲突处理、rebase、squash、cherry-pick、monorepo、tag、版本管理
Audited -
bokuwalily Skill Vercel Dns Catchall EmailVercel DNS管理のドメインに無料のcatch-allメール受信転送を付けたい時。第三者アカウント作成なし・DNSレコード追記だけでForward Emailにより全アドレスをGmail等へ転送する。送信は対象外(受信のみ)
-
d-wwei Skill Fsi Pe Cmd Dd PrepPrep for a diligence meeting or expert call — usage: /dd-prep [company name] [meeting type]
-
d-wwei Skill Fsi Er Morning NoteDraft concise morning meeting notes summarizing overnight developments, trade ideas, and key events for coverage stocks. Designed for the 7am morning meeting format — tight, opinionated, actionable. Triggers on "morning note", "morning meeting", "what happened overnight", "trade idea", "morning call prep", or "daily note".
Audited -
kinginyellows Skill Memory Recall PatternRecall-Before-Act pattern for ruvector — query past learnings via hooks_recall at workflow start. Use when authoring commands or agents that should seed a workflow with relevant institutional memory before executing.
Audited -
kinginyellows Skill Stack Provider RouterResolve which stacked-PR provider is active and route provider-specific work to it, or refuse when the state is ambiguous. Use when a workflow needs to know whether Graphite or GitHub native stacks is in effect before running a stack operation.
-
kinginyellows Skill Github Stack AmendFold working-tree changes into the current branch commit and re-submit via gh stack. Use when user says "amend this" or "add this to the current PR" on the github stacked-PR provider.
-
kinginyellows Skill Github Stack MergeMerge a stacked PR via gh stack merge. Use when the user says "merge my stack" or "land this PR" on the github stacked-PR provider and the target is fully reviewed and ready.
-
kinginyellows Skill Github Stack SetupCheck GitHub-native stacked-PR prerequisites — gh CLI, authentication, and the official github/gh-stack extension. Use when first installing the plugin, after gh auth changes, or when /stack:status reports PARTIAL_TOOLING for the github provider.
-
kinginyellows Skill Github Stack SubmitStage, commit, and submit uncommitted changes as a GitHub-native stacked PR. Use when user says "submit this" or "ship it" on the github stacked-PR provider and has uncommitted work to turn into a PR.
-
kinginyellows Skill Memory Remember PatternTiered-Remember-After-Act pattern for ruvector — record learnings via hooks_remember at workflow completion with signal-strength tiers (Auto/Prompted/Skip). Use when authoring commands that should compound institutional memory from workflow outcomes.
Audited -
kinginyellows Skill Stack Decomposition FormatStructured format contract for "## Stack Decomposition" sections in plan documents, shared by gt-stack-plan (producer) and flow:work (consumer). Use when writing or parsing a Stack Decomposition section.
-
hamza-ali-shahjahan Skill Launch PlanBuild a full launch playbook for a product — PH, HN, X, LinkedIn, email warm-up, cold outreach, pricing, brand assets. Sequenced for compounding signal.
-
hamza-ali-shahjahan Skill Auto OrchestratorIntelligent workflow orchestrator that automatically chains the right skills (spec, plan, build, test, review, code-simplify, ship) based on the current state of the work. Use when you want Claude to drive a feature or task end-to-end without manually invoking each skill.
-
hamza-ali-shahjahan Skill Planning And Task BreakdownBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
-
2799662352 Skill Deep Agents OrchestrationINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
-
mn755 Bundle Mission Control Context PackShow or build Mission Control context packs for agents. Use when the user wants to know which files, docs, and constraints are being packaged for a task, why they were selected, and where context coverage is still missing.
-
mn755 Bundle Mission Control Quick ClarifyAsk only a few high-impact Mission Control clarifying questions. Use when the user wants speed, the repo already explains most things, or the task is urgent and only 3–6 targeted questions are justified.
-
mn755 Bundle Mission Control Change RequestRun a post-handoff or mid-project Mission Control change request flow. Use when the user wants additional work classified, impact-estimated, task-created, validated, and folded into the current handoff or milestone safely.
-
mn755 Bundle Mission Control Refactor SafelyRun a safe Mission Control refactor workflow. Use when the user wants non-trivial refactors that need codebase understanding, snapshots, path locks, contracts, validation planning, and controlled risk.
-
mn755 Bundle Mission Control Existing Repo FixRun a direct Mission Control fix workflow for an existing repo. Use when the task is a bugfix or targeted change in a non-empty codebase and the Manager should classify the request, plan narrowly, request write permission, and execute safely.
-
mn755 Bundle Mission Control Scope Creep CheckAsk Mission Control whether the project is drifting beyond approved scope. Use when the task list is growing, the user asks for more work midstream, or you need a Manager recommendation on include now versus defer.
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 doc-keeper, ground-truth, gws-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.