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.
-
technickai-openclaw-config Bundle FirefliesQuery Fireflies.ai meeting transcripts - summaries, action items, and searchable history
-
technickai-openclaw-config Skill Drive To DoneDrive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.
-
dcjanus Bundle Github CLI使用 GitHub CLI 与 GitHub 资源交互;适用于 repo、issue、PR、comment、release、workflow 等查看、更新或创建场景。创建任何 GitHub Issue 时,统一使用本 skill 的 github_issue.py,保留模板 labels/assignees 并在创建后回读验证。
-
alexzio00 Bundle FreezeScope lock for current task. Declares editable zone — everything outside is frozen (read-only). Call before starting implementation to prevent scope creep.
-
dcjanus Bundle Repository Workflow处理从本地 Git 变更到 GitHub/GitLab 协作发布的完整工作流;适用于创建或更新分支、语义化 commit message、commit、push、Issue/PR/MR 文案、inline review reply、Breaking Change 与提交范围核对。纯只读的平台查询不使用本 skill。
-
jeff-stapleton Skill RefinementValidate a ClickUp task's readiness and size it using fibonacci points. Checks for user story/description and acceptance criteria, then suggests sizing with improvement recommendations.
-
zby Skill NextSurface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".
-
zby Skill SeedAdd a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".
-
zby Skill TasksView and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".
-
nandkapadia Skill Verification Before CompletionEnforce evidence-based completion claims with actual command output. Use before (1) claiming tests pass, (2) claiming a bug is fixed, (3) claiming a task completed successfully, (4) claiming performance improved, (5) saying "ready for review". Prevents phrases like "should pass" or "that should fix it" - requires fresh verification evidence.
-
cyperx84 Skill Git Workflow GuideProvide guidance on git workflows, branching strategies, and best practices for individual and team development
-
jiunbae Bundle Obsidian TasksReads and manages tasks from Obsidian Vault's TaskManager. Supports Board.md (Kanban), Table.md (Dataview), Notes/*, with automatic workspace project sync. Use for "작업 목록", "할일 조회", "task 읽기", "obsidian 작업" requests.
-
jiunbae Bundle Context WorktreeEvaluates context similarity between new and existing work, automatically creating git worktree on a new branch when tasks differ. Activates on task start, new feature implementation, or switching to different issues.
-
ikatsuba Skill Spec TasksTask Breakdown - generates an implementation plan with tracked tasks based on requirements and design documents. Use when breaking down a design into actionable work items.
-
feixeyes Skill Draft WriteProduce a first draft from an approved outline in the AI 实践记录 workflow.
-
feixeyes Skill Outline FirstCreate and confirm article outlines before any drafting in the AI 实践记录 workflow.
-
feixeyes Skill Write ArticleEnd-to-end workflow for writing an article in the Real World AI Log project, focusing on practice-first, workflow-first collaboration.
-
sssemil Skill Codex CoopCo-operative workflow with OpenAI Codex CLI for plan review and pre-commit code review. Use this skill whenever Claude is about to present a plan to the user, propose an implementation approach, or commit code changes. Also triggers when the user mentions "codex", "co-op", "second opinion", "review with codex", or asks Claude to validate plans or changes before proceeding. This skill should fire before ANY plan is shown to the user and before ANY git commit — even if the user doesn't explicitly ask for Codex review.
-
sssemil Bundle Brutal SwarmDrain a BRUTAL.md task graph through parallel isolated workers and stacked pull requests. Managed workers use append-only phases with fresh execution context.
-
sssemil Bundle Brutal WorkerOwn one exact BRUTAL.md task or review finding through claim, isolated implementation, verification, stacked pull request publication, and an uncapped material-correctness review/fix loop. Managed workers execute one phase at a time with fresh context.
-
dwmkerr Bundle Exploration ProtocolStructured approach to explore features before production development. Templates for objectives, acceptance criteria, architecture, prototypes, and verification. This skill should be used when the user asks to "explore a feature", "start an exploration", "create a task folder", or mentions exploration protocol.
-
feixeyes Bundle Wechat Material UploadUpload 1-9 images (files or directories) to the WeChat Official Account media library (素材库→图片) using the same Chrome CDP workflow as baoyu-post-to-wechat. Use when the user needs to push local images into the公众号素材库 with default watermark and close the browser afterward.
-
ureca-corp Bundle Plan Build VerifyUse when implementing a non-trivial coding task end-to-end with built-in quality gates — plan the work into slices AND rate each slice's difficulty (tier), implement slice by slice, run difficulty-adaptive review (light=1 lens, medium=2 lenses, heavy=4 lenses + Codex) after each slice, auto-escalate a slice to full review when it turns out risky, refactor until zero critical/major issues, then guarantee the full test+build passes. Trigger for requests like "구현 계획부터 검증까지", "슬라이스별로 구현하고 적대적 리뷰", multi-step feature builds, migrations/refactors that need a verify-and-refactor loop, or whenever the user asks to build something with adversarial review + zero-issue refactoring before finishing.
-
sunxd3 Skill Python EnvironmentReference for the Bayesian workflow Python environment — uv usage, dependencies, script structure conventions, and where the Stan execution recipes live. Assumes the environment has been bootstrapped via `/bayesian-workflow:setup`.
-
sunxd3 Skill Validation ProtocolEntry/exit contract for workflow subagents — input validation, the completed-work short-circuit, structured returns with audited numeric fields, and the status.json completion record.
-
vince-winkintel Bundle Pscale OrgList, show, switch, update PlanetScale organizations, manage organization SSO and directory sync, and inspect or manage organization members and teams. Use when managing multiple organizations, switching between accounts, viewing organization details, enabling/configuring/disabling SSO, verifying SSO email domains, enabling/disabling directory sync, changing billing email/spend alerts/IdP-managed roles, listing members, showing a member by email or user ID, updating member roles, removing members, creating/updating/deleting teams, adding/removing team members, or troubleshooting organization access. Triggers on org, organization, switch org, list orgs, org update, organization SSO, SSO domain, domain verify, directory sync, spend alert, billing email, IdP roles, idp-sso-managed-roles, org member, organization member, member role, remove member, org team, team member.
-
bigpapicb Skill DebuggingSystematic diagnostic strategy with decision tree for reproducing, isolating, and tracing bugs. Use when investigating bugs, crashes, or unexpected behavior. Complements systematic-debugging workflow with concrete diagnostic patterns.
-
varie-ai Skill Work StartInitialize a new task with proper context loading and archive setup. Use when starting fresh work on a feature, bug fix, or project.
-
bam-bam-2 Skill Meeting Minutes회의 전사록을 받아 회의록으로 정리하고 노션 DB에 등록한 뒤 디스코드에 공지까지 한 번에 처리한다.
-
varie-ai Skill Work ResumeResume a task using fuzzy matching across all repos. Use when user wants to continue previous work, says "resume", "continue", or references a past task.
-
profsynapse Skill Pact TeachbackCommand-style teachback protocol for PACT teammates. Invoking this skill directly instructs you to store your teachback in task metadata and idle on awaiting_lead_completion before any implementation work.
-
profsynapse Skill Worktree SetupCreate an isolated git worktree with a feature branch for PACT workflows. Use when: starting a new feature, beginning orchestrate or comPACT, creating sub-scope isolation for ATOMIZE, or manually isolating work. Triggers on: worktree setup, feature isolation, parallel workflow, new worktree.
-
profsynapse Skill Worktree CleanupRemove a git worktree and its branch after PACT workflow completes. Use when: PR is merged, sub-scope work is consolidated, or manual cleanup is needed. Triggers on: worktree cleanup, remove worktree, delete worktree, branch cleanup.
-
twentyhq Skill Twenty Partner IntroSend the partner introductions for a lead - record them in the CRM and open the ready-to-send emails in Chrome. Use once the user has reviewed a shortlist and named the partners they want to introduce, or whenever they say to make the intro, send the intros, connect the client with a partner, or generate the intro emails. Writes Application records in INVITED state, stamps introSentAt on the Opportunity, and opens each partner email as a prefilled Gmail draft. Chains after twenty-partner-shortlist.
-
potpie-ai Skill Potpie GraphUse when the task can read or write the project-memory graph through the potpie CLI: discover the contract with `graph catalog`, read named views with `graph read`, resolve entity identity with `graph search-entities`, create validated plans with `graph propose`, commit plans with `graph commit --verify`, inspect quality with `graph quality`, or capture uncertain work with `graph inbox`. Also covers writing retrieval-grade descriptions and responding to nudges.
-
potpie-ai Bundle Potpie CLIUse when the task is centered on running, explaining, configuring, or troubleshooting the `potpie` command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
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 fireflies, drive-to-done, github-cli. 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.