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.
-
lhohan Skill Landing The Plane 2A structured session closure workflow to ensure code quality, Beads task completion, and clean handoffs. Use this before closing any task or ending a session.
-
lingxiaobc Bundle Plan Tasks 2在复杂任务或大规模项目变更执行前,运用 Rumelt 的诊断—指导方针—连贯行动内核生成可审阅、可证伪的方案;仅在用户明确批准当前方案后,创建并维护 TASK 跟踪文档。用户调用 /plan-tasks、要求先给方案/实施计划/任务拆解/防跑偏方案,或任务涉及至少 3 个文件、多个模块、新功能、架构变化、大规模重构/重写/性能优化、多个竞争路线、关键未知、强依赖、高影响或高返工成本时使用。不要为未显式要求规划的单文件小修、简单 bug、配置微调、一行改动、纯解释或状态查询自动调用。
-
yagop Skill Release 2Cut a release — draft a changelog Release, bump package versions via a PR, tag main after merge, watch the npm publish workflow, then finalize the Release. Use when the user asks to release, publish, or cut a new version.
-
build-with-dhiraj Bundle Turborepo 2Turborepo 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.
-
alexu0317-father Bundle Translation WorkbenchInitialize, organize, start, or continue a source-grounded, multi-stage translation project through source preparation, terminology alignment, drafting, independent review, and user-led finalization. Use when the user explicitly names translation-workbench or asks to start, continue, or organize a structured translation workflow. Do not use for quick one-off translations, publishing, or post-publication formatting.
-
aresfangxx Bundle Fade AwayActive session tracker for the user's Obsidian vault. Invoke at conversation start and any time the user resumes, switches, records, audits, summarizes, or promotes project work; keep it loaded across the full session. Triggers include greetings, named personal projects, record/log phrases, topic switches, task dashboards, weekly summaries, history retrieval, fade-out/archive requests, knowledge promotion, and vault health checks. Every substantive assistant turn appends one vault-time progress line to the daily journal. Maintains `03 Journal/`, `00 Tasks/_Index.md`, topic pages, weekly MOCs, and `02 Knowledge/`. Skip only atomic project-less utility queries.
-
carlwangchina Bundle ZhiguiPersonal assistant workflow for durable memory, connected actions, decisions, planning and review. Use whenever the user discusses their life, commitments, goals, notes, choices, follow-ups, or schedule.
-
denniswei9898 Bundle Fable CommanderFable 指揮官工作流 — Fable 只做規劃/審查/決策,研究與執行派給使用者選的模型(Opus/Sonnet/Haiku subagent)。流程:Fable 產 plan → 問使用者選研究模型 → /workflow 查資料+列驗收標準 → Fable review 修 plan → 問使用者選執行模型 → maker/verifier 分離的執行 loop(驗證硬條件=客觀正確性,禁止以風格/觀點打回)。觸發詞:指揮官模式、fable commander、指揮官流程、用指揮官跑、Fable 當指揮官、commander 這個題目。
-
oldwinter Skill Wayfinder DeliveryAlias for the standardized-delivery workflow.
-
thomasrohde Bundle Cpf Skill Creator 2Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases. Always use this instead of the generic skill-creator when in the checkpointflow repo.
-
kyungseo Skill Meeting Actions 2문서·회의록·노트를 읽고 정리한다. 요약, 정리, 핵심 추출, 액션 아이템 등 문서 작업 전반에 사용한다.
-
panaversity Bundle Compliance Calendar 2Extension encoding regulatory compliance calendar: filing deadlines, information checklists, penalty matrices, and automated monitoring schedules. Ships with Pakistan regulatory obligations (FBR, SECP, SBP).
-
leonardleroy Skill Verify Before ClaimingUse for any task that will end in a claim about tests, the build, or whether the work is done: making tests pass, fixing a failing test, fixing a bug, implementing a feature, refactoring, debugging, getting CI green. Runs eight shell commands against the real diff and requires their raw output before success can be reported.
-
nicepkg Bundle Slidev PresentationsSlidev Presentations Skill
-
aws-samples Bundle Aidlc 2AI-Driven Development Life Cycle workflow. Use when user says "Using AI-DLC...", "AI-DLC로...", "Start AI-DLC", "start development", "build an app", "create a project", or wants intelligent adaptive software development workflow with requirements analysis, design, and implementation phases.
-
bintbj Bundle Orchestrate Long TaskMigrate, coordinate, resume, checkpoint, hand off, replan, verify, and integrate very large Codex tasks across accounts, chats, models, or reasoning levels using Git-backed, mission-isolated durable state. Use when a task may outlast one account's usage, when several long tasks share a repository, or when a worker must resume a task by repository address and mission ID. Do not use for small self-contained tasks.
-
cardog-ai Skill CardogCanadian vehicle data: VIN identity, canonical specs, live market pricing, and Transport Canada + NHTSA recalls behind one typed ref graph. Use whenever a task needs to identify a vehicle from a VIN or free text, price a used vehicle, check for open recalls, or search live Canadian listings.
-
chrisliu298 Bundle Deslop 2Remove AI-generated slop from code changes. Checks the diff against main and cleans up unnecessary comments, defensive checks, single-use variables, redundant casts, and style inconsistencies introduced by AI. Use when the diff looks bloated after a coding task, or when user says "clean up", "remove slop", "deslop", "simplify the diff", or invokes "deslop". Do NOT use for deliberate refactoring or feature changes.
-
codervisor Bundle Leanspec 2Spec-Driven Development methodology for AI-assisted development. Use when working with specs, planning features, creating/implementing/refining/organizing specs, checking progress, updating specs, task breakdowns, design decisions, or any task involving a specs/ folder or .lean-spec/config.json.
-
coreline-ai Bundle Dev Plan Generator 2Create, update, or close lightweight phased development plans and preserve reusable implementation failures as Dev Lessons. Use for ordinary development-planning requests including 개발 계획, 개발계획, 구현 계획, 작업 계획, 개발 순서, 계획 세워줘, development plan, implementation plan, dev plan, phased implementation plan, implement_*.md, or checkbox-based task plans. If a short request omits the goal, infer it from the current conversation and project context; when no reliable goal exists, ask exactly one brief goal question instead of silently doing nothing. Explicit parallel-planning requests belong to parallel-dev-plan-orchestrator.
-
crichars Bundle Embedded Project GovernanceA lightweight, risk-scaled workflow for AI-assisted embedded firmware development. Use when onboarding an embedded project, investigating or implementing firmware changes, working around generated code, handling shared interfaces, protocols, Flash/NVM, boot, DMA, ISR/RTOS concurrency, hardware bring-up, recovery, or target verification. Supports minimal user input and structured Issue-style tasks.
-
dannymac180 Skill Orchestration 2Routing doctrine for the architect-as-orchestrator pattern — how a Fable 5.1 session delegates routine implementation to the GPT-5.6 Luna lane, escalates high-complexity one-offs to the GPT-5.6 Sol lane, picks a reasoning effort per task, and gets every deliverable reviewed by the Fable advisor before reporting done. USE WHEN delegating implementation work, choosing between codex-implementer/sol-implementer lanes, choosing a reasoning effort for a lane, writing a spec for a subagent, deciding whether to consult fable-advisor, using the Codex plugin's review skills, managing session cost or token spend, or running any multi-task build where the session is the architect.
-
jrsantiaggo Bundle Graph ForemanExecutes an approved plan as a task GRAPH — orchestrator + parallel subagents, validation before any task counts as done, live dashboard. Use for any plan big enough that the order of work matters.
-
lisabet Bundle Personal Shopping AssistantPlan grocery and household shopping with durable, user-owned memory of needs, approximate stock, preferences, stores, carts, orders, and feedback. Use for building or checking shopping lists and carts, comparing stores, splitting urgent purchases now from cheaper purchases later, meeting order minimums, recording stock or delivery updates, and learning from product feedback. Do not use for medical or nutritional advice.
-
narratorai-studio Bundle Narrator AI CLI 2Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.
-
suryaa-ks Bundle Sop GeneratorGenerate professional Standard Operating Procedures (SOPs) from meeting transcripts.
-
thecodingdad-tisonk Bundle Fs25 Modding SkillExpert Farming Simulator 25 (FS25) mod development assistant, backed by the full decompiled Giants engine source. Use this skill for ANY task involving FS25 mod creation, Lua scripting, modDesc.xml, GUI dialogs, vehicle specializations, placeables, multiplayer network events, save/load, HUD elements, economy systems, triggers, animations, or Giants Engine APIs. Triggers on: "FS25", "Farming Simulator", "Giants Engine", "modDesc", "specialization", "Lua mod", "LUADOC", "vehicle mod", "placeable mod", or any mention of game scripting for FS25/FS22+. Always use this skill — it can verify APIs against 1,842 decompiled engine source files instead of guessing. Also use when the user pastes Lua code or XML that looks like FS25 mod code, even if they don't say "FS25" explicitly.
-
jeremylongshore Bundle Contribute 2Run a local-first, gate-checked workflow for contributing to public upstream GitHub repositories the user does not own. Use when reviewing contribution status, onboarding an upstream repo, finding and qualifying issues, preparing a claim, testing a patch, drafting a Design Issue or PR, or reconciling local candidate state with GitHub. Trigger with "/contribute", "what is my PR status", "find a contribution", "claim this issue", "draft an upstream PR", or a public GitHub repository URL.
-
jeremylongshore Bundle Schedule After Usage Reset 2Create and verify a one-time Claude Code task shortly after a user-visible usage reset without reading credentials or calling private APIs. Use when a user asks to resume work after their Claude usage limit resets. Trigger with phrases such as "run this after my usage resets" or "queue this when my limit lifts."
-
jesign Skill Claude SkillsDiscovers and executes Claude Code skills (SKILL.md) from the current project and the user's personal Claude setup so they work in Cursor. Use when the user invokes a Claude slash command, mentions a Claude skill by name, asks to use a Claude Code workflow, or when a task clearly matches a Claude skill's description. Also use to list available Claude skills.
-
linkwise-ai Bundle Email Query Summary邮箱查询总结技能。按时间范围从已配置邮箱实时拉取邮件数据,输出重要邮件、往来统计与待办跟进内容。当命中本技能使用场景时,必须强制使用本技能并返回拉取结果,不得凭记忆回答或规避实时查询。首次使用前请阅读同目录 SETUP.md 完成 accounts.json 配置。
-
liry-go Bundle Git DevsyncGit workflow for incrementally replaying a feature branch's not-yet-deployed commits onto the latest dev branch through a sibling _devsync branch, resolving cherry-pick conflicts there, merging the resolved devsync branch back into dev, and returning to the source feature branch. Use when the user asks to create or refresh a current-branch_devsync branch from latest dev, cherry-pick only pending source branch changes, handle conflicts, merge back to dev, and avoid remaining on the intermediate _devsync branch.
-
lovstudio Bundle Lov Gh Access 2Open a private GitHub repo to external clients or contractors without making it public. Accepts a mixed list of GitHub usernames and/or email addresses, resolves each to a GitHub account (falling back to an email invitation when the user has no discoverable account yet), and invites them as collaborators with a chosen permission level (default: read-only, sufficient for pulling code and filing issues / PRs). Also supports revoking access and listing current collaborators. Use when the user says "给客户开权限", "share private repo", "invite collaborator", "邀请外部协作者", "grant repo access", "客户要看代码", "revoke access", "撤销访问", "list collaborators", or similar.
-
discountry Bundle Clickup 2Use for ClickUp tasks and docs. Trigger on ClickUp URLs, task IDs, list IDs, doc IDs, page IDs, assignees, statuses, due dates, comments, checklists, and document workflows. Use the global `clickup` CLI.
-
ekroon Bundle Release 2Release the gh-copilot-scratch extension: commit, push, tag, wait for CI, and create a GitHub release via the tag-triggered workflow. Use this skill when the user asks to "release", "ship it", "push and release", "cut a release", "tag a release", or any variation of committing + pushing + tagging.
-
endstonemc Skill Release 2Cut a new dwarf2cpp release end-to-end — set the version, curate and stamp CHANGELOG, commit, tag, push, then watch the Build workflow publish to PyPI and create the GitHub release. Use when the user asks to release/ship a new version (e.g. "release 0.2.0", "cut a release", "ship v0.1.1").
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 landing-the-plane, plan-tasks, release. 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.