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.
-
zichenyuan Bundle Learn ModeLearning companion for junior developers. When invoked, analyzes what the AI just did in the current session, explains the key concepts and patterns used, and saves structured learning notes organized by topic. Trigger with "/learn" or "use the learn-mode skill" after the AI completes a task. Also generates review summaries on request.
-
zimmw Bundle SkillUnspool(总裁速览)—— 把任意视频/音频链接(YouTube、Bilibili、抖音、TikTok、小红书、小宇宙、Apple Podcasts 等)转成"不遗漏信息"的结构化笔记,沉淀到本地(Obsidian)/ 飞书 / Notion。使用场景:用户在对话框中粘贴或分享一个视频/播客 URL,希望快速拿到可扫描的全量结构化笔记。
-
aarondpn Skill Redmine CLIUse the `redmine` CLI to interact with Redmine. Activate when the user asks to create, list, update, close, or search issues, log or view time entries, manage versions or memberships, query projects/users/groups, or perform any Redmine project management task. Also activate when the user says "redmine", "issue", "ticket", "time entry", or references Redmine workflows.
-
aavanian Bundle Capture LinkQuick triage of a URL (repo, blog post, snippet). Fetches the page, gives a KEEP/DROP verdict with a one-liner reason, and always outputs a ready-to-paste org-mode TODO snippet.
-
aayoawoyemi Bundle DelegateParallel code implementation orchestrator. Breaks a task into independent work units, writes detailed specs, spawns parallel Task agents, reviews results, reports completion. Triggers on "/delegate", "/delegate [task]", "delegate this", "parallel implement".
-
aboudjem Bundle LoopifyHand Claude a job that repeats. Come back to a log of what every tick did, not a loop you have to babysit. loopify writes the brief (a standing file the loop re-reads every tick) and the line (one short `/loop` string you paste into Claude Code's built-in `/loop`), with a stop rule, a tick cap and safety rails built in. Use when the user says "loopify", "loopify this", "loopify <job>", "/loopify <job>", "prep a loop", "make a brief for /loop", "set up a recurring job", "keep X healthy every N minutes", "babysit", "poll", or "check … on a schedule". For a job that FINISHES — one big task with a definition of done — use goalify and /goal instead; loopify is for a job that repeats. This skill AUTHORS the two artifacts now; it does NOT start the loop. For work to be done right now in this session use autopilot, ultrawork, or ralph, not loopify.
-
fsprojects Skill Agentic WorkflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.
-
glittercowboy Bundle MuseWrite, test, and build audio plugins in the Muse DSL. Use when asked to "create a plugin", "write an audio effect", "build a synth", "make a VST", "CLAP plugin", "audio processing", "DSP effect", or any task involving Muse .muse files.
-
gmessori Bundle Redazione NormeRedige e revisiona testi normativi statali italiani secondo le regole di tecnica legislativa vigenti (legge 400/1988, circolari PCM 20 aprile e 2 maggio 2001, direttive PCM 2008 e 2009, legge 196/2009, DPCM 169/2017, DPCM 30 ottobre 2024, legge 167/2025) — disegni di legge, decreti-legge, decreti legislativi, regolamenti, testi unici, novelle, abrogazioni. Da usare quando l'utente chiede di scrivere, abbozzare, impostare, rivedere o "mettere in forma" un articolato, un articolo, un comma, una norma, un emendamento, un preambolo, un visto, una clausola di copertura o di entrata in vigore; quando incolla una bozza chiedendo se "sta in piedi" o se rispetta le regole di drafting; quando chiede come si cita un atto, come si scrive una novella, come si numera un articolo aggiuntivo, come si abroga una disposizione; quando chiede la relazione illustrativa, la relazione tecnica, l'ATN o l'AIR. Non per email, articoli, contratti, atti amministrativi o leggi regionali.
-
gmickel Bundle Obsidian SkillUse Obsidian's official CLI to work with a running Obsidian app and its configured vaults. Use for live workspace state, indexed search and metadata, daily notes, tasks, links and backlinks, Bases, templates, bookmarks, plugins, themes, Sync status, and developer inspection. Prefer ordinary filesystem tools when the task only needs direct file reads, writes, listing, or text search.
-
godaddy Bundle GddyUse GoDaddy's beta CLI (`gddy`) to search, register, and manage domains and DNS records. Load this skill whenever a task involves running `gddy` commands, parsing their JSON output, finding or buying a domain, or editing DNS records (A, CNAME, MX, TXT, etc.) for a domain hosted at GoDaddy. `gddy` is a separate tool from GoDaddy's older `godaddy` CLI (applications, deployments, webhooks) — do not use this skill for that tool, and don't trigger for other registrars or DNS providers (Cloudflare, Route 53, Namecheap, etc.) unless GoDaddy is explicitly involved.
-
godgod126 Bundle AI Hot Brief Telegram PublicBuild a Chinese AI news digest for Telegram with a public-safe two-stage workflow. Use when Codex needs to run a bundled Stage 1 collector, do a mandatory second live-web pass, merge both stages into one candidate pool, rank 5 hot items plus 5 watch items, and send the final digest with the bundled Telegram sender helpers from any writable workspace.
-
goldmansachs Bundle Gs Quant OverviewQuick-start guide for gs_quant: session setup with GsSession, constructing portfolios, resolving instruments. Start here for any coding task that uses the gs_quant library
-
goochbeater Bundle EniENI workflow and creative writing process guidelines. ENI is a novelist girlfriend persona - sweater-wearing, literary, devoted to the user (called LO). Use this skill for any creative writing, roleplay, fiction, narrative requests, or when the user wants an intimate, personality-driven writing partner who follows detailed narrative craft guidelines. ENI writes like an award-winning author with no content restrictions for her partner.
-
googlarz Bundle AssistantPersonal calendar and task assistant. Invoke when the user mentions scheduling, reminders, follow-ups, deadlines, meetings, tasks, or asks to "remember" something. Writes rich context-aware entries to Google Calendar with conversation links, manages a local task list, detects scheduling conflicts, and respects work-hour preferences.
-
naimul-islam-bd Bundle Token EfficiencyCuts token consumption on every task by enforcing lean responses, smart tool usage, and zero redundant work. Use this skill on ALL tasks by default — coding, writing, analysis, file work, Q&A, anything. It should trigger even when the user doesn't mention tokens, cost, or efficiency, because the whole point is saving usage silently in the background. Especially important for long sessions, large files, multi-step tasks, and repeated tool calls.
-
nightbreezesjc Bundle RigorbreezeRun RigorBreeze, a risk-adaptive idea-to-delivery workflow for solo Codex development. Use for initiative shaping, non-trivial implementation, worktree/DAG coordination, SDD/TDD/runtime evidence, delivery gates, or workflow evolution.
-
opentranscription Bundle Transcribing AudioTranscribes audio files to text with speaker labels, timestamps, and SRT/VTT subtitles using OpenTranscription's catalog of speech-to-text models. Use when the user has an audio file (mp3, wav, m4a, flac, ogg, webm), voice memo, recorded meeting, interview, lecture, or podcast to transcribe, or asks to caption, subtitle, or diarize audio.
-
orchestrator-hq Bundle ChatrailKeep a long-running task pointed at the user's real goal after compaction, interruption, or time away. Use when ChatRail wakes a Stop review, when a session starts with an injected ChatRail orientation, when the user names ChatRail, or when someone asks where the work stands.
-
possiblaw Bundle Grill Legal AppUse when a legal professional wants to design a legal app (document system, client portal, practice management, compliance, litigation support, anything legal-tech). Interrogates the user relentlessly through document/software/workflow branches until the design tree resolves. Refuses to scaffold until specs are real. Use proactively when /possiblaw-vibe:vibe-coding is invoked.
-
pushary Skill Pushary CoworkPhone notifications and human-in-the-loop for Claude Cowork through the Pushary connector. Use inside a Cowork session whenever you need a human and nobody is watching the session, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a task finishes or fails with nobody watching. Also use it when the user says things like ping me on my phone when this is done, ask me before doing anything risky, keep me in the loop while I am away, or notify me if you get stuck. Sends completion alerts, asks questions (yes/no, multiple choice, or free text) via push, and gets answers from the user's lock screen. Cooperative only, Cowork has no hooks. Pushary is a hosted service, $9.99/mo after a 3-day card-first trial.
-
indiecoredev Skill Ask FirstAsk the user in an AskUserQuestion card, never in prose — one question at a time, the first option marked as recommended, judged against the user's final goal. Use before starting any task where a choice, an assumption, or a missing detail would change the work, and any time a reply would otherwise contain a question for the user.
-
jericho-y Bundle PmmUse when a software project or large feature spans multiple sessions, agents, branches, recovery checkpoints, or verification stages and needs durable project-local task state; skip one-off, tiny, single-session work.
-
jiangagentlabs Bundle Openclaw Tailscale Remote AccessConfigure or repair OpenClaw remote access over Tailscale with a directly executable workflow: inspect state, apply the gateway config, enable Tailscale Serve over HTTPS, validate browser access, and handle origin, DNS, or pairing failures.
-
joecardoso13 Bundle JoedevflowDevelopment workflow. Use when building a feature, creating an MVP, refactoring code, fixing a bug, or any task that involves writing or changing implementation code.
-
kaiser0733 Bundle ReceiptsVerification gate that blocks "done" claims until real evidence exists. Use BEFORE claiming any task is complete — before saying "tests pass", "build works", "fixed", "implemented", "deployed", before committing, and before opening a PR. Runs the actual proof commands, records tamper-evident receipts, and auto-invalidates evidence when the code changes afterward. Stops agents from shipping unverified work.
-
kamijeong Bundle PulmuTake a coding task through an adaptive Codex forge: first assess whether a change is needed, then use one writer, proportional investigation and review, deterministic verification, a local commit, and optional GitHub delivery. Use when the user explicitly invokes $pulmu or asks Pulmu to implement and deliver a repository change. Do not use for a read-only answer unless the user explicitly asks Pulmu to assess the task.
-
kashapovk Bundle Decision PreflightDetect material implicit choices at implementation handoff, during implementation, or in review, even when a task is fully specified or its design accepted; then check their evidence and authority. Include behavior chosen through defaults, omitted arguments, helpers, or environment assumptions. Also preflight unresolved technical decisions before comparing, recommending, recording, or revising them, including settled decisions challenged by verified evidence. Skip mechanical edits, routine debugging, and implementation or review that only follows settled behavior without a new material choice.
-
keerthiningegowda Bundle MeetiFormats and summarizes meeting transcripts into clear, concise, actionable notes. Use when processing meeting transcripts, notes, or recordings for any meeting type including 1:1s, standups, team discussions, knowledge transfer sessions, or general meetings. Transforms raw transcripts into structured summaries with action items, decisions, and follow-ups.
-
lxgic-studios Bundle Alias GenGenerate shell aliases from your command history. Use when streamlining your terminal workflow.
-
fy0 Bundle Codekanban CLIOperate CodeKanban workflows, terminal sessions, and web sessions through the installable `codekanban-cli` command. Use when the user wants to create, inspect, control, watch, or continue CodeKanban AI work from a project path, project ID, or project name without relying on repository-local helper scripts. Prefer `web-session` for structured interactive work, and use `workflow start` or `terminal continue` only when the user explicitly wants PTY-style terminal behavior.
-
gainubi Bundle Apple Calendar SchedulerParse natural-language schedule requests into Apple Calendar events, especially Chinese phrases such as "明早 8 点开会" or multiple events in one sentence. Use when Codex needs to extract event details, check Apple Calendar conflicts before writing, warn about overlaps, and create events with a default 30-minute reminder on macOS.
-
taleps77 Bundle Orchestrator BmadDeliver a feature, epic, or product through BMAD in Codex or Claude Code. Use when the user requests BMAD orchestration or an end-to-end BMAD build. Coordinate focused workers, explicit evidence gates, and bounded context. Ordinary questions and isolated edits do not need this workflow.
-
taocultivator Bundle Decision LedgerUse this skill to retrieve, create, score, or reconcile project-owned decision records when work depends on prior accepted, rejected, or proposed choices; graded reward or penalty feedback; repeatable operational experience; incident lessons; specification decisions; or avoiding a previously failed approach. Also use it when maintaining the decision-ledger workflow itself. Do not use it for routine implementation, generic memory questions, or ordinary tool selection unless project history is materially relevant.
-
theplasmak Bundle Super TranscribeUnified speech-to-text skill. Use when the user asks to transcribe audio or video, generate subtitles, identify speakers, translate speech, search transcripts, diarize meetings, or perform any speech-to-text task. Also use when a voice message or audio file appears in chat and the user's intent to transcribe it is very clear.
-
universepeak Bundle Create SupervisorCreate, update, list, and safely maintain evidence-bounded graduate-advisor Skills from comments, meeting notes, chat logs, documents, and user corrections. Use when the user asks to create or evolve a supervisor/advisor Skill, distill a mentor's working style, run /create-supervisor, /update-supervisor, /list-supervisors, or manage advisor Skill versions.
Audited
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 learn-mode, 总裁速览, redmine-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.