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.
-
gaelic-ghost Bundle Coreaudio Modernization Repair WorkflowGuide legacy Core Audio and Audio Toolbox modernization and repair, including AudioUnit, AudioQueue, AudioConverter, AudioStreamBasicDescription, AudioComponentDescription, OSStatus diagnostics, callback lifetime, pointer ownership, Swift bridging, and migration decisions toward AVFAudio when appropriate. Use when fixing low-level Apple audio implementations or deciding whether to keep or replace legacy Core Audio code.
-
gaelic-ghost Bundle Realtime Media Over Quic WorkflowPlan, evaluate, and diagnose Media over QUIC or MoQ work, including draft-state checks, relay/client/server topology, publish/subscribe object flow, media packaging, live latency, reliability tradeoffs, authorization/privacy drafts, qlog or protocol evidence, and fallback routing to WebRTC, HLS/DASH, HTTP streaming, or stack-specific implementation plugins.
-
clowlove Bundle Testing Workflow Optimizer专注流程分析和优化的效率专家,通过消除瓶颈、精简流程和引入自动化,让团队干活更快、出错更少、人也更舒服。
-
clowlove Bundle Specialized Workflow Architect工作流设计专家,为每个系统、用户旅程和智能体交互绘制完整的工作流树——涵盖正常路径、所有分支条件、故障模式、恢复路径、交接契约和可观测状态,产出可直接用于构建的规格说明,让开发人员据此实现、QA 据此测试。
-
clowlove Bundle Engineering Git Workflow MasterGit 工作流专家,精通分支策略、版本控制最佳实践,包括约定式提交、变基、工作树和 CI 友好的分支管理。
-
clowlove Bundle Engineering Email Intelligence Engineer专精从原始邮件线程中提取结构化、可供 AI 推理的数据,服务于智能体和自动化系统。
-
clowlove Bundle Project Management Jira Workflow Steward交付运营专家,执行Jira关联的Git工作流,确保提交可追溯、PR结构规范、分支策略安全可控。
-
melodic-software Bundle ManageManage the Kindle for PC 2.8.0 + Calibre DeDRM workflow for personal-use ebook DRM removal on books you own (Windows only). Action router: setup (first-time provisioning — download, firewall block, ICACLS lock, Calibre plugins, keyfinder; delegated to the dedicated /kindle-dedrm:setup check/apply skill), sync (new purchases — disable firewall, sync Kindle, re-enable, re-run keyfinder), update (drift check — upstream version pins and tutorial URLs, no mutations), cleanup (reversible decommission — per-item confirmation, --soft or --full), status (diagnostic). Every state mutation has a documented compensating reversal. Use when: 'set up Kindle DRM removal', 'convert Kindle books to EPUB', or syncing, drift-checking, or decommissioning personal-use Kindle DRM removal; making an owned Kindle library readable on a non-Kindle device; or Calibre and Kindle are mentioned together.
-
melodic-software Bundle Co WriteRun a co-writing session and generate titles and high-volume options with Pat Pattison's methods, the No-Free-Zone co-write protocol and feedback discipline, the Title Game (chained vowel-cascade title generation), title generation from an idea, and high-volume brainstorm dumps for ONE line or ONE section. Use when: 'co-write tonight', 'co-write rules', 'no-free-zone', 'Title Game', '10 titles fast', 'title candidates for X', 'give me 30 options for this line', 'brainstorm the whole chorus'. For blank-page/idea/fragment starts use /songwriting:workflow; for rhyme dumps use /songwriting:rhyme.
-
melodic-software Bundle WorkflowStart-here situation router for songwriting with Pat Pattison's methods. Picks the scenario for a blank page, an idea/seed, a stuck fragment, a co-write, a diagnose-only pass, or a daily habit, and runs step-by-step coaching dialog. Also applies Pat's response filter to AI-generated material and points to going-deeper resources (Coursera / Berklee / columns / podcasts). Use when: 'I want to write a new song', 'I have nothing — just want to write', 'I have an image but no title', 'this fragment is stuck', 'walk me through writing this', 'guide me', 'where do I start', 'review the rhyme list this AI gave me', 'how do I go deeper'. Craft-specific requests route to the concern skills below.
-
melodic-software Bundle Keep GoingRecover and continue after an interruption, rate limit, crash, disconnect, or gap, or when live off-thread work looks stalled and you are asked to check on it. Inventory off-thread work, inspect its REAL output, act only on evidence (resume / rerun / kill-and-restart), then continue the main task where it stood. Use when: asked to keep going, continue, resume, or pick up where you left off; after being cut off or interrupted ('what were you doing'); or asked to check on, poke, or judge whether off-thread work is stuck ('check the monitor', 'is it stuck', 'stop staring at it'). Infers intent from the conversation; arguments optional. After a usage limit lifts it continues rather than summarizing-and-stalling; it gates killing or re-firing side-effectful work. To retire finished off-thread work and reconcile the task ledger rather than resume, use /session-flow:reconcile.
-
robsonkades Bundle Gof StateState in modern Java: making an object's behaviour depend on an explicit state, with the transitions themselves modelled rather than implied by scattered flags. Covers the intent difference from Strategy, where transitions should live — in the state classes, in a table, or in one exhaustive switch — sealed records against enums, rejecting illegal transitions by default, persisting a state through stable codes rather than ordinals, atomic transitions under concurrency, and timeouts as transitions in a durable workflow. Use when boolean flags multiply on an entity, when a status field is checked in scattered ifs, when an illegal transition reaches production, when a workflow must survive a restart, or when two requests transition the same entity concurrently. Does not cover interchangeable algorithms chosen by a caller (gof-strategy), saga orchestration across services (distributed-transactions-and-sagas, gof-mediator), or optimistic locking mechanics (offline-concurrency-control).
-
robsonkades Bundle IdempotencyMaking an operation safe to apply more than once: natural idempotency versus an idempotency key plus durable operation state; choosing and scoping the key, and why a broker message id covers only one redelivery scope; handling concurrent in-flight duplicates; replaying the stored response instead of returning a conflict; and why idempotent is not commutative. Use when a retry produces a second row, charge or email, when a handler starts with an exists() check before a write, when an Idempotency-Key header is being added or ignored, when two identical requests arrive concurrently, or when a dedup table has no TTL. Does not cover why duplicates arrive (delivery-semantics), compensating actions (distributed-transactions-and-sagas), what the dedup store's own consistency must be (consistency-models), or caching (caching-strategies).
-
robsonkades Bundle Feature EngineeringOwning a Product Feature or Tech Feature from definition intake to completion review: selecting proportionate depth, routing iterative analysis and explicit returns, holding readiness gates, and keeping versioned evidence another engineer can resume. Use when feature implementation is being prepared, resumed, or validated and its scope, contracts, decisions, or completion need a trustworthy lifecycle. Does not co-author the initial feature brief (collaborative-feature-definition), own any specialist phase in depth, orchestrate an arbitrary change (clean-delivery-workflow), or define the ADR record format (architecture-decision-making).
-
knuckles-team Bundle Ebook CompilerOutline, draft, and edit a multi-chapter manuscript, then merge the chapters into one compiled document and run a final readiness check. Use when a user has an approved chapter list, audience, and voice constraints and wants a review-ready compiled ebook; this workflow never publishes or uploads it.
-
knuckles-team Bundle Strategy ExportParallel execution workflow for strategy export using the Unified Parallel Engine
-
knuckles-team Bundle Crypto ArbitrageParallel execution workflow for crypto arbitrage using the Unified Parallel Engine
-
knuckles-team Bundle Full Ecosystem HealthEnd-to-end ecosystem health check across containers, system resources, workspace, and observability stack. This is the "canary" workflow that validates all infrastructure layers are operational.
-
knuckles-team Bundle Podcast Show NotesOutline, draft, and edit show notes from a supplied episode transcript, then run a final readiness check. Use when a user has an approved transcript, audience, and voice constraints and wants review-ready show notes; this workflow never publishes or uploads them.
-
knuckles-team Bundle Portfolio AnalysisParallel execution workflow for portfolio analysis using the Unified Parallel Engine
-
knuckles-team Bundle Host DoctorOnboard-diagnose a host (or a whole fleet) and remediate under gate. Validates the OS/kernel/arch, samples CPU/mem/disk/load utilization, inspects processes for zombies, runaway/orphaned hogs, and swap exhaustion, and checks PHYSICAL storage + BMC health (SMART incl. RAID megaraid passthrough, drive-slot/IPMI faults, predicted failures) that the filesystem checks miss — then, only after presenting the findings and getting explicit per-host confirmation, remediates by delegating to the systems-issue-troubleshooter workflow (kill rogue PIDs, reclaim swap/temp), and re-verifies. Use when a machine is hot, sluggish, throwing a drive fault, or newly onboarded and you want a single "how is this host doing, and make it run cool" pass. Composes hardware-profile-sweep, host-resource-sampler, and host-process-inspector over tunnel-manager SSH, plus sm_storage_health (systems-manager) and the fan-manager IPMI/BMC tools. Diagnosis is read-only; every change is gated on user approval.
-
knuckles-team Bundle Qlib Factor BacktestIngest market data for a supplied universe and backtest a supplied alpha-factor definition with Qlib. Use when a researcher wants a direct, evidence-linked backtest of one or more already-defined factors; this workflow does not discover new factors or place trades.
-
knuckles-team Bundle Max Drawdown RecoveryIngest market data, backtest a supplied strategy to surface its maximum-drawdown episodes, and run the TradingAgents swarm debate to vet a candidate recovery hypothesis for the observed drawdown. Use when a researcher wants evidence-linked drawdown analysis and a vetted recovery hypothesis; this workflow does not place trades or guarantee recovery.
-
knuckles-team Bundle Trading Signal FusionIngest market data and run the TradingAgents swarm debate to vet and fuse a supplied set of candidate trading signals, then backtest the fused signal with Qlib. Use when a researcher wants evidence-linked fusion of multiple candidate signals into one backtested view; this workflow does not place trades.
-
knuckles-team Bundle Disk Space RemediationSample a host's current resource utilization and then discover and safely reclaim disk space where it is under pressure. Use when a filesystem is full or nearly full and a host needs a governed reclamation pass; this workflow never deletes anything outside the reclaimer's own safety checks.
-
knuckles-team Bundle Trade Journal AnalysisExecute a supplied strategy via paper trading with freqtrade to produce a trade execution log, then profile that log's structure and statistics. Use when a researcher wants a structured trade journal ready for review; this workflow only paper-trades and never places live orders.
-
knuckles-team Bundle Host Hardware InventoryCollect hardware profile details (CPU, memory, disk, OS, GPU/accelerator) and current resource utilization across reachable hardware nodes. Use when a fleet operator needs a consolidated hardware and current-utilization inventory; this workflow is read-only.
-
knuckles-team Bundle Factor Exposure MonitorIngest current market data and backtest a supplied, already-defined factor set with Qlib to surface the portfolio's present exposure to those factors. Use when a researcher wants an evidence-linked factor-exposure snapshot; this workflow does not discover new factors or place trades.
-
knuckles-team Bundle Multi Strategy AllocationIngest market data, backtest a supplied set of candidate strategies with Qlib, and run the TradingAgents swarm debate to vet the backtested evidence as input to an allocation decision. Use when a researcher wants evidence-linked support for weighting multiple strategies; this workflow does not execute the allocation or place trades.
-
knuckles-team Bundle Code Enhancer WorkflowParallel execution workflow for code enhancement and multi-domain deep-dive auditing using the Unified Parallel Engine
-
legendtkl Skill Syn Image CompressSkill for compressing and optimizing file size in the context of image files. Use when the user's task is specifically about compressing and optimizing file size.
-
legendtkl Skill Syn JSON TransformSkill for reshaping and transforming structure in the context of JSON data. Use when the user's task is specifically about reshaping and transforming structure.
-
legendtkl Skill Syn Regex ValidateSkill for validating string formats in the context of regular expressions. Use when the user's task is specifically about validating string formats.
-
legendtkl Skill Syn Video SubtitleSkill for adding subtitles and captions in the context of video files. Use when the user's task is specifically about adding subtitles and captions.
-
legendtkl Skill Syn Audio NormalizeSkill for loudness normalization in the context of audio files. Use when the user's task is specifically about loudness normalization.
-
legendtkl Skill Syn Image WatermarkSkill for applying watermarks in the context of image files. Use when the user's task is specifically about applying watermarks.
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 coreaudio-modernization-repair-workflow, realtime-media-over-quic-workflow, testing-workflow-optimizer. 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.