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.
-
yoochankim Skill Action Item ExtractorExtract action items from a meeting summary and append them to todos.md. Called as a downstream step by meeting-transcript-notes, or run manually to add tasks from any source.
-
yutkat Bundle Write Teach CommitDraft `teach:` commit messages for `.github/workflows/improve-add-skill.yml`. Use when preparing or reviewing a correction commit that should trigger the Improve Add Skill workflow from `$add` categorization feedback, including moved plugin entries, removed or excluded plugins, changed `.reason.md` categories, or review-approved rationale that should be generalized into `.codex/skills/add/**`.
-
zacsweers Bundle Test Metro LocallyPublish the current Metro checkout to Maven Local and verify it in an external consumer or reproducer. Use when testing an unreleased Metro compiler or Gradle plugin change downstream, validating a GitHub issue reproduction, comparing released and local behavior, or when a task mentions `metrow publish --local`, Maven Local, or local Metro artifacts.
-
zapier Skill Exec Weekly Agenda GeneratorSynthesize the past week across meetings, chat, email, and calendar to generate a ranked list of 5-10 topics for the weekly leadership team meeting. Use when the user asks to prep for their leadership meeting, generate meeting topics, build the agenda, or says "prep me for Monday."
-
zeikar Skill Hyper AutopilotThis skill should be used when the user asks to "autopilot", "autopilot now", "kick off autopilot immediately", "start work in N hours", "work on it while I'm asleep", "trigger in a few hours", "set up autopilot for later", or makes any "leave it running" / "fire-and-forget" request over the local hyperclaude loop (distinct from GitHub-native octoperator autopilot). Runs a fire-and-forget autonomous workflow that loops the hyperclaude cycle (hyper-auto → plan-loop → implement-loop) → ff merge → push → next task, until context exhausts or a stop condition fires. Two delivery modes — (a) **scheduled** wakes up N hours/minutes from now via `CronCreate`; (b) **immediate** starts right now in this session, no cron. Requires the hyperclaude plugin installed (it drives `/hyperclaude:hyper-auto`).
-
zhnt Skill StandardApply the standard Coding workspace workflow with explicit inspection, scoped edits, and proportionate validation.
-
zhongerxin Bundle Cowart Open CanvasOpen, reopen, or explicitly refresh the native Cowart canvas when the user asks to see it, or when a bare @Cowart invocation has no other requested workflow.
-
zjy365 Bundle Objective CrafterTurn rough work requests into strong Codex /goal objectives with measurable outcomes, verification evidence, constraints, iteration policy, and blocked stop conditions. Use when the user asks to write, refine, strengthen, or translate a task into a Goal; says things like 帮我写 goal, 制定可执行目标, 收敛成 goal, turn this into /goal, keep working until done, continue until fixed, or wants Codex to persist across multiple turns until evidence says the task is complete.
-
znkd Bundle Gemit WorkflowA color-coded, AI-enhanced Git workflow assistant that guides users through staging, analyzing, committing, and syncing code with safety checks. Use this when you need a standardized Git workflow.
-
t-0-co Bundle Workspace Ralph OrchestratorOrchestrate Ralph automation loops for spec-driven development. Use when starting, stopping, monitoring, or checking status of Ralph loops. Triggers on Ralph start, Ralph stop, Ralph status, spec automation, task loop, run tasks, check progress, kill Ralph, resume Ralph, or tmux session management.
-
wazzamo Bundle Note TakingNotes are held in the `notes/` directory and follow this document guide for formatting.
-
webioinfo01 Bundle Aweskill CreatorUse when creating, authoring, or improving a skill: scaffold a new skill, draft SKILL.md content, write trigger descriptions, test with realistic prompts, iterate wording, turn a repeated workflow from the current conversation into a reusable skill, or customize an installed skill. 中文触发词:制作技能、创建技能、新建skill、写一个技能、把这段流程做成技能、技能创作、改进技能、改进触发词、定制已安装技能。
-
sourman Skill Supabase WorkflowSupabase database migrations, type generation, edge function management, and best practices for this project
-
specture-system Skill Github WorkflowUse when working with GitHub issues or pull requests for the Specture repository, including viewing issues, preparing PRs, and choosing conventional-commit titles.
-
specula-org Bundle Harness GenTrace harness generation for SysMoBench. Use when bootstrapping a new task: clone the system into artifacts/<task>/, instrument it to emit NDJSON traces at the task-required granularity, write a run.sh, and produce INSTRUMENTATION.md. One-time work per task; the resulting harness is reused for every spec evaluation via the tv-eval skill.
-
ssshooter Skill Wxt Extension Release WorkflowA complete step-by-step workflow for upgrading the extension version, documenting updates in CHANGELOG.md, packaging the extension for Chrome, Firefox, and Edge, and submitting the release to the web stores in a single workflow.
-
startx-founders Bundle Startx Boa PrepHelp a StartX founder prepare for a Board of Advisors meeting, a CEO or board review, or a formal advisor review. Use when a founder says they have a BoA meeting, board review, or advisor review coming up and wants to prep, build their pre-read, or sharpen what they bring to the room. Walks six StartX forcing questions across the whole company (not one challenge), helps assemble an advisor-ready pre-read with evidence per claim and explicit open risks, plus a 2-3 challenge agenda. Helps sharpen the founder's thinking and surface real gaps; it does not replace judgment or invent evidence.
-
superplanehq Skill Superplane MonitorMonitor and debug SuperPlane workflow executions. Inspect runs, diagnose failures, and manage execution queues. Use when a workflow fails, an execution is stuck, or the user wants to check run status. Triggers on "debug", "failed", "failure", "execution", "output channel", "passed but failed", "run status", "stuck", "queue", "troubleshoot".
-
syabro Skill Mdtask DoWork one project task end to end — pick, plan, review, execute, review code, update the spec, commit
-
syabro Skill Mdtask AddALWAYS invoke this skill when user asks to add, create, or track a task — including indirect requests like "make a task for X", "add a task for this", "we need a task to...". Never add tasks manually by editing spec files. Handles full workflow — collect requirements, pick or create the spec, propose text, get approval, save, assign ID, commit.
-
syedahmad0786 Skill Meeting MinutesTurn raw meeting notes or a transcript into structured minutes with decisions, action items, and owners. Use when notes need formatting into minutes.
-
syjcnss Bundle Dune2Focused Dune CLI skill for on-chain investigation queries that are hard or impossible via RPC: finding token transfers from/to a specific address (across all tokens), locating a contract's creation transaction, finding all transactions that called a specific function on a contract, filtering/searching logs by contract or event, and looking up labels/names for any Ethereum address. Use this skill whenever the user wants to search for transactions meeting specific conditions, find who interacted with a contract, trace token flows for a wallet, look up contract deployment, filter events, or identify an address — especially when they say things like 'find all txs that called X', 'show token transfers for address', 'when was this contract deployed', 'search for logs', 'who called this function', 'what is this address', 'label for address', or 'who owns this wallet'.
-
tanishqkancharla Skill Scroll XExtract posts from X.com feed via Libretto workflow, then analyze for comment-worthy and generally interesting content
-
tanishqkancharla Skill Scroll LinkedinExtract posts from LinkedIn feed via Libretto workflow, then analyze for comment-worthy and generally interesting content
-
tao3k Skill Rust Verification ProfileUse when configuring RustVerificationProfileHint, verification task mappings, receipts, waivers, or verification-policy tests.
-
tao3k Skill Rust Verification PerformanceUse when a rust-lang-project-harness task touches latency, throughput, allocation behavior, parser/render loops, or Rust performance verification contracts.
-
tdesktop-x64 Bundle ContinueContinue autonomous Telegram Desktop development from the shared ai-tdesktop repository. Use when the user invokes $continue or /continue, asks Codex to keep working through the AI queue, or wants one command to resume the active task at the head of a frozen startup batch, drain matching queued work, or process the local inbox only when startup has no task work, while including and consolidating follow-ups discovered from the batch but deferring unrelated tasks added mid-run.
-
tdesktop-x64 Bundle Perform TaskResolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results. Use when the user invokes $perform-task or /perform-task with a known task name, or when the continue scheduler delegates one selected task. Runs standard review lenses with fast applicability bailouts and selects task-specific domain and evidence instruments without selecting additional work.
-
tdesktop-x64 Bundle Process InboxProcess the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active. Use when the user invokes $process-inbox or /process-inbox, asks to triage or process ai-tdesktop/inbox/inbox.md, or wants inbox notes and pasted images routed into new or existing AI projects and dated tasks without implementing them.
-
team-reflect Skill Brain BackfillSource-led first-run or large historical Local Brain import. Use when setting up a new brain from Gmail/GWS, Granola, WhatsApp, Reflect notes, Calendar, contacts, or other personal data sources, especially when the user asks for a comprehensive backfill.
-
terryyin Skill Bug FixingFix bugs with a test-first workflow. Use when the user reports a bug, asks to fix a defect, or describes unexpected behavior. Triggers on: bug, fix, defect, broken, regression, not working, unexpected behavior.
-
terryyin Skill Phased PlanningDecompose tasks into phased plans with one behavior per phase. Use when planning new features, breaking down large tasks, when a task has been in progress for over 10 minutes, or when the planning timer hook fires. Triggers on: plan, decompose, phases, break down, task too large, stuck.
-
terseai Skill Terse ImproveImprove an existing Terse workflow. Use when the user wants to fix, speed up, or refactor an automation already built on Terse, or asks why a deployed job misbehaved. Diagnoses from production run history and verifies with replay.
Audited -
tetherto Skill Qts Pr CreateGenerate qvac-test-suite pull request titles and descriptions for framework runtime changes, packaging or export changes, workflow or publish changes, docs-only cleanup, and template or mobile runtime updates. Use when creating a framework PR or refining its title/body.
-
tetherto Skill Qts Pr ReviewReviews qvac-test-suite pull requests and diffs for package-surface risk, CLI/versioning behavior, dist hygiene, workflow parity, docs accuracy, and mobile template/runtime integrity. Use when reviewing a PR, a branch diff, or doing a senior engineer pass on framework changes.
-
tetherto Skill Qts Skill ListCatalog of the repo-local qts-* skills for qvac-test-suite with one-line purpose and when-to-use guidance. Use when the user asks what skills exist in this repository, which skill fits a task, or how to invoke a repo-specific skill.
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 startx-boa-prep, action-item-extractor, write-teach-commit. 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.