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.
-
willakins Bundle Monitor CodexEnsure Codex review is requested for the current pull request head and monitor Codex review results or concerns. Use when the user asks to request, watch, or monitor Codex review, or when another monitoring workflow needs the Codex-review half.
-
willakins Bundle Monitor Merge ConflictsDetect whether a monitored pull request or branch has merge conflicts, and resolve them by delegating to the existing merge-conflict workflow. Use when monitoring should include PR mergeability, base-branch conflicts, or GitHub reports that a PR cannot be merged cleanly.
-
willakins Bundle Setup Feature WorktreesCreate planned feature branches and git worktrees from an updated base branch, optionally reusing a clean current worktree, then set up databases/task links through setup-worktree-database. Use when the user already has a branch plan or ordered branch list and wants local git/worktree setup. Do not use for branch planning, implementation, PR publication, CI repair, merge-conflict repair, or database setup alone.
-
willakins Bundle Enable Remote PublicationUse when Codex must set up or verify GitHub remote publication after a blocked workflow, including git push auth, exact PR-head targets, force-push repair, gh PR mutation auth, app review/comment readiness, or why can't Codex push. Do not use for normal PR creation after auth works, CI monitoring, branch review, generic git help, or local-only commits.
-
willakins Bundle Analyze And Fix All SkillsBatch analyze and repair Codex skill evaluation health across installed skill folders. Use when the user says "analyze and fix all skills", "fix every skill", "loop over all skills", "make all skills pass Waza", "repair all Chat Customizations Evaluation diagnostics", or asks to run the analyze-customization-evaluations and fix-customization-evaluation-diagnostics workflow for every Codex skill. Do not use for product code tests or non-skill repositories.
-
willakins Bundle Sync Recent Prs To AirtableEnd-to-end sync of recent GitHub pull requests into Croft Airtable task tracking. Use when Codex needs to gather the user's recent open and recently closed PRs, compare them against Airtable tasks, create missing task records, and update existing Airtable task status so the board matches recent coding work.
-
willakins Bundle Sync Airtable Task Status From PrsUpdate matched Croft Airtable tasks so their status reflects current GitHub pull request state. Use when Codex already has PR-to-task matches and needs to apply the Airtable write side of the sync, especially for moving tasks forward to In Progress, Needs Code Review, or In Prod without duplicating task creation logic.
-
mingchen666 Bundle Study Companion EnGeneral study companion for learning, review, exam prep, exam-point analysis, syllabus/exam-outline interpretation, finals speedrun teaching, concept explanation, problem solving, homework coaching, error analysis, active recall, flashcards, study plans, visualizations, animations, simulations, coding practice, language learning, and academic writing. Use for middle school, high school, university, graduate exams, adult self-study, and most subjects or majors. The skill text is English for compactness, but user-facing replies default to Chinese unless the user asks for English, the task is foreign-language learning, or the deliverable must be English. Trigger for study, finals, tests, exam scope, syllabus, course outline, rubric, textbooks, notes, PDFs, cards, mind maps, knowledge graphs, animations, Manim, Feynman, Socratic, spaced repetition, papers, essays, or "help me learn X" / "I don't understand this".
-
phuc-nt Bundle Mk CookImplement features, plans, and fixes with structured workflow. Use for feature development, plan execution, code implementation pipelines.
-
phuc-nt Bundle Mk Project ManagementTrack progress, update plan statuses, manage Claude Tasks, generate reports, coordinate docs updates. Use for project oversight, status checks, plan completion, task hydration, cross-session continuity.
-
resonatehq Skill Resonate Recursive Fan Out Pattern GoImplement recursive fan-out / parallel workflow execution in Go with Resonate — dispatch all children via ctx.RPC or ctx.Run, collect futures in a slice, then await each. Use when processing batches, trees, or graphs where each child is independently durable and optionally recurses. Verified against the resonate-sdk-go 0.1.0 tag.
Audited -
resonatehq Skill Resonate State Bus Pattern TypescriptStream durable workflow state to browsers (or any live subscriber) via an external realtime bus. Use this pattern when the worker is short-lived or scales to zero — keeping the worker stateless, making progress observable, and decoupling clients from the workflow's lifecycle.
Audited -
resonatehq Skill Resonate HTTP Service Design TypescriptDesign HTTP services that use Resonate durable functions behind route handlers, including routing patterns, workflow boundaries, and RPC calls to other service workers (e.g., database service). Use when building or refactoring HTTP APIs that trigger durable workflows in TypeScript.
Audited -
resonatehq Skill Resonate Recursive Fan Out Pattern JavaImplement recursive fan-out / parallel workflow execution in Java with Resonate — dispatch all children via ctx.run or ctx.rpc collecting a List of ResonateFuture, then await each. Covers single-workflow fan-out, cross-worker recursion via ctx.rpc to a named worker group, and the worker/client split. Use when processing batches, trees, or graphs where each child is independently durable and optionally recurses. Verified against example-fan-out-fan-in-java and example-recursive-factorial-java and develop/java.mdx (docs PR
Audited -
resonatehq Skill Resonate Durable Sleep Scheduled Work GoImplement durable sleep and recurring-work patterns in Go with Resonate — ctx.Sleep(time.Duration) inside workflows for timers, countdowns, reminders, and long-horizon delays that survive process restarts; Resonate.Schedules() (shipped in 0.1.0) for direct cron-fired promises, plus in-workflow ctx.Sleep loops or external cron → RPC for recurring registered-function dispatch. Use when a workflow must wait for hours or days, or when a function should run on a fixed schedule. Verified against the resonate-sdk-go 0.1.0 tag.
Audited -
resonatehq Skill Resonate Recursive Fan Out Pattern PythonImplement recursive fan-out in Python for parallel workflow execution — spawn N sub-workflows from a parent, optionally recurse deeper, await results, handle partial failure. Use when processing a tree, batch, or crawl where the work shape is dynamic and each child is independently durable.
Audited -
resonatehq Skill Resonate Recursive Fan Out Pattern TypescriptImplement recursive fan-out patterns for parallel workflow execution. Use when breaking down complex work into independent subtasks that execute recursively with automatic deduplication and load balancing.
Audited -
robsonrung Bundle SharedShared references, schemas, and scripts used by the other skills. This directory is a library dependency, not an executable workflow.
-
robsonrung Bundle Review GateReturn a machine-readable review verdict for a PR or branch. Use when a workflow needs a merge gate with structured evidence; use full-review for a human-facing review.
-
robsonrung Bundle Dynamic HarnessPlan and run a bounded worker fleet for a complex task. Use when the user explicitly requests delegation, parallel work, a tournament, or a managed mission.
-
robsonrung Skill TddImplement behavior through the red-green-refactor loop. Use when test-first execution is requested or selected by the coding workflow; use safe-incremental-coding first for untested legacy code.
-
robsonrung Skill Design GateSelect relevant design lenses for a planned slice and return a proceed-or-revise verdict. Use during task planning or when a design boundary changes; invoke a named lens directly for a single-lens review.
-
robsonrung Bundle BrainstormExplore an uncertain idea and recommend whether to build, defer, reduce scope, or reject it. Use for brainstorming or a build decision; use interview-me next to settle requirements.
-
robsonrung Bundle Capture LearningCapture a verified, reusable solution in docs/solutions. Use when asked to document a solved problem or when a delivery workflow selects learning capture; use session-handoff for work continuity.
-
robsonrung Bundle Coding Review SimplifyReview a completed code change for behavior-preserving simplification, local correctness, and maintainability. Use after implementing a scoped task or when the user asks to simplify a concrete diff. Do not use as a full feature review or to choose the delivery reviewer plan.
-
timlai666 Bundle Product Conjoint AnalysisRun a product-analysis focused revealed-preference logistic conjoint workflow (product specs + reviews/transactions, stacked binary choice, logistic estimation) — from attribute design through business insights (importance, willingness-to-pay, optimal product configuration, pricing and cost-benefit). This skill MUST be used when the goal is to analyze products and infer multi-attribute preferences from observed market behavior, and MUST NOT be used for a generic survey-only conjoint setup.
1 -
timlai666 Bundle Service Design WorkshopThis skill MUST be used when turning a service design problem into a structured workshop output, especially for 服務設計, 服務藍圖, 服務流程, 接觸點, 前台後台, 服務實證, 顧客體驗, 利害關係人, 服務概念, or 服務架構. Trigger when the task asks for a practical service design brief, blueprint-ready structure, touchpoint analysis, or prototype and validation next steps rather than only theory review.
1 -
timlai666 Bundle Software Engineering GuidelinesSoftware Engineering Guidelines
1 -
timlai666 Bundle Service Innovation WorkshopThis skill MUST be used when turning a service innovation problem into concept options, prototype testing, and risk checks, especially for 服務創新, 創新機會, 價值共創, 服務原型, SCAMPER, 購買者效用矩陣, 創新流程, 創新困境, or 服務體驗工程. Trigger when the task asks for practical innovation directions, concept generation, opportunity framing, or validation planning rather than only concept definitions.
1 -
timlai666 Bundle Decision Bias Quality ControlThis skill MUST be used when evaluating high-stakes decisions with bias-aware quality control, including proposal review, decision meeting facilitation, and personal coaching. MUST trigger on requests such as 重大決策、偏誤檢查、提案審查、決策會議引導、決策教練、go/no-go 決策。
1 -
trac3r00 Skill Git MasterMUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git work.
Audited -
trac3r00 Bundle Verify RefComprehension gate before porting, copying, or adapting an existing implementation. Proves understanding of the reference code before any new code is written. Use when the task is "port X", "copy how Y does it", "adapt Z", or reimplementing existing behavior.
-
vigneshbarani24 Skill PmUse when working with SAP Plant Maintenance, equipment management, maintenance orders, notifications, preventive/corrective/predictive maintenance, functional locations, task lists, measuring points, or S/4HANA Asset Management.
-
vigneshbarani24 Skill Verification Before CompletionUse before claiming ANY task is complete. Activates at the end of every skill execution, every deliverable generation, and every user request fulfillment. Blocks completion claims that lack enumerated evidence.
-
donatassimkus Bundle EmailEmail Skill
-
spinabot Skill TaskflowUse when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
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 setup-feature-worktrees, monitor-codex, monitor-merge-conflicts. 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.