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.
-
luissambrano Bundle Sdd WorkflowSpec-Driven Development methodology. Use when starting a new feature, project, or complex implementation. Transforms vague ideas into structured specifications before writing code.
-
luissambrano Bundle Tdd WorkflowMaster TDD orchestrator specializing in red-green-refactor
-
anastasiyaw Bundle Agents Best PracticesUse when designing, auditing, refactoring, or explaining an agentic harness for any domain, especially when work must continue from a measured gap to verified completion. Covers provider-neutral loops, tools, permissions, environment adaptation, planning, durable workflow state, context, skills, observability, evals, and safety for OpenAI, Anthropic, and compatible APIs. Not for implementing an ordinary app feature or reviewing one concrete diff.
-
anastasiyaw Bundle Refactoring SafelyChange the structure of code that already exists without changing what it does: smells as triggers, the named transformations (extract/inline, move feature, organise data, simplify conditionals), and above all the workflow that makes it safe — characterization tests first, one transformation at a time, green between every step. Use when a file or function is already too large; when asked to "split this module", "extract this", "break up main.py", "clean up this legacy code", "reduce coupling here"; when a shape advisory fires on a grown file; or before any restructuring of code that has users. Do NOT use to decide the target layout of a NEW project (use architecture-first), for unit-level naming and function quality in code you are writing fresh (use code-complexity), for capacity or storage decisions (use system-and-data-design), or to strip over-engineering on request (use lean-code). This is the transformation with a net; deciding WHERE things should end up is a different question, and doing both at once i
-
uxcel-lab Skill UX TablesDesign or critique data tables and lists — scannable structure, alignment rules (left for text, right for numbers), sorting/filtering, row interactions, and the right list type for the content. Trigger when the user asks to design or review a data table, data grid, admin table, list view, email/feed list, or asks how to present tabular or structured data.
Audited -
uxcel-lab Skill UX Login SignupDesign or critique a login / sign-up screen. Applies the always-true core (separate pages, minimal fields, inline validation, full password-reset flow) and gates context-dependent choices (social login, 2FA, "stay logged in", username vs. email) with trade-offs. Trigger when designing auth screens, sign-up forms, registration flows, or password recovery.
Audited -
uxcel-lab Skill Pm User StoryWrite or critique a user story — a small unit of user value framed from a real persona's need, not a restated task. Frames stories around who/what/why, keeps them INVEST and testable, maps them across the journey, and resists writing stories that add no clarity. Applies the always-true core and gates context-dependent decisions (strict formula vs. free-form, whether to write a story at all, acceptance-criteria depth, splitting into a map, communication framing). Trigger when asked to write user stories, turn a persona or need into stories, frame requirements as stories, build a story map, apply INVEST, or review/strengthen existing stories.
Audited -
uxcel-lab Skill UX Loaders And ProgressDesign or critique loading states and progress indicators — match the feedback type (spinner, text, determinate bar, skeleton, progress tracker) to the wait duration and task structure, and manage perceived performance. Trigger when the user asks to design or review loaders, spinners, loading states, skeleton screens, progress bars, progress trackers, steppers, or multi-step flow progress.
Audited -
ctoth Bundle Go ContextGuides Go context.Context discipline — pass it as the first parameter named ctx and never store it in a struct, derive children with WithCancel/WithTimeout/WithDeadline and ALWAYS defer cancel() (go vet's lostcancel flags a missing one), check ctx.Done()/ctx.Err() in loops and before expensive work, start from context.Background() at entry points and context.TODO() when you don't have one yet, attach reasons with WithCancelCause/Cause and decouple with WithoutCancel/AfterFunc (1.20/1.21), and carry only request-scoped values behind an unexported key type. Auto-invokes when writing or editing functions taking context.Context, WithCancel/WithTimeout/WithValue, ctx.Done()/Err(), or on "where should ctx go" / "is this context leaking" requests. The propagation-and-cancellation depth behind the policy root's "never start a goroutine you can't stop."
-
erikpr1994 Skill PlanUse when you have a spec or requirements for a multi-step task, before touching code. Triggers - plan, design, architect, implementation plan, spec, requirements.
-
erikpr1994 Skill ExecuteUse when following a written plan or task list. Checkpoint verification at each step. Triggers - execute plan, follow plan, implement plan, next step, continue, proceed.
-
erikpr1994 Skill Git ExpertUse when working with git operations including commits, branches, worktrees, and PRs. Covers the full git workflow from feature isolation to PR submission.
Audited -
erikpr1994 Skill Pr WorkflowUse when creating PRs, managing stacked PRs, or completing feature branches.
-
erikpr1994 Bundle LinearIntelligent work tracking. Automatically classifies issues, gathers codebase context, and creates well-formed Linear tickets. Triggers - linear, issue, track, bug, todo, fix, question, debt.
-
erikpr1994 Skill Dispatching Parallel AgentsUse when multiple independent tasks can run simultaneously. Maximizes throughput through parallel Task tool invocations.
-
matejformanek Skill Corpus ChainTraverse the pg-claude knowledge graph to answer "what does this feature/file/pattern touch across the corpus?" — pulls scenarios, idioms, call-site file examples, sibling patterns, subsystem ownership, and analogous past features from planning/ + sessions/ into a single chain map. Uses the graph edges built by `scripts/populate-idiom-callsites.py` (idiom → files) and `scripts/build-scenario-idiom-matrix.py` (scenario ↔ idiom bidirectional). Use proactively when brainstorming a new PG feature, planning §3 file table, investigating an unfamiliar subsystem, or trying to find "have we touched something like this before?". Also use inside `pg-feature-brainstorm` step 1 (subsystem framing) and `pg-feature-plan` before §3 to seed the file list from existing evidence rather than pure grep. Skip when you already have the anchor's downstream chain memorized, when the task is a one-file bug fix, or when the ask is about non-PG code.
-
understudy-ai Skill Things MacManage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Understudy to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
-
understudy-ai Skill Target Brief StudioHand-written end-to-end playbook for a reusable target brief workflow.
-
droodotfoo Bundle TddTest-driven development workflow for polyglot codebases. TRIGGER when: user asks to write tests first, do TDD, red-green-refactor, or requests test-driven implementation of a feature. DO NOT TRIGGER when: user asks to add tests after the fact, debug existing tests, or fix failing tests without a TDD workflow.
-
droodotfoo Bundle EthskillsEthereum ecosystem tooling and standards reference. TRIGGER when: asking about Ethereum development tools, framework selection, RPC providers, block explorers, EIP/ERC standards, or general Web3 development workflow. DO NOT TRIGGER when: writing or auditing Solidity code (use solidity-auditor skill), or working with Noir/ZK circuits (use noir skill).
-
bitterbot-ai Skill Things MacManage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Bitterbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
-
irahardianto Skill Parallel DispatchMECE task decomposition, file ownership enforcement, DAG-based execution, and safe merge protocol for intra-domain parallel dispatch. The safety invariants that prevent merge chaos when multiple agents write in parallel. Applies recursively at every nesting depth.
-
oceanfsdfsvfdsvs Bundle Iep 504 Meeting PreflightReview IEP, Section 504, special education evaluation, reevaluation, accommodation, service-log, progress, manifestation, or school meeting packets before a parent, caregiver, advocate, or school team attends a meeting, requests records, escalates a concern, or submits a complaint. Use when the user needs to map student needs, evaluations, goals, accommodations, services, progress data, missed services, consent/notice, deadlines, and evidence gaps without giving legal advice or taking live school-portal actions.
-
smicolon Bundle Tdd PlannerThis skill should be used when the user asks to "plan a feature", "prepare for dev loop", "structure TDD approach", "break down this task", "create development plan", or when generating structured prompts for iterative development. Creates dev-loop-ready plans with TDD phases, file tables, code snippets, and framework-specific guidance.
-
smicolon Skill Flow DetectorAnalyzes a task description plus the surrounding codebase and produces a list of candidate end-to-end flows. Activates when a developer describes a task using vague verbs (send, notify, sync, handle, process, integrate) without specifying entity, trigger, or recipient. Returns 1 candidate when the flow is unambiguous, 2+ when multiple plausible interpretations exist. Each candidate is a complete proposed execution context, never a question.
-
redhat-developer Bundle Rhdh Jira LinkTies a GitHub pull request or GitLab merge request to an RHDH Jira issue in RHIDP, RHDHPLAN, RHDHBUGS, or RHDHSUPP: attach the Jira Web link titled `repo #N: <title>`, post or update the structured comment, fill empty issue fields, move an RHDHPLAN Epic, Story, or Task to RHIDP, and mark a Web link merged or closed. Raises the PR or MR first when one does not exist yet. Use for "link this PR to RHIDP-1234", "attach the MR to the Jira issue", "mark the Web links merged", "mark closed PRs", replacing a hand-rolled remotelink or comment step, or a PR outside the rhdh-plugins and community-plugins monorepo flow. The full monorepo flow — build, changeset, recordings — is rhdh-pr-create.
-
redhat-developer Bundle Rhdh Konflux TasksBumps Konflux Tekton task bundle digests in `.tekton` and `.tekton-templates`, applies each task's MIGRATION.md, regenerates PipelineRuns, and checks pins against data-acceptable-bundles so ECP does not reject expired or untrusted tag@sha256 refs (tasks.unsupported, required_untrusted_task_found). Then invokes /rhdh-base-images for the matching GitHub main or release-* branch so FROM tags, rpms.lock.yaml, and Node headers stay current. Use for "bump konflux task digests", "apply the tekton migration", "ECP violation", "expired task", "trusted task", "missing node headers", node-v*-headers.tar.gz, .nvm/releases, catalog builder.Containerfile, UBI nodejs, quay.io/konflux-ci/tekton-catalog/task-* upgrades such as buildah-oci-ta or prefetch-dependencies-oci-ta, and build-definitions MIGRATION.md URLs that 404. Runs on rhdh-plugin-catalog and RHDH midstream (updateDigests.sh, generatePipelineRuns.sh, updatePLRs.sh; generatePipelineRunsForPlugins.sh is the deprecated 1.9/1.10 name).
Audited -
redhat-developer Bundle Rhdh Jira CreateOpens new work in RHDH Jira and decides what kind of work it is — Feature or Feature Request in RHDHPLAN, Epic, Story, Task, Spike or Vulnerability in RHIDP, Bug in RHDHBUGS, support conversation in RHDHSUPP — then interviews, drafts, and creates it with the right fields and parent link. Use for "file a ticket", "create a feature", "open an epic for this", "raise a bug", "log a spike", "we should track this in Jira", or turning an RHDHSUPP support case into an RHDHBUGS defect or an RHDHPLAN feature request. Picking the issue type is this skill's job, not the caller's. Editing or transitioning an issue that already exists, such as RHIDP-1234, is not creation.
-
redhat-developer Bundle Openspec OnboardGuided, narrated walkthrough of one complete OpenSpec cycle — explore, create a change, build proposal then sibling specs/design then tasks, implement, archive — using a real small task in the user's own codebase. Use for "walk me through OpenSpec", "teach me the OpenSpec workflow", "onboard me to OpenSpec", or a first-time user asking what OpenSpec even is. Does real work, not a simulation; teaches by doing rather than lecturing.
-
redhat-developer Bundle Rhdh Jira AuthoringSupplies the craft of writing good RHDH Jira work in RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP: the Feature, Epic, Story, Task, and Bug description templates with filled examples, the RHDH challenge matrix that stress-tests scope, sizing, acceptance criteria, and Epic independence, the T-shirt and Fibonacci sizing scales, keyword duplicate detection, and the tracer-bullet rules for breaking a Feature into Epics or an Epic into Stories. Use when drafting or judging the text and shape of an issue such as RHIDP-1234 — how big is this, is this AC testable, should this be one Epic or three, does this already exist. Prose and estimation craft only; it runs no Jira command.
-
redhat-developer Bundle Openspec Archive ChangeArchives a completed OpenSpec change into openspec/changes/archive/, after confirming artifact and task completion and offering to sync any delta specs into the main specs first. Use for "archive this change", "finalize <change>", or "this is done, wrap it up". Warns but does not block on incomplete artifacts or tasks — the user decides whether to proceed anyway.
-
seed-forge Bundle Devlab Web Visual OpsWeb 视觉化操作(Web Visual Operations):对 Web 应用做 Observe/Navigate/Interact/Inspect/Validate/Capture 的 day-2 操作手册。Router 层统一编排 Playwright(确定性)、Stagehand(AI 增强)、DevTools(Console/Network/Runtime)、Vision/CUA(视觉兜底)四类执行器,覆盖 Debug / UI Review / Visual Regression / E2E / Browser Automation 五类 Workflow。Stagehand 定位为 Router 的 AI Adapter 而非底座,Skill 不绑定单一框架。触发词:视觉走查、UI 审查、页面调试、控制台报错、网络请求排查、截图对比、视觉回归、浏览器自动化、visual ops、stagehand、playwright
-
seed-forge Bundle Public Git Workflow Expert BaseGit 工作流知识基座。extends netresearch/git-workflow-skill 上游通用 Git 知识,叠加团队 commit 规范、分支策略、Gitea 工作流、镜像同步经验。供 devlab-git-workflow-expert 等下游技能通过 extends 继承。
-
ntaffzii Skill TradingRoute and manage trading/investing workflow skills — market breadth and uptrend participation scoring, exposure/posture synthesis, risk-based position sizing, drawdown circuit breaker, periodic portfolio review, dividend/value screening, and trade journaling. Use when the user asks for market-regime checks, position sizing, risk gates, portfolio review, or trade journaling/stats.
-
ntaffzii Skill Deep PlanningUse this skill for any non-trivial coding task — new features, multi-file changes, architecture decisions, bug fixes with unclear root cause, or any request where the "obvious" first solution might not be the best one. Do NOT use for mechanical tasks (typo fixes, formatting, adding a single import, renaming a variable) — those should stay in Fast Mode.
-
ntaffzii Bundle Thai PdpaUse this skill for any task drafting a Thai PDPA-compliant privacy notice, consent banner, or cookie consent flow. Trigger on "PDPA", "นโยบายความเป็นส่วนตัว", "privacy policy ไทย", "consent banner", "cookie consent", "ขอความยินยอมข้อมูลส่วนบุคคล", "พ.ร.บ.คุ้มครองข้อมูลส่วนบุคคล". If the request is a GDPR-only privacy notice with no Thai users/data involved, use general GDPR patterns instead — do not silently apply Thai PDPA rules to a non-Thai context or vice versa; they overlap but aren't identical.
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 agents-best-practices, refactoring-safely, sdd-workflow. 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.