Best Skills for Workflow and Productivity

The AI writes decent code. But it does not plan before coding. It does not verify before claiming success. It writes commit messages that say “update stuff.” It cannot run a browser, audit a website, or create a PR that follows your repo’s template. The code is fine; everything around the code is amateur.

Productivity skills address these gaps. This guide links to real published projects and gives you practical prompts for common workflows. Marketplace counts are time-sensitive adoption signals, not quality scores.

Note

The generic skills CLI can copy portable SKILL.md files into Cursor, Claude Code, and Codex. A full plugin can also contain a bootstrap, hooks, tool mappings, or executable code, so a generic npx skills add command is not always equivalent to the host’s native plugin installer. Counts in individual entries are historical snapshots unless a newer date is stated; check the linked registry before making adoption decisions.

What You’ll Walk Away With

• Published skills for planning, debugging, review, and git workflows
• The difference between portable skill installation and a complete plugin
• Prompts that leverage each skill for common workflows
• A recommended stack that covers the biggest productivity gaps

Planning and Execution Skills

obra/superpowers — A Complete Agent Workflow

obra/superpowers is a 14-skill methodology and plugin that covers design, worktree isolation, executable plans, TDD, task review, final review, fresh verification, and branch completion. At the July 11, 2026 snapshot, skills.sh showed roughly 2.2 million aggregate skill installs—but aggregate skill installs, plugin installs, and GitHub stars are different metrics.

The complete plugin should be installed through the native Claude Code, Codex, or Cursor marketplace. npx skills add obra/superpowers can copy its portable skills, but may not install the bootstrap and host adapter that activate the full workflow.

Its planning and execution chain contains:

• brainstorming: asks one question at a time, compares approaches, and saves an approved design before implementation;
• using-git-worktrees: detects existing isolation, asks for consent when needed, and verifies a clean baseline;
• writing-plans: records exact files, interfaces, tests, commands, and small executable tasks;
• subagent-driven-development: uses a fresh sequential implementer and reviewer for each task, then reviews the whole branch;
• executing-plans: executes the saved plan in a separate session with review checkpoints;
• dispatching-parallel-agents: parallelizes only genuinely independent investigations.

Tip

Copy-paste prompt for plan-then-execute workflow:

“I need to add OAuth2 login with Google and GitHub providers. Use your brainstorming skill first to ask me clarifying questions about scope and requirements. Once we agree on the approach, use writing-plans to create a detailed implementation plan. Do not write any code until I approve the plan.”

Verification Before Completion

Part of obra/superpowers. This skill requires fresh output from relevant verification commands—tests, type checks, linting, or builds—before the agent claims completion. It strongly steers behavior, but CI remains the hard enforcement layer.

What it prevents:

• Claiming success when tests fail
• Missing type errors that only show up at build time
• Forgetting to run the linter after refactoring
• Skipping manual verification steps defined in your project

Define Goal — openai/skills

npx skills add openai/skills

OpenAI’s official skill collection (2,900 installs) includes define-goal, which turns a fuzzy intention into a concrete, measurable objective with explicit success criteria before any code gets written. Lighter weight than obra’s planning skills, useful when you want to pin down the outcome and scope rather than produce a full task breakdown. Confirm it installed with npx skills list before relying on it.

Debugging Skills

Systematic Debugging

Part of obra/superpowers. A four-phase root-cause method: investigate, compare working patterns, test one falsifiable hypothesis, then implement with a regression test. After three failed fixes, it tells the agent to question the architecture instead of stacking another patch.

Tip

Copy-paste prompt for structured debugging:

“The checkout flow fails silently when a user has both a gift card and a discount code applied. Use your systematic-debugging skill: reproduce the issue, list possible root causes, test each hypothesis, and only propose a fix after confirming the root cause. Do not guess.”

Test-Driven Development

Part of obra/superpowers. Its strict RED–GREEN–REFACTOR loop requires the agent to observe the right failure before writing the smallest passing implementation, then refactor while green.

What it teaches:

• Write the failing test before the implementation
• Red-green-refactor cycle discipline
• Edge case identification and test coverage
• When to use mocks versus real dependencies

Code Review Skills

Requesting Code Review

Part of obra/superpowers. Current v6 dispatches a fresh, read-only task reviewer that returns separate specification-compliance and code-quality verdicts. The old named code-reviewer agent was removed in v5.1.0.

Tip

Copy-paste prompt for AI code review:

“Review the changes on this branch compared to main. Use the requesting-code-review skill to dispatch a reviewer subagent. Categorize each finding as critical, suggestion, or nitpick. For critical findings, explain the risk and provide a fix. Ignore pure style issues.”

Code Reviewer — google-gemini/gemini-cli (1.6K installs)

Google’s code review automation skill supporting TypeScript, JavaScript, Python, Go, Swift, and Kotlin. Focused on language-specific idioms and best practices.

npx skills add google-gemini/gemini-cli

What it covers:

• Language-specific anti-patterns and idiomatic improvements
• Performance concerns per language runtime
• Security patterns relevant to each language ecosystem
• Constructive feedback with specific suggestions

Git Workflow Skills

Using Git Worktrees

Part of obra/superpowers. It first detects an existing isolated workspace, follows repository preferences, asks before creating a worktree when no preference exists, verifies ignore rules, and runs baseline tests.

What it teaches:

• Creating worktrees for feature branches
• Managing multiple worktrees without confusion
• Cleaning up worktrees after merge
• When worktrees are better than branch switching

Finishing a Development Branch

Part of obra/superpowers. It reruns tests, detects workspace provenance, then presents four explicit choices: merge locally, push and open a PR, keep the branch, or discard it. Destructive cleanup requires confirmation.

Yeet — openai/skills

Part of openai/skills (2,900 installs total). Stages, commits, pushes, and opens a PR in one flow. When you just need to ship the current changes without ceremony, this skill handles the entire git-to-PR pipeline in a single command.

npx skills add openai/skills

PR Creator — google-gemini/gemini-cli (481 installs)

Creates pull requests following your repo’s PR template. Reads the template from .github/PULL_REQUEST_TEMPLATE.md, fills in each section based on the actual changes, and submits the PR.

npx skills add google-gemini/gemini-cli

Tip

Copy-paste prompt for PR creation:

“Create a pull request for the changes on this branch. Follow the repo’s PR template. Include a summary of what changed, why it changed, how to test it, and any risks for reviewers. Link to the relevant ticket if one is mentioned in the branch name.”

GitHub and CI Skills

Address PR Comments — openai/skills

Part of openai/skills. Reads GitHub PR review comments and issue comments, then addresses them: fixes code issues, responds to questions, and marks conversations as resolved.

Fix CI — openai/skills

Part of openai/skills. Debugs and fixes failing GitHub Actions workflows. Reads the CI logs, identifies the failure, and proposes or applies a fix. Saves you from manually parsing through hundreds of lines of CI output.

Sentry — openai/skills

Part of openai/skills. Inspects Sentry issues and pulls error summaries. When a production error fires, this skill fetches the stack trace, context, and frequency data so the AI can start debugging with full information.

Linear — openai/skills

Part of openai/skills. Manages Linear issues, projects, and team workflows. Creates issues, updates status, assigns team members, and links issues to PRs.

Documentation Skills

Docs Writer — google-gemini/gemini-cli (686 installs)

Writing and reviewing documentation. Teaches the AI to write docs that developers actually read: clear structure, practical examples, and appropriate detail.

npx skills add google-gemini/gemini-cli

What it teaches:

• Lead with the “why,” then the “how”
• Use concrete examples, not abstract descriptions
• Write for scanners: headings, bullet points, code blocks
• Keep paragraphs short (3-4 sentences maximum)
• Include working code examples that can be copied directly

Tip

Copy-paste prompt for documentation generation:

“Generate documentation for the authentication module in src/lib/auth/. Read the code first, then use the docs-writer skill: start with what the module does and why someone would use it, show the main use cases with code examples, and end with configuration options and troubleshooting.”

Browser and Web Skills

browser-use/browser-use (24.4K installs)

Browser automation, testing, form filling, and screenshots. This skill gives the AI the ability to interact with actual web pages: navigate, click, fill forms, take screenshots, and verify UI state.

npx skills add browser-use/browser-use

Use cases:

• E2E testing without writing Playwright scripts manually
• Filling out forms to test validation logic
• Taking screenshots for documentation or bug reports
• Verifying deployed UI matches expectations

Playwright — openai/skills

Part of openai/skills. E2E testing patterns using Playwright. More structured than browser-use for teams that want repeatable, committed test suites rather than ad-hoc browser interaction.

squirrelscan/skills — Website Auditing (14.8K installs)

Audits websites for SEO, performance, accessibility, and security using over 230 rules. Run it against your staging URL before every release to catch issues the AI would otherwise miss.

npx skills add squirrelscan/skills

firecrawl/cli — Web Scraping and Data Extraction (89K installs)

The most-installed data extraction skill collection on skills.sh. Firecrawl turns websites into structured data for AI consumption. Includes 7 skills: firecrawl (21K) for core scraping, plus specialized skills for browser-based scraping, search, multi-page crawling, autonomous research agents, and site mapping. See Official Skills from Technology Makers for the full skill breakdown.

npx skills add firecrawl/cli

Design and Implementation Skills

figma-generate-design

Part of figma/mcp-server-guide (11,100+ installs total). Translates Figma designs to code with high fidelity. Reads the Figma file, extracts layout, spacing, colors, and typography, then generates component code that matches the design.

npx skills add figma/mcp-server-guide

figma-generate-library

Also part of figma/mcp-server-guide. Generates a design-system component library from your Figma file so the AI consistently reuses the right tokens, spacing, and patterns across all generated code.

Skill Discovery

find-skills — vercel-labs/skills (154K installs)

The most-installed skill on the entire platform. Helps the AI discover and install other skills. When you describe a workflow need, this skill searches the registry and recommends relevant skills.

npx skills add vercel-labs/skills

Building Your Skill Stack

Recommended Starter Stack

For most teams, combine the native Superpowers plugin with selected portable skill collections. Install Superpowers through your host’s marketplace, then add the other repositories you actually need:

npx skills add openai/skills
npx skills add google-gemini/gemini-cli

Superpowers supplies 14 process skills for planning, debugging, TDD, review, git workflows, and verification. Review overlapping instructions before enabling multiple workflow collections at once.

Adding Project-Specific Conventions

After installing community skills, create a project-specific skill that captures your team’s unique conventions:

Cursor

Create .cursor/rules/team-conventions.md covering:

• Branch naming: type/TEAM-123-description
• PR reviewers: backend changes need @backend-team, frontend needs @frontend-team
• Deploy process: merge to main triggers staging, manual promotion to production
• Communication: post in #releases after each production deploy

Claude Code

Create .claude/skills/team-conventions/instructions.md covering:

• Branch naming: type/TEAM-123-description
• PR reviewers: backend changes need @backend-team, frontend needs @frontend-team
• Deploy process: merge to main triggers staging, manual promotion to production
• Communication: post in #releases after each production deploy

Codex

Add to .codex/instructions.md:

• Branch naming: type/TEAM-123-description
• PR reviewers: backend changes need @backend-team, frontend needs @frontend-team
• Deploy process: merge to main triggers staging, manual promotion to production
• Communication: post in #releases after each production deploy

Tip

Copy-paste prompt for convention extraction:

“Analyze the last 50 commit messages, the last 20 PR descriptions, and the README files in this repository. Identify recurring patterns in how the team communicates: commit message format, PR structure, documentation style, and naming conventions. Generate a team conventions skill file that codifies these patterns.”

More Official Productivity Skills

Many technology companies publish official skills for monitoring, data pipelines, and developer workflows. These are covered in detail in Official Skills from Technology Makers:

Skill	Installs	What It Does
apify/agent-skills	36,000+	Web scraping, market research, lead generation, competitor intelligence
getsentry/sentry-for-ai	8,700+	AI-assisted error triage and stack trace analysis
getsentry/sentry-agent-skills	5,200+	Sentry SDK setup, alerting, performance monitoring
astronomer/agents	8,800+	Apache Airflow data pipeline orchestration
coderabbitai/skills	1,800+	AI-powered code review automation
datadog-labs/agent-skills	1,300+	Datadog monitoring and observability
dagster-io/skills	992	Dagster data orchestration
dbt-labs/dbt-agent-skills	1,100+	dbt data transformation
makenotion/claude-code-notion-plugin	23	Notion workspace integration
n8n-io/n8n	11	n8n workflow automation
posthog/posthog	123	PostHog product analytics

Business and Product Workflow Skills

The Wondel.ai Skills Library includes several skills that overlap with productivity workflows — structured product discovery, customer research, and rapid prototyping cadences:

Skill	Source	What It Does
wondelai/skills/design-sprint	Sprint (Jake Knapp)	Structured 5-day process to prototype and test product ideas
wondelai/skills/continuous-discovery	Continuous Discovery Habits (Teresa Torres)	Weekly customer touchpoints with Opportunity Solution Trees
wondelai/skills/mom-test	The Mom Test (Rob Fitzpatrick)	Customer interview methodology that surfaces real insights
wondelai/skills/lean-startup	The Lean Startup (Eric Ries)	Build-Measure-Learn loops and MVP experiments

For the full collection of 41 business, design, and engineering framework skills, see Best Skills for Business and Product.

When This Breaks

Superpowers makes the agent too methodical. The full workflow is intentionally thorough. Explicitly agree on a reduced path—for example, “This is a mechanical one-line fix: skip design and planning, but run the targeted test and final verification.” Do not assume a terse request silently disables every process skill.

Verification stops on flaky or already failing tests. Record the exact failure and distinguish an accepted red baseline from a regression. Do not silently retry until green or ignore a file without an explicit team policy and compensating evidence.

The workflow becomes slow or token-heavy. Compare a smaller subset, inspect which skills actually trigger, and measure cost after model, plugin, or harness upgrades. Modern hosts often load skill bodies progressively, so diagnose actual activation instead of blaming the number of files alone.

Parallel agent work collides. Parallelize only independent domains. In Superpowers v6.1.1, never run two SDD workflows in the same checkout because issue #1942 documents shared .superpowers/sdd/ state; give each session a separate worktree.

Browser-use skill needs a running browser. The browser-use skill requires a browser instance. If you are running in a headless CI environment, ensure you have a headless browser configured. The skill will fail silently without one.

find-skills returns too many results. The vercel-labs find-skills skill searches broadly. Be specific in your query: “Find skills for Playwright E2E testing” works better than “Find testing skills.”

What’s Next

Superpowers Deep Dive Installation, all 14 skills, lifecycle, evidence, security, limitations, and team adoption.

Best Business Skills Marketing, product strategy, UX methodology, and sales skills.

Building Custom Skills Create and publish skills tailored to your team's workflows.

Skills Best Practices Optimize your skill setup for maximum team impact.