stackpicks.dev
All posts
Claude Skills Explained — The 2026 Guide to Reusable AI Workflows (with Examples)
AI Tooling·9 min read

Claude Skills Explained — The 2026 Guide to Reusable AI Workflows (with Examples)

Complete guide to Claude Skills: what they are, how they differ from MCP servers + Projects, the 12 most useful built-in Skills, and how to write your own in 5 minutes.

Piyush Jangir
Verified author

Founder of StackPicks. Self-taught builder shipping open-source dev tools, marketing, and curator content since 2019. Based in Mumbai, India. Available on GitHub and LinkedIn.

9 min read
Quick answer
Claude Skills are reusable, named workflows that turn one-off prompts into permanent capabilities. Released October 2025 by Anthropic, a Skill is a markdown file describing how Claude should handle a specific task (write a blog post, review a PR, design a logo) plus the resources it needs. Unlike Projects (which scope to one conversation) or MCP servers (which expose external tools), Skills are portable instructions Claude can invoke by name in any context.

Most builders skipped past the "Claude Skills" launch announcement in October 2025 because the name sounds boring. They were wrong. Skills are the most important Claude primitive since MCP, and they fundamentally change how you use AI agents day-to-day.

This guide covers what Skills actually are, how they differ from MCP servers and Projects, the 12 most useful built-in Skills, and how to write your own in 5 minutes.

What Claude Skills are

A Claude Skill is a structured markdown document that defines a reusable workflow. Anthropic released them in October 2025 as a way to turn one-off prompts into permanent, portable capabilities.

Three core properties of every Skill:

  1. Named — invoked by typing the Skill name (e.g., /review-pr or use the design-logo skill)
  2. Portable — works across any Claude conversation, any Project, any context
  3. Structured — written in markdown with explicit inputs, expected outputs, and step-by-step workflow

A minimum-viable Skill looks like this:

---
name: review-pr
description: Reviews a GitHub pull request and suggests improvements
inputs:
  - pr_url: GitHub PR URL
  - focus: Optional focus area (security, performance, readability)
---

## Workflow
1. Fetch the PR diff using the GitHub MCP server
2. Read the PR description for stated intent
3. Identify the 3 highest-priority changes needed
4. Format response as: <issue> | <line ref> | <suggested fix>
5. End with a one-line verdict (LGTM, needs changes, blocking issues)

That's it. Claude reads the Skill on invocation and follows the workflow.

How Skills differ from MCP and Projects

These three primitives confuse people. Here's the clean breakdown:

PrimitiveWhat it isWhen to use
MCP serversExternal tool access (DBs, APIs, files)"Give Claude the ability to touch X"
ProjectsScoped conversation workspace"Constrain this chat to these files + this system prompt"
SkillsReusable named workflows"Teach Claude to do X consistently across all conversations"

A real example combining all three:

> I open my "Quarterly Planning" Project (scoped to my company's notion docs). I invoke the `draft-quarter-okrs` Skill (which knows our OKR format). The Skill uses the MCP server for Linear to pull the previous quarter's actuals.

Each does one thing. Together they compose.

The 12 most useful built-in Skills

After 6 months of public usage, these are the Skills that show up in every advanced builder's setup. All available from github.com/anthropics/claude-skills or via the Skill marketplace.

Coding (3)

  1. `review-pr` — Analyzes a GitHub PR diff, identifies issues, suggests fixes. Saves 20 min per PR.
  2. `refactor-to-pattern` — Refactors a function to match a named pattern (e.g., "convert to async/await", "extract to hook"). Most useful when modernizing legacy code.
  3. `write-tests` — Generates Vitest/Jest tests for a given file with edge cases + happy path. ~80% coverage on first try for pure functions.

Writing (3)

  1. `draft-blog-post` — Turns a 1-sentence topic into a full post with intro, body, FAQ. Best for technical content.
  2. `draft-email-reply` — Reads an incoming email, drafts a reply that matches the sender's tone. Massive time-saver.
  3. `summarize-meeting` — Transcript in → bullet summary + action items + assigned owners out.

Design (2)

  1. `design-logo` — Generates SVG logos with brand variables (primary, accent, font). Outputs production-ready code.
  2. `design-icon-set` — Creates a 12-icon set matching a single visual style. Saves $200 in stock icon licensing.

Ops + Productivity (4)

  1. `weekly-status` — Pulls from Linear + Slack + GitHub via MCP, writes your weekly status update.
  2. `run-incident-postmortem` — Templates a postmortem doc from incident timeline.
  3. `onboard-new-hire` — Generates a personalized first-week plan based on the role + company docs.
  4. `translate-jargon` — Rewrites technical docs in plain English for non-technical stakeholders.

How to write your own Skill in 5 minutes

The fastest way to build a Skill is to start from one you use repeatedly.

Step 1: Take a prompt you write often

Pick a task you've prompted Claude for 3+ times. Copy the prompt verbatim.

Step 2: Turn it into Skill format

Save it as my-skill.md with the structure:

---
name: my-skill
description: One sentence describing what this Skill does
inputs:
  - input_1: Description of input 1
  - input_2: Description of input 2
---

## Workflow
1. First step
2. Second step
3. Third step

## Output format
[Describe expected output structure]

## Examples
[1-2 input → output examples]

Step 3: Save to Claude's Skills directory

  • macOS/Linux: ~/.config/claude/skills/
  • Windows: %APPDATA%/claude/skills/

Or upload to Claude's web UI: Settings → Skills → Upload.

Step 4: Invoke it

In any conversation: "Use the my-skill skill with input_1 = ..."

That's it. The Skill is now permanent and portable.

Skill best practices (after 6 months of usage)

  1. One Skill, one job. Don't make a "do-everything" Skill. The whole point is composition.
  2. Specify input shapes precisely. "Email subject" not "topic". "GitHub PR URL" not "link". Specificity eliminates 80% of failed runs.
  3. Include a Workflow section. Step-by-step beats free-form prose for repeatability.
  4. Add 1-2 examples. Few-shot patterns lift success rate from 60% to 95% for non-trivial Skills.
  5. Test in isolation first. Run the Skill in a fresh conversation before adding it to a Project — debugging is easier without context bleed.

Why Skills matter for builders

Three reasons to care, ranked by impact:

  1. Compounding productivity — A Skill written once saves 5-20 min per invocation. After 10 uses, that's 1-3 hours saved on something you would've prompt-engineered from scratch each time.
  1. Team-level workflow standardization — Skills are shareable as markdown files. Your team uses the same review-pr skill → consistent code review quality across humans.
  1. Composability with MCP and Projects — Skills + MCP + Projects compose into custom agents that match your actual workflow, not Anthropic's defaults.

Common mistakes to avoid

  • ❌ Making Skills too generic ("write content") — they fail unpredictably
  • ❌ Skipping the inputs section — Claude has to guess what you mean
  • ❌ Forgetting to test on edge cases (empty inputs, malformed URLs)
  • ❌ Writing Skills that depend on conversation context (defeats portability)

What's next

Anthropic is rumored to ship a public Skill Marketplace in Q3 2026 — think GitHub for Skills, where popular ones get ratings + version history. If you write a useful Skill, publish it now to claim the name before the marketplace launches.

If you're using Claude Code daily and haven't written a Skill yet, that's the single highest-ROI 30 minutes you can spend this week.

Frequently asked questions

What is a Claude Skill?+

A Claude Skill is a structured markdown document that defines a reusable workflow — name, description, instructions, required inputs, expected outputs, and supporting resources. Claude treats the Skill as a named capability it can invoke. Examples: "review-pr", "draft-blog-post", "design-logo". Released by Anthropic in October 2025.

How are Claude Skills different from MCP servers?+

MCP servers expose external tools (databases, APIs, file systems) to Claude via the JSON-RPC protocol. Skills are pure instruction sets — markdown files that tell Claude HOW to do something. MCP is "what Claude can touch." Skills are "what Claude knows how to do." A Skill often calls MCP tools as part of its workflow, but the two are distinct primitives.

How are Skills different from Claude Projects?+

Projects scope a single conversation to specific files + system prompt. They are session-bound. Skills are portable — you invoke a Skill by name in any conversation, any context. Think of Projects as "workspaces" and Skills as "tools in your toolbox."

Can I write my own Claude Skill?+

Yes. A Skill is a markdown file with frontmatter (name, description, inputs) and a body explaining the workflow step-by-step. Save it to Claude's Skills directory and invoke by name. Anthropic publishes examples at github.com/anthropics/claude-skills. Most useful Skills are 50-200 lines.

Which Claude Skills should I install first?+

Start with these 5: write-blog-post (turns a topic into a full post), review-pr (analyzes diffs + suggests changes), design-logo (creates SVG logos with brand vars), summarize-meeting (transcripts to action items), and draft-email-reply (matches tone of incoming email). Each unlocks 80% of a common workflow in a single command.

Do Claude Skills cost extra?+

No additional cost. Skills consume your normal Claude usage (token + message limits on Pro/Max plans). The Skill itself is free — what costs is the underlying LLM calls when you invoke it. A typical Skill consumes 2-10x more tokens than a one-off prompt because of the structured workflow.

More in AI Tooling

Claude Skills Explained — The 2026 Guide to Reusable AI Workflows (with Examples) — StackPicks — StackPicks