> Claude Dev Skills Library

Use when you have a bug, stack trace, or failing test and want Claude to isolate cause and suggest a fix.

Use when you want to scaffold a full-stack SaaS (auth, billing, dashboard) with Claude Code in one session.

Use when you have an idea or MVP and want Claude to stress-test it: market, competition, and execution risks.

Use when you need a blog post, meta description, or landing section that targets specific keywords and stays on-brand.

Use when you want to design a repeatable agent workflow (e.g. “review PR”, “summarize docs”) for Claude or Claude Code.

Use when you want to improve code structure, naming, or patterns without changing behavior.

Use when you need REST or RPC API design: endpoints, request/response shapes, and versioning.

Use when you have functions or classes without docs and want consistent docstrings (JSDoc, Google style, or reStructuredText).

Use when you have a new idea and want quick, tough feedback on viability and positioning.

Use when you have several manual steps (e.g. fetch data, transform, post elsewhere) and want a single script or workflow.

Use when you want Claude Code to use an MCP server (e.g. GitHub, DB, Slack) in a safe and explicit way.

Use when you have many sources (articles, docs, threads) and need a structured summary with claims and citations.

Use when you have pricing, funnel, or monetization data and want hypotheses to test for more revenue.

Use when you want Claude to act as a consistent code reviewer: security, style, and maintainability.

Use when you want to define slash-style shortcuts or one-line triggers for repeated Claude tasks.

Use when you need a structured brief (outline, keywords, tone) for a writer or for Claude to draft from.

Use when you need ad copy, email subject lines, or landing headlines that convert, with A/B variants.

Use when you need a structured research plan or question set before diving into a topic with Claude or tools.

Use when you have a product or audience and want concrete monetization options with pros and cons.

Use when you have a big task (e.g. "migrate auth") and want a step-by-step plan with dependencies and checks.

Use when you need a concise comparison of competitors (features, pricing, positioning) from public info.

Use when your app throws vague errors and you want Claude to suggest clearer, actionable messages.

Use when you have a branch or diff and want a consistent PR title and description (what, why, how to test).

Use when you have a feature or spec and want a test plan (unit, integration, manual) before writing tests.

Use at the start of a session to give Claude project context (stack, conventions, and current focus) in one block.

Use when you have raw notes or a transcript and need structured summary: decisions, actions, and open questions.

Use when you have a schema or sample data and need a correct, safe SQL query (read-only unless you ask for writes).

Use when you have a list of keywords and want them grouped by intent or topic for content planning.

Use when you have logs or error dumps and want patterns, top errors, and suggested next steps.

Use when you have a chat or thread about a feature and want a clean spec (user story, acceptance criteria, out of scope).

Use when you want to upgrade major dependencies (e.g. React, Next) and need a safe, ordered plan.

Use when you need a concise user persona (goals, pain points, channels) for positioning or content.

Use when you have rough notes from the day and want a concise standup update (done, next, blockers).