claude-md-writer
Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
40,996 results
Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context",…
Analyze Maven dependencies in Java projects, build class indexes, and decompile classes from JAR files to retrieve source code. Use when you need to view…
Provides project-specific prerequisites for AI execution accuracy — domain constraints, development phase, directory conventions, external resource access…
Local git workflows behind one command: prune merged branches and worktrees, guard secrets and destructive commands, resolve merge conflicts, create isolated…
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if…
Build LangChain (Python) tools using Claude Code's fail-closed design pattern — unified name/schema/security/execution in one class, with automatic three-layer…
Expert code reviewer that enforces best practices, clean code principles, strong typing (TypeScript), architecture guidelines, and security standards. Reviews…
Technical architect assistant that helps design robust, scalable, and maintainable backend/frontend architectures. Provides visual diagrams, pattern…
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
This skill should be used when the user asks to "create a marketplace", "set up marketplace.json", "organize multiple plugins", "distribute plugins", "host…
This skill should be used when the user asks about "Claude Code plugins", "plugin development", "how to build a plugin", "what plugin components exist",…
Run a stateful whole-repository review campaign with a persistent `reviews/` ledger. Explicit invocation only.
Design advisor for AGENTS.md / CLAUDE.md / GEMINI.md and .claude configuration, three modes: review & diagnose / draft for new projects / best-practice Q&A. Six dimensions: length budget / executability / section routing / duplication & contradiction / entry-point consistency / timeliness. By default it only diagnoses and does not modify; changes are made only after confirmation. Triggers: "review my AGENTS.md", "CLAUDE.md…
Use when extracting or generating an OpenAPI spec from existing API code. Triggers on "extract OpenAPI", "code first", "generate spec from code", "FastAPI…
Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI.
Resolve inline code review comments on a GitHub PR. Use when asked to "resolve review comments", "address PR feedback", "fix PR comments", or "work through…
Accompany the user seamlessly from brainstorming ideas to a working prototype plus a full demo package (startup verification, screenshots, demo steps).
Use when reviewing an upstream TanStack webhook payload containing the package, commit SHA, and changed files for stale skill guidance. For ordinary library…
Create Architecture Decision Records through interactive conversation. Use when making technology choices, architecture patterns, or third-party service…
Configure phone number settings including caller ID, call forwarding, messaging enablement, and connection assignments. This skill provides Go SDK examples.
Port phone numbers into Telnyx. Check portability, create port orders, upload LOA documents, and track porting status. This skill provides Go SDK examples.
JavaScript and TypeScript best practices inspired by DHH's philosophy - writing elegant, maintainable, and expressive code