0
Verify before claiming done (Superpowers)SkillLow risk
Requires Claude to run real checks and show evidence before saying work is finished.
discuss1 use
Reusable AI prompts, coding-agent files, skills and MCP servers
0
Git worktrees for isolation (Superpowers)SkillLow risk
Sets up an isolated git worktree with a clean, passing baseline before feature work starts.
discuss1 use
0
CommandVault MCP serverMCP serverRead-only
Search CommandVault's prompts, CLAUDE.md templates, Cursor rules, skills and MCP servers from your editor.
discuss1 use
0
Subagent-driven development (Superpowers)Skill
Executes a plan by sending each task to a fresh subagent, with a review after every step.
discuss1 use
0
Systematic debugging (Superpowers)Skill
A four-phase process that finds the root cause of a bug before any fix is attempted.
discuss1 use
0
Test-driven development (Superpowers)Skill
Enforces red-green-refactor: write a failing test first, then the minimal code to pass it.
discuss1 use
0
Writing implementation plans (Superpowers)SkillLow risk
Converts a spec into a step-by-step implementation plan with small, testable tasks.
discuss1 use
0
Brainstorming before building (Superpowers)Skill
Turns a rough idea into an agreed design through focused questions before any code is written.
discuss2 uses
0
Claude API reference (Anthropic)Skill
Up-to-date guidance for building apps on the Claude API and Anthropic SDKs.
discuss2 uses
0
Doc co-authoring workflow (Anthropic)SkillLow risk
A structured workflow for writing specs, proposals and decision docs together with Claude.
discuss1 use
0
Canvas design (Anthropic)Skill
Create original posters and static art as PNG or PDF, guided by a design philosophy.
discuss1 use
0
Web artifacts builder (Anthropic)Skill
Build multi-component React + Tailwind + shadcn/ui apps bundled into a single HTML file.
discuss1 use
0
Web app testing with Playwright (Anthropic)Skill
Drive a local web app in a real browser to test flows, grab screenshots and read logs.
discuss1 use
0
Frontend design (Anthropic)Skill
Push UI work past generic defaults toward a distinctive, deliberate visual design.
discuss1 use
0
MCP server builder (Anthropic)Skill
Build well-designed MCP servers in Python or TypeScript that wrap an external API.
discuss1 use
0
Skill creator (Anthropic)Skill
Design, test and tune your own Agent Skills, including evals and description tuning.
discuss1 use
0
Excel spreadsheets (Anthropic)Skill
Create, clean and analyze Excel and CSV files with working formulas and formatting.
discuss1 use
0
PowerPoint decks (Anthropic)Skill
Build, edit and QA PowerPoint presentations, from pitch decks to template updates.
discuss1 use
0
Word documents (Anthropic)Skill
Create and edit Word .docx files with real formatting, tracked changes and comments.
discuss1 use
0
PDF toolkit (Anthropic)Skill
Read, create, merge, split, fill and OCR PDF files from inside Claude.
discuss1 use
0
Claude Code subagent: refactorerTemplateLow risk Tested
A .claude/agents/refactorer.md that simplifies code without changing behavior.
discuss1 use
0
Safety rules block for coding agentsSnippet
A 'never do' section for CLAUDE.md / AGENTS.md that prevents the expensive mistakes.
0
Claude Code subagent: security auditorTemplate Tested
A .claude/agents/security-auditor.md that checks changes for the vulnerabilities attackers try first.
discuss1 use
0
Claude Code subagent: docs writerTemplateLow risk
A .claude/agents/docs-writer.md that keeps README and docs in sync with the code.
0
Definition of done block for agent context filesSnippetLow risk
Paste into CLAUDE.md or AGENTS.md so agents stop declaring victory before the work is verified.