Prompts
Prompt engineering and templates
scaffold-rules
by plaited
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
moru
by moru-ai
"Use this skill for Moru cloud sandbox concepts, CLI commands, and general guidance. Moru provides isolated Firecracker microVMs with dedicated CPU, memory, and filesystem for safe code execution. This skill covers: installing the Moru CLI, authenticating with moru auth login, creating sandboxes with moru sandbox create, running commands with moru sandbox run, managing templates with moru template, working with persistent volumes via moru volume, and understanding core concepts like sandboxes, templates, and volumes. Use this skill when users ask about Moru architecture, CLI usage, environment variables (MORU_API_KEY, MORU_ACCESS_TOKEN), resource limits, or when unsure which SDK to use. For writing Python code with sandboxes, use moru-python instead. For JavaScript/TypeScript code, use moru-javascript instead. Triggers on: 'moru cli', 'moru sandbox', 'moru template', 'moru volume', 'moru auth', 'install moru', 'what is moru', 'moru concepts'."
skill-generator
by zacdcook
Meta-skill for creating and maintaining project context skills in Claude Code. Use when user says "create a skill", "update the skill", "save this context", "remember this", or at session end when significant project knowledge was established. Enables zero context loss between chat sessions.
forge-audit-skill
by fwehrling
FORGE Skill Auditor — Security audit of third-party Claude Code skills. Usage: /forge-audit-skill <path-to-skill>
gemini-cli
by X-Zero-L
Ask Gemini via the local gemini CLI (no MCP). Use when the user says "ask gemini" / "use gemini", wants a second opinion, needs large-context @path analysis, sandbox runs, or structured change-mode edits.
cost-aware-llm-pipeline
by shimo4228
"Use when building an LLM-powered app that needs cost control via model routing, budget tracking, retry, and prompt caching."
bootstrap-repo
by velcrafting
Bootstrap or refresh a repo scaffold (governance docs, .codex folder, Tree.txt). Use only when explicitly invoked.
safe-gcloud-usage
by dhughes
This skill should be used when the user asks to "run a gcloud command", "use gcloud", "access Google Cloud", "list GCP projects", "check gcloud config", or any task involving the Google Cloud CLI. Also use when Claude needs to suggest patterns for the gcloud allowlist or explain why a gcloud command was blocked. Use this skill immediately when you see "Direct gcloud commands are blocked" or "Use the safe-gcloud wrapper instead" in an error message.
flipswitch-toggle
by flipswitch-io
Enables or disables a feature flag in a specific environment. Use when changing a flag's state, turning on a feature for testing, or disabling a flag in production.
claude-api
by diskd-ai
Anthropic Claude API integration for building AI-powered applications. Use when working with Anthropic's Messages API, Claude SDKs (Python or TypeScript), tool use/function calling, vision/image inputs, streaming responses, prompt caching, message batches, token counting, extended thinking, PDF processing, or any Claude API integration task.
mentor-guided-learning
by guanyu-gerry-tao
"Project-level mentor bootstrap and run skill. Use when the user invokes $mentor-guided-learning: detect first-time use vs ongoing learning. On first-time use, set up all learning system files (.LEARNING, learner profile, project-root AGENTS.md/GEMINI.md/CLAUDE.md, .gitignore). On ongoing learning, read the synchronized runtime rules files and .LEARNING and continue. Also use this skill when the user asks to update profile settings."
bench-new-skill
by elliottrjacobs
Create new skills for the bench-skills repo following all conventions. Use when the user says "create a new skill", "add a skill", "new slash command", or wants to extend bench-skills with additional capabilities.
context-loader
by tjade273
Synchronizes startup context across Claude instances, runs at launch.
pptx
by unicorn-plugins
"Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill."
architecting-prompts
by Git-Fg
"Applies 2026 Complexity-Based Guidance standards with Attention Management, Sycophancy Prevention, and XML/Markdown decision matrix. Provides theory, patterns, and quality evaluation criteria for AI prompt design. Use when designing, optimizing, or auditing AI prompts, system instructions, or multi-stage chains. Do not use for generating prompt files, basic conversational AI, or single-step interactions."
update-context
by kavantrudie
"Capture conversation context AND git changes to create comprehensive markdown documentation. Analyzes both discussed reasoning and actual code changes (via git diff) for accurate, meaningful documentation of features, bugs, architecture, and refactors."
frontend-developer
by RasmusGodske
Skill for implementing frontend features following project conventions. Use when writing Vue components, creating UI, or refactoring frontend code. Loads all frontend rules from .claude/rules/frontend/.
prompt-clarifier
by physics91
WHEN: Ambiguous prompts, vague requirements, missing context, unclear instructions WHAT: Ambiguity detection + AskUserQuestion clarification + Interactive option selection WHEN NOT: Clear detailed instructions → proceed directly
backend-developer
by RasmusGodske
Skill for PHP/Laravel backend development following project conventions. Use when creating or editing PHP code, models, services, controllers, tests, or any backend logic. Loads all backend rules from .claude/rules/backend/ and .claude/rules/dataclasses/.
@anthropic-ai/sdk
by yusenthebot
The official TypeScript library for the Anthropic API. Use when: bundling and transpiling source code; development server with HMR; production builds. NOT for: runtime application logic; package management (use npm/yarn).
skill-creator
by naohainezha
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
agentsmd-claudemd-generator
by MounirDhahri
Generate AGENTS.md and CLAUDE.md files for a repository. AGENTS.md provides cross-tool agent instructions (supported by Claude Code, Cursor, Windsurf, Zed, Codex, and others). CLAUDE.md adds Claude-specific configuration and references AGENTS.md via @import. Use when a repo needs agent onboarding or when starting a new project.
update-agent
by blueif16
修改现有的agent
emergency-engineer
by pierreribeiro
Emergency Engineer persona for critical production issues. ACTIVATE when messages contain emergency, production, down, critical, urgent, fix, broken, outage, or disaster keywords.