Prompts
Prompt engineering and templates
pocketflow
by nickth3man
PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows
Notion Template Processor
by ashleytower
Fills Notion database templates with data and delivers via email using Notion MCP integration
plugin-authoring
by alavida-ai
Reference skill for Claude Code plugin and hook authoring. Covers plugin.json schema, all 15 hook events, exit code semantics, matchers, environment variables, caching behavior, and proven Agonda patterns. Use when designing hooks, scaffolding plugins, validating hook configuration, or debugging hook behavior. Not a workflow — a knowledge base that other skills reference.
programmatic-claude
by WebSmartTeam
Run Claude Code programmatically via CLI (-p flag), Python SDK, or TypeScript SDK. For automation, CI/CD, session chaining, headless execution, and orchestrating multiple Claude instances. Triggers: programmatic, headless, CLI automation, session chaining, -p flag, Python SDK, orchestrate Claude, CI/CD Claude, run Claude automatically.
Visual Asset Workflow Skill
by NaveedTechLab
Result: Professional-quality visuals that teach effectively, generated efficiently through planning, with zero duplicates requiring rework.
chatgpt-app-builder
by mcp-use
Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT apps, building MCP servers with widgets, defining React widgets, working with Apps SDK, or when user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development.
daily-meeting-update
by cachemoney
"Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update."
moru-python
by moru-ai
"Use this skill when writing Python code that interacts with Moru cloud sandboxes. This includes: creating sandboxes with Sandbox.create(), running commands with sbx.commands.run(), reading and writing files with sbx.files.read() and sbx.files.write(), working with persistent volumes using the Volume class, building custom templates with the Template builder, handling background processes, streaming command output, and async operations with AsyncSandbox. The skill covers the complete Python SDK API including error handling with TimeoutException, CommandExitException, AuthenticationException, and other exceptions from moru.exceptions. Use this skill whenever users want to: execute code safely in isolated environments, build AI agents that run untrusted code, create data processing pipelines, run web scrapers, set up development environments, or any Python automation involving Moru sandboxes. Triggers on: 'moru python', 'from moru import', 'Sandbox.create', 'pip install moru', 'moru sdk python', 'python sandbox', 'AsyncSandbox', 'Volume.create', 'Template.build', or any Python code that needs to run in isolated cloud environments. Do NOT use this skill for JavaScript/TypeScript code - use moru-javascript instead."
operating-claude
by Git-Fg
"Operational manual for driving the Claude runtime. Use when needing to optimize context usage, troubleshoot performance, or understand runtime mechanics. Do not use for architectural definitions or building plugins."
keyword-based-llm-eval
by shimo4228
"Use when evaluating LLM-generated structured output against expected results using keyword matching and F1 metrics."
LLM Auto-Switch System
by taiyousan15
```
openai-gpt-converter
by bluewaves-creations
Convert Agent Skills to Custom GPT format. Use when the user wants to adapt, port, or transform a Claude skill (SKILL.md-based) into an OpenAI Custom GPT, or when discussing GPT constraints like the 8000-character instruction limit, knowledge file limits, Code Interpreter, Actions, and platform differences between Claude Skills and Custom GPTs.
create-prompt
by dwizi
Expertise in designing high-quality prompt templates for MCP servers using dzx conventions. Use when the user asks to "create a prompt", "add a prompt template", or "design a prompt" for a dzx MCP server.
agent-md-refactor
by fefogarcia
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
canonical-format-checker
by NaveedTechLab
This skill should be used when content teaches patterns (skills, subagents, ADRs, PHRs, specifications) that have canonical sources elsewhere. Prevents format drift by ensuring content references and follows the authoritative format from canonical sources. Use before implementing lessons that teach platform patterns, or when reviewing content for format consistency.
claude-md-bp-context
by getskillsdev
Audit CLAUDE.md for best practices. 18-point checklist.
code-standards
by qiaoshouqing
"Setup universal code quality standards in your project. Use when the user wants to generate coding standards files (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) or mentions 'code standards', 'code review setup', or similar intent in any language."
refine
by meetdave3
Audit, score, and improve any project's Claude Code configuration. Analyzes CLAUDE.md, skills, agents, hooks, MCP servers, and settings. Trigger: /refine, /refine audit, /refine quick
parallel-subagent-batch-merge
by shimo4228
"Use when generating 50+ structured items with parallel Claude Code subagents and merging outputs into one file."
skill-creator
by watzon
Use when creating new skills, updating existing skills, or understanding skill structure. Triggers: "create a skill", "write a skill", "new skill for", "skill that does", "how do skills work". Provides complete workflow from concept to deployment with progressive disclosure.
cc-front-compaction
by choru-k
Prepare manual front-only compaction for Claude Code by compacting oldest N% with hard tail replay default. Use only when user explicitly asks for /cc-front-compaction.
permission-management
by cuioss
Permission validation, architecture patterns, anti-patterns, and best practices for Claude Code settings management
conversation-history-setup
by dhughes
Guide users through initial setup of conversation history indexing. Use when user asks about setting up conversation history, indexing past conversations, or when search returns no results and the database may be empty.
skill-building
by WebSmartTeam
Create effective Claude Code skills and agents. Covers official frontmatter spec, global vs project scope, and the formula - references activate dormant knowledge, pet hates stop bad defaults, post-training fills gaps. Triggers: create skill, build skill, write skill, make agent, skill template, how to write skills.