prompting
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,653 results
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive…
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…
Build an AI agent that lives in Pachca as a bot: called by @mention in a chat or thread or messaged in a DM, it reads the thread for context, shows the…
Designs an MCP server's tool/resource/prompt surface - outcome-oriented consolidation, tool budget, naming, descriptions-as-prompts, flat typed schemas,…
Records a session's open work as append-only events in the session-memory store, and renders the watchable view. Use when a session's progress must be visible…
Coordinate multiple terminal coding agents through the Superset CLI by creating isolated workspaces, launching workers, sending follow-ups, reading terminal…
Question the user about important system design decisions, then prepare the decided design for a specification. Use when a design needs a focused interview…
Write prompts and choose settings for Claude Fable 5. Use when the user asks about Fable prompts, reasoning effort, long-running goals, worktrees, workflows,…
Report active Codex and Claude Code sessions in the current repository by default, with optional machine-wide detail.
Compare agent guidance, workflows, and dependencies across repositories, then adopt the practices each recipient would benefit from.
This skill should be used ONLY when the user asks to update README.md, CLAUDE.md, AGENTS.md, or CONTRIBUTING.md. Trigger phrases include "update README",…
Sets up Agentic Marketing Suite module in a project. Use when the user requests to 'install ams module', 'configure Agentic Marketing Suite', or 'setup Agentic…
Orchestrate parallel sub-tasks by spawning non-interactive instances of your own CLI as subagents. Use when you need to parallelize work across multiple files,…
Knowledge management skill based on the Karpathy LLM Wiki pattern. Supports both code projects and Obsidian notes. Reads Raw Sources (code/documents) to build and maintain an accumulating knowledge base in docs/wiki/. "wiki", "wiki", "ingest", "ingest", "wiki check",…
Break down reference videos or original video prompts according to user goals, extract the timeline, shots, camera positions, camera movement, composition, actions, transitions, subtitles, sound, and visual elements, then generate finished prompts that are general or adapted to a specified video model. Used for tasks such as "break down this reference video", "analyze by shot", "reverse-engineer prompts from a video", "rewrite content while keeping the camera movement", "only change the characters' clothing and products", and "recreate based on the structure of a viral hit"; supports breakdown only, writing prompts after breakdown, selectively preserv...
Use only when the user explicitly invokes $chatgpt-pro-reasoner to send a focused thinking problem to ChatGPT Pro through the Codex in-app browser. Treat…
Use when repository behaviour, routing, counts, validation, or release procedures change and README, AGENTS, CLAUDE, CONTRIBUTING, or focused docs must be…
Creates new AI agent skills following the Agent Skills spec.
Design and implement agentic product flows using the contract: model decides what to do, tools decide how it is done, UI schema decides how it is rendered. Use…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
Replace with description of the skill and when Claude should use it.
Use this skill when authoring Ping Identity specific plugin skills for this repository. Plugin skills are those in `./plugins/**/skills/`. Covers structure,…
Integrate LLMs into applications - APIs, prompting, fine-tuning, and context management