hook-creator
Guide for creating Claude Code plugin hooks — language selection heuristic (Node.js default, match project runtime when obvious), hooks.json configuration,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Agents & models
25,119 results
implementation-manager
Manages feature implementation task state via SAM MCP tools. Use when querying task status, listing ready tasks, dispatching tasks for execution, updating task…
mcp-integration
Integrate MCP servers into Claude Code plugins — covers .mcp.json configuration, plugin.json mcpServers field, server types (stdio, SSE, HTTP, WebSocket),…
orchestrator-discipline-meta-docs
Orchestrator discipline plugin documentation index. Load when needing to read about orchestration patterns, delegation rules, or context window management.
prompt-optimization
Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files.…
session-historian
Look up prior Claude Code sessions when context is lost or forgotten. Use when asked what was done before, what happened in the last session, or any request to…
skill-creator
Use when creating a new skill or updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.…
skill-research-process
Builds comprehensive Claude Code skills using parallel research agents — categorization, parallel documentation gathering, anti-hallucination checkpoints, and…
write-frontmatter-description
Write or tighten the description field of a skill or agent so the right one loads. Use when creating a skill or agent, when a description is vague, bloated, or…
cursor-custom-prompts
Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates. Triggers on "cursor prompts", "prompt…
cursor-model-selection
Configure and select AI models in Cursor for Chat, Composer, and Agent mode. Triggers on "cursor model", "cursor gpt", "cursor claude", "change cursor model",…
mistral-core-workflow-b
Build Mistral embeddings, retrieval, and function-calling loops with tenant isolation and application-owned execution. Use when adding RAG or tools. Trigger…
mistral-webhooks-events
Implement Mistral Workflows event ingestion over SSE with checkpoints, deduplication, reconnect control, and reconciliation. Use when consuming workflow event…
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or…
krypton-vps-codex-app
Set up, harden, audit, or explain a Linux VPS as a Codex App SSH host for Krypton-style agent workflows. Use when the user wants to move Codex or Claude Code…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
prompting-claude-models
Design prompts, system prompts, and agent scaffolding for LLM-backed features built on Claude models — LLM-as-judge and evaluation harnesses, RAG over…
plan-antislop
Plan-only authenticity / AI-slop audit across prose, UI, code, and IA. Use when "looks like AI slop", "reads like ChatGPT", or "authenticity burndown".…
orchestrate
Work the tracker's ready-for-agent tickets unattended — claim, build, and independently verify them a wave at a time, integrating each wave into the current…
save-note
File a valuable conversation synthesis into the Obsidian LLM Wiki so it can be retrieved and compounded later. Use for "save this to my notes", "add this to my…
scrum-master
Agent team role for Scrum Master facilitation, coaching, and servant leadership. Use when the user asks to facilitate scrum events, coach a team on…
launchdarkly-release-autopilot-settings
Configure LaunchDarkly Release Autopilot settings (GitHub App auto-flagging and auto-releasing) via the hosted MCP, or diagnose why a pull request was not…
agent-sdk
Guide for Claude Agent SDK - build custom AI agents powered by Claude. Covers installation, authentication providers, tool permissions, file-based…
threads
Use when the user explicitly asks for $threads, Codex-native subagents, open a few subagents, or a GitHub issue/PR queue needing parallel lanes, worktrees, review/merge…