self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-26 00:15
Agents & models
24,842 results
unit-executor
Execute exactly one eligible Unit in an existing research Workspace; use for stepwise or manual semantic execution when status, Attempt, Artifact, Manifest,…
crd-respond
For cross-project CRD recipients: evaluate requirements and long-term options, reply or continue clarification; originators use crd to draft and consolidate replies, not Kubernetes CRD or direct implementation. Reply at the end of the original text based on the latest code; use dev-plan when code changes are needed.
search-intent-coverage
Build a standalone search-intent analysis or content outline from localized SERP evidence or competitor pages. Use when the user wants to understand and plan…
agent-style
Literature-backed English technical-prose writing rules. Use when writing or editing prose in .md, .tex, .rst, or .txt files, especially research papers,…
zerion-agent-management
Manage Zerion agent tokens and security policies — the primitives for autonomous trading and signing. Create / list / use / revoke agent tokens; create / list…
zerion-trading
Execute on-chain trading actions via the Zerion CLI: swap, bridge, and send tokens across 14 EVM chains and Solana. Use whenever the user asks to swap / trade…
brainstorming
Must be used before any creative work—creating features, building components, adding functionality, or modifying behavior. Explore user intent, requirements, and design before implementation.
browser-use
AI-driven intelligent browser automation tool. Uses LLM to understand pages and automatically execute tasks, smarter and more token-efficient than traditional Playwright. Suitable for complex interactions, dynamic pages, and browser operations that require intelligent decision-making. Chrome browser preferred.
curator-skill
Atlas.skill — cross-author persona skill smart router that lives in your IDE. When users need it across the entire persona skill ecosystem (Huashu nuwa / titanwings colleague / various individual…
servicenow-agent-skills
Expert-level agent skills for the entire ServiceNow development ecosystem. Covers Fluent SDK metadata (.now.ts), legacy scripting (GlideRecord, Script…
orchestrator
Central entry point of the afonsoft agent harness. Use when starting a new project, resuming an existing one, planning features/Epics/releases, or running any…
agently-agent-extensions
Use when the user wants tool use, MCP access, HTTP or streaming API exposure, auto-function helpers, wait-for-key behavior, or optional `agently-devtools`…
agently-langchain-to-agently
Use when a migration is already known to stay on the LangChain agent side, including agent setup, tools, structured output, retrieval, and short-term memory.
agently-langgraph-to-triggerflow
Use when a migration is already known to stay on the LangGraph orchestration side, including stages, routing, checkpoints, interrupts, persistence, streaming,…
agently-output-control
Use when the user wants stable structured fields, required keys, reliable machine-readable sections, or downstream-consumable output from one model request,…
creating-claude-rules
Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like…
using-agent-relay
Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent…
soup
Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO,…
azure-storage
Manage Azure Blob Storage, Data Lake, and storage account operations.
langchain
Framework for building applications with large language models and chains.
mcporter
MCP server management: install, configure, bridge external tools, protocol handling
session-mesh
Session topology: discover alive sessions, specialization registry, steer/kill sub-agents, session keys
pymol
Control PyMOL molecular visualization through Claude Code. Use when asked to "visualize protein", "render structure", "show cartoon", "color by chain", "ray…