iterate
Builder/critic iterative improvement loop (evaluator-optimizer pattern) for any reviewable deliverable — code, documents, designs, research. The session…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,710 results
agency
An AI automation agency that runs inside Claude Code: an outbound agent that writes personalized cold emails to a list of businesses, a sales agent that preps…
umodel-query
Read from a UModel object-graph semantic layer with the `umctl` CLI (MCP alternative noted). Three kinds of read: (1) entities & relationships / topology…
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks,…
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies…
agent-id
Use the Alien Agent ID system on any agent harness — verifiable agent identity (Ed25519, L0/L1/L2 assurance), an encrypted credential vault (passkey/Touch ID,…
agent-id-browser
Drive Alien Browser with an anonymous L0 profile created automatically for public pages, or a logged-in profile sealed in the agent vault. Inspect forms…
agent-id-proxy
Local credential-injecting HTTP proxy. The agent calls `http://localhost:PORT/<credname>/<upstream-host>/<path>`; the proxy looks up the credential in the…
release
Drive the changesets-based release flow for the agent-id npm packages. Use when the user wants to release packages, cut a version, declare a release intent,…
grade-iterate
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader),…
session-handoff
Write a handoff document so a fresh session or another agent can pick up exactly where this one left off: goal, current state, decisions, next steps and the…
workflow
Use to run a dynamic, goal-driven workflow — orchestrate a multi-step goal by composing skills, tools, and MCPs, with a quality gate and verification at each…
alibabacloud-ebs-usage-summary
Analyze Alibaba Cloud block storage (EBS) disk performance and fleet composition. Use it to locate performance bottlenecks (saturated IOPS or bandwidth),…
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…
dispatching-parallel-agents
Use when there are multiple independent subtasks that can progress in parallel without overlapping ownership or blocking the next local step
allure-test-agent-setup
Add Allure test-agent guidance to a project by detecting the local Allure and test setup, adding short root agent entry-file routers such as AGENTS.md or…
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…
alpaca-trading-example
One-line trigger description for when an agent should load this skill.
technology-mapping
Fully automatic generation of a panoramic map of frontier technology fields. Suitable for technology-centric tracks (such as quantum computing, nuclear fusion, AI Agents, etc.), constructing a complete academic → open source → commercialization trajectory through bidirectional mining (forward tracking of academic origins + reverse tracing of unicorn founding teams). Trigger words: "technology mapping", "technology panorama", "technology map", "track map".
0xaa-binance-agentic-wallet
Use when the user mentions wallet connect/sign in/sign out, check balance, send/transfer tokens, swap/buy/sell tokens, DEX trade, limit/market order, cancel…
quark-onnx-ptq
End-to-end ONNX PTQ workflow for AMD Quark — for `.onnx` input models (with optional sibling `.onnx_data` external-weights file). Use when the user wants a…
quark-torch-install
Install or verify the correct PyTorch build for a user's accelerator backend before Quark installation. Trigger for "install PyTorch", "pip install torch",…
quark-torch-llm-ptq-eval
End-to-end Torch LLM PTQ recipe for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize, then validate, then evaluate…
tmux-agent-orchestrator
Govern interactive agentic harnesses running in tmux. Use when the user asks the primary agent to discover, launch, take over, resume, direct, monitor,…