Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Covers testing and benchmarking LLM agents through behavioral tests, capability assessments, and reliability metrics. Also addresses production monitoring to evaluate agent performance.
Evaluates agents through LLM regression testing, trajectory assessment, and judge rubrics. Measures quality, latency, token cost, and drift to verify behavior and compare changes against a baseline.
Hosts agents or workflows as streaming HTTP endpoints and consumes AG-UI servers through Python clients. Covers conversation continuity, thread-scoped state, rich tool payloads, and features such as human-in-the-loop interaction, generative UI, and predictive state updates.
Examines Agent Host diagnostic bundles supplied as ZIP files or folders. Supports events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, and copilot-logs.
Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.
Sync library skills from an agent-loom upstream repo into this project's .agents/skills while preserving project-local and forked skills. Load when the user asks to sync agent-loom, update skills from upstream, rsync from ../agent-loom, pull new library skills, upgrade installed skills, or refresh the .agents folder without losing custom project skills. Also triggers on "sync skills from agent-loo…
Continuous autonomous agent execution loop for open-ended, complex, or emergent multi-step tasks. Iterates through assessment, single tool execution, observation, and state updating until the task goal is fully resolved.
Manages multiple local CLI agents using tmux sessions. Supports starting, stopping, monitoring, and assigning agents, with scheduling suitable for cron.
Provides a hybrid memory system for persistent, searchable AI agent knowledge. Organizes knowledge such as architecture, patterns, and decisions.
Covers short-term context memory, long-term vector storage, and cognitive architectures for organizing agent memory. Emphasizes retrieval quality through chunking, embedding, and retrieval strategies.
Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent …
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name