GitHub collection

evalstate/fast-agent

Imported from GitHub — is this yours?

2 skills imported from this repository.

View on GitHub
3921 446 Apache-2.0
Claude Skill

pr-writing-review

Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparin

LLM Mart

Claude Skill

session-investigator

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON

LLM Mart

Agents (9)

Claude Agent

environments

Run shell and filesystem tools in local, Docker, Hugging Face, or custom environments.

Claude Agent

index

Attach files, MCP resources, and prompt files directly to agent conversations.

Claude Agent

instructions

Shape agent behavior with reusable instructions and prompt files.

Claude Agent

plugins

Add slash commands and post-turn displays to fast-agent.

Claude Agent

prompting

Send structured prompts, files, and resource content to agents.

Claude Agent

running

Run agents locally, from scripts, or as reusable command-line workflows.

Claude Agent

tool_runner

Expose tools through a focused agent for safe, direct tool execution.

Claude Agent

workflows

Compose agents into orchestrated workflows with routing, chaining,

Claude Agent

researcher

Research a topic using Hugging Face Inference Providers.

Commands (1)

  • /README — This directory contains the command implementations for the fast-agent CLI. source