akashgit
UserDomain-agnostic multi-agent software design and evolution harness
Categories
Indexed Skills (6)
factory
Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation. Detects project state, spawns specialist agents, runs evals, and archives learnings.
pipeline-subagents
Design and execute a custom multi-agent pipeline using Claude Code subagents directly. Spawns researcher, builder, etc. via the Agent tool with native parallel and background execution. Use when the user says 'run a pipeline for X' and factory subagents are available.
pipeline
Design and execute a custom multi-agent pipeline for any goal. Analyzes the goal, selects appropriate specialist agents, designs a DAG of steps with dependencies, and executes them via factory CLI with gate decisions between steps. Use when the user says 'run a pipeline for X', 'orchestrate X', or wants a custom multi-agent workflow.
implement
Build a specific feature or improvement using Factory's multi-agent system. Runs the Factory CEO in focus mode to study the codebase, generate a hypothesis, build the change, review it, and evaluate the result. Use when the user says 'implement X', 'build X', 'add X feature', or wants autonomous multi-agent development on a specific task.
status
Show the current Factory status for this project, including project state, experiment history, eval scores, and active backlog. Use when the user asks about the factory status, project state, or experiment history.
study
Analyze the current codebase using Factory's observation engine. Generates a report covering code quality, eval scores, open issues, backlog items, observability coverage, and improvement opportunities. Use when the user wants to understand the state of their project before making changes.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.