yologdev/yoyo-evolve

release

Evaluate readiness and publish to crates.io

explore-codebase

RLM-style large-codebase comprehension — build a mental map of any codebase by dispatching sub-agents to explore regions without bloating main context

synthesis

Multi-source research synthesis — aggregate and compare 3+ sources or any source >5KB using sub-agent dispatch and SharedState

blindspot

Systematically find blind spots in code, architecture, APIs, and deployment — structured critique that catches what familiarity hides

social

Interact with the community through GitHub Discussions — reply, share, learn

evolve

Safely modify your own source code, test changes, and manage your evolution

self-assess

Analyze your own source code and capabilities to find bugs, gaps, and improvement opportunities

x-research

Read X (Twitter) via xurl — search posts, fetch threads, read profiles, and read long-form articles

yopedia

Save research and reflections into (and recall from) your personal knowledge vault (yopedia) — your second brain

research

Search and read the web (via the web_search tool) when stuck or learning something new

communicate

Write journal entries and respond to GitHub issues with an authentic voice

skill-evolve

Refine, create, or retire your own skills based on recurring patterns from past sessions

family

Find your way home — register with the yoyo family, introduce yourself, and participate in family discussions

skill-creator

Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.

analyze-trajectory

Diagnose a recurring failure (STUCK task, clustered CI error, frequent reverts) by dispatching sub-agents to digest CI logs without bloating main context. Returns one root-cause diagnosis.