ワンクリックで
omo
omo には speson から収集した 22 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Review the current diff, run the narrowest useful verification, and summarize remaining release risk. Activate when #sc appears anywhere in the user message.
Show unified omo status dashboard — boulder, ralph-loop, tasks, teams, and memory state at a glance. Activate when #ss appears anywhere in the user message.
Check if README.md and user guide reflect current project state — philosophy, features, agent models, skill list. Fix any drift. Activate when #sync appears anywhere in the user message.
Full release pipeline — commit, push, tag, GitHub release, marketplace version sync. Activate when #rel appears anywhere in the user message.
Triage a failure by capturing symptoms, narrowing reproduction, isolating likely files, and choosing the smallest useful verification loop. Activate when #bh appears anywhere in the user message.
Multi-perspective code review on the current diff or specified files. Examines correctness, security, performance, maintainability, and scope creep. Activate when #dr appears anywhere in the user message.
Dispatch multiple agents in parallel for independent tasks. Use when work splits cleanly into non-overlapping units that can execute simultaneously. Activate when #sp appears anywhere in the user message.
Orchestrate large Claude Code tasks with planning, todo discipline, subagent delegation, parallel execution, and targeted verification. Does not stop until the task is done or explicitly blocked. Activate when #ulw appears anywhere in the user message.
Validate omo plugin integrity — structure, frontmatter, script permissions, version consistency. Activate when #st appears anywhere in the user message.
Auto-detect and configure omo prerequisites — Stop hook registration, MCP settings, statusline configuration. Activate when #sw appears anywhere in the user message.
Write a structured handoff note and refresh current task state so work can resume cleanly later. Activate when #ho appears anywhere in the user message.
System-enforced development loop with optional Oracle verification. Stop hook blocks agent from stopping until task is complete and verified. Use for tasks that must reach 100% completion. Activate when #rl appears anywhere in the user message.
Recover session context quickly from the current repo state, pending changes, and recent commands. Use when the user says continue, resume, or asks what was in progress. Activate when #rw appears anywhere in the user message.
Dependency security audit — run ecosystem-specific audit tools and cross-verify new or updated dependencies. Activate when #da appears anywhere in the user message.
Initialize or refresh a task note with interview-mode scoping. Questions ambiguities before planning. Defines execution and verification strategy. Activate when #kit appears anywhere in the user message.
Orchestrate framework, API, or language version migration — analyze impact, plan changes, execute in slices, verify each step. Activate when #mg appears anywhere in the user message.
Performance impact analysis — detect O(n²) patterns, large bundle risks, unbounded data structures, and expensive operations in recent changes. Activate when #pc appears anywhere in the user message.
Comprehensive GitHub PR review — diff analysis, CI status check, multi-perspective code review, and actionable feedback. Activate when #pr appears anywhere in the user message.
Retrospective analysis after ultrawork or ralph-loop sessions — agent usage patterns, bottlenecks, and improvement suggestions. Activate when #re appears anywhere in the user message.
Multi-strategy parallel search across the codebase. Combines symbol search, text patterns, file structure, imports, and git history for comprehensive results. Activate when #ds appears anywhere in the user message.
Automated test-fix-retest cycle. Runs tests, fixes failures, and re-runs until all pass or a maximum retry count is reached. Activate when #qa appears anywhere in the user message.
Build or refresh a concise repository map with deep scanning. Supports init-deep mode for generating hierarchical AGENTS.md files throughout the project. Activate when #rr appears anywhere in the user message.