code-yeongyu/oh-my-openagent

这个仓库里有 62 个技能，GitHub 星标 ★ 69,100。

• codex-qaQA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in stric
• get-unpublished-changesCompare HEAD with the latest published npm versions and list all unpublished cha
• github-triageRead-only GitHub triage for issues AND PRs. 1 item = 1 background task (category
• hyperplanAdversarial multi-agent planning skill. Self-orchestrates 5 hostile category mem
• omomomoEaster egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.
• opencode-qaQA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve,
• pre-publish-reviewNuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes t
• publishPublish oh-my-opencode to npm by triggering the GitHub Actions publish workflow
• remove-deadcodeRemove unused code from this project with ultrawork mode, LSP-verified safety, a
• security-researchTeam Mode security research skill. Orchestrates 3 vulnerability hunters and 2 Po
• senpi-qaQA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the R
• tech-debt-auditThorough, file-cited technical debt audit across 9 dimensions using AST-grep (tr
• work-with-prFull PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop
• github-triageRead-only GitHub triage for issues AND PRs. 1 item = 1 background task (category
• hyperplanAdversarial multi-agent planning skill. Self-orchestrates 5 hostile category mem
• pre-publish-reviewNuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes t
• work-with-prFull PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop
• comment-checkerUse when Codex needs to understand or respond to automatic comment-checker feedb
• lcx-contribute-bug-fixContribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Co
• lcx-doctorDiagnose LazyCodex and Codex CLI installation health against the latest sources.
• lcx-report-bugCreate a high-signal bug issue or PR in the repo that owns the defect. Use this
• lspUse when Codex needs language-server diagnostics, definitions, references, symbo
• rulesUse when the user asks about Codex Rules behavior, injected project rules, suppo
• teammodeCodex-only team orchestration: run a named team of cooperating Codex workers wit
• ulw-planACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user t
• ulw-loopA goal-like loop that decomposes work into systematic, evidence-bound ultrawork
• init-deepInitializes a hierarchical AGENTS.md knowledge base for a project. Use when a re
• ulw-planACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user t
• init-deepInitializes a hierarchical AGENTS.md knowledge base for a project. Use when a re
• onboardingGuides a first-time omo user through setup and the core workflow. Use when a new
• dag-libraryStores a DAG definition once and re-runs it by name, instead of pasting the defi
• give-me-tipsExplains any senpi tip in depth, including Tip: lines in the TUI. Use when the u
• hyperplanAdversarial multi-agent planning: a hostile team cross-critiques a plan before i
• init-deepInitializes a hierarchical AGENTS.md knowledge base for a project. Use when a re
• mass-ulwDrives dependency-ordered child work through the native workflow tool, one run p
• onboardingGuides a first-time omo user through setup and the core workflow. Use when a new
• ultraworkThe binding ultrawork-mode directive. This file IS the directive; read it only w
• ulw-loopA goal-like loop that decomposes work into systematic, evidence-bound ultrawork
• ulw-planExplore-first planning consultant that writes one decision-complete work plan be
• ulw-researchRuns maximum-saturation research with a cooperating team, claim-graph gating, an
• x-searchMUST read before searching X/Twitter with the x_search tool. When xAI is connect
• ast-grepSearches and rewrites code by AST shape across 25 languages. Use when the target
• coding-agent-sessionsFinds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenC
• data-scientistProcesses and analyzes data with resident-kernel engines (DuckDB, Polars) and on
• debuggingRuns a hypothesis-driven debugging loop across any language or binary, escalatin
• frontendBuilds, styles, and polishes web UI and UX. Use for any frontend, page, componen
• git-masterHandles git work: atomic commits, rebase, squash, blame, bisect, reflog, and his
• init-deepInitializes a hierarchical AGENTS.md knowledge base for a project. Use when a re
• lsp-setupConfigures a language server so editor/agent tooling (diagnostics, go-to-definit
• programmingApplies strict, modern language practice (typed errors, exhaustive match, TDD) f
• refactorGuides a refactor, cleanup, or restructure with the right decomposition. Use whe
• remove-ai-slopsRemoves AI-generated code smells from branch changes or an explicit file list be
• review-workPost-implementation gate review: run manual QA on the real surface yourself, the
• ultimate-browsingRenders, drives, and screenshots web pages: JS-rendered sources, clicks and form
• ulw-executeExecutes a written ulw-plan work plan with Boulder state, evidence ledger, workt
• ulw-planExplore-first planning consultant that writes one decision-complete work plan be
• ulw-researchRuns maximum-saturation research with a cooperating team, claim-graph gating, an
• visual-qaRuns rigorous visual QA across web, terminal, and paginated surfaces with screen
• dev-browserBrowser automation with persistent page state. Use when users ask to navigate we
• frontendBuilds, styles, and polishes web UI and UX. Use for any frontend, page, componen
• git-masterMUST USE for ANY git operations. Atomic commits, rebase/squash, history search (
• security-research