Hacker.
YeonGyu-Kim publishes skills that help an agent search and rewrite code by syntax structure across 25 languages with ast-grep, audit codebases for technical debt and security exploitability, and file well-evidenced bug reports against Codex tooling. Their collection also covers multi-agent orchestration, including saved DAG graphs that can be re-run by name and checkpointed goal loops for durable execution.
Oh My Openagent
54 skills · 70,745 stars · NOASSERTION
Browser Drives a real browser through the omowright library from the js eval kernel: sites the user is al…
Codex Qa QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ON…
Coding Agent Sessions Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, a…
Comment Checker Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after…
Dag Library Stores a DAG definition once and re-runs it by name, instead of pasting the definition into every…
Data Scientist Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools.
Debugging Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal o…
Dev Browser Browser automation with persistent page state.
Frontend Builds, styles, and polishes web UI and UX.
Get Unpublished Changes Compare HEAD with the latest published npm versions and list all unpublished changes by release l…
Git Master MUST USE for ANY git operations.
Git Master Handles git work: atomic commits, rebase, squash, blame, bisect, reflog, and history questions.
Github Triage Read-only GitHub triage for issues AND PRs.
Give Me Tips Explains any senpi tip in depth, including Tip: lines in the TUI.
Hyperplan Adversarial multi-agent planning: a hostile team cross-critiques a plan before it is formalized.
Hyperplan Adversarial multi-agent planning skill.
Init Deep Initializes a hierarchical AGENTS.md knowledge base for a project.
Init Deep Initializes a hierarchical AGENTS.md knowledge base for a project.
Lcx Contribute Bug Fix Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or up…
Lcx Doctor Diagnose LazyCodex and Codex CLI installation health against the latest sources.
Lcx Report Bug Create a high-signal bug issue or PR in the repo that owns the defect.
Lsp Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename saf…
Lsp Setup Configures a language server so editor/agent tooling (diagnostics, go-to-definition, references,…
Mass Ulw Drives dependency-ordered child work through the native workflow tool, each phase's stages define…
Omomomo Easter egg command - about oh-my-opencode.
Onboarding Guides a first-time omo user through setup and the core workflow.
Opencode Qa QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a…
Pre Publish Review Nuclear-grade 12-agent pre-publish release gate.
Programming Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) fo…
Publish Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its…
Refactor Guides a refactor, cleanup, or restructure with the right decomposition.
Remove Ai Slops Removes AI-generated code smells from branch changes or an explicit file list behind regression t…
Remove Deadcode Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
Review Work Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate…
Rules Use when the user asks about Codex Rules behavior, injected project rules, supported rule file lo…
Search and rewrite code by syntax structure with ast-grep Find and bulk-refactor code by its structure across 25 languages, not by text.
Security Research Team Mode security research skill.
Security Research Runs a parallel, exploitability-driven security audit of a repository, diff, PR, or release candidat
Senpi Qa QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary…
Teammode Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script…
Tech Debt Audit Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep,…
Ultimate Browsing Reaches web pages the user's browser cannot open: WAF-blocked and bot-scored hosts, platform-nati…
Ultrawork The binding ultrawork-mode directive.
Ulw Execute Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, a…
Ulw Loop A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps.
Ulw Loop A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps.
Ulw Plan Explore-first planning consultant that writes one decision-complete work plan before coding.
Ulw Plan ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying…