@skills · Owner
Agent skills by code-yeongyu
101 skills indexed from github.com/code-yeongyu. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- .agents · Collection · 67,387 stars
- .opencode · Collection · 67,387 stars
- agent-browser · Skill · 67,387 stars
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with
- ast-grep · Skill · 67,387 stars
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a Y
- builtin-skills · Collection · 67,387 stars
- codex-qa · Skill · 67,387 stars
QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex
- coding-agent-sessions · Skill · 67,387 stars
Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or searc
- comment-checker · Skill · 67,387 stars
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
- comment-checker · Collection · 67,387 stars
- components · Collection · 67,387 stars
- data-scientist · Skill · 67,387 stars
Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation,
- debugging · Skill · 67,387 stars
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use
- dev-browser · Skill · 67,387 stars
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or a
- features · Collection · 67,387 stars
- frontend · Skill · 67,387 stars
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to mak
- frontend · Skill · 67,387 stars
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to mak
- get-unpublished-changes · Skill · 67,387 stars
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what chang
- git-master · Skill · 67,387 stars
MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with task(category='quick
- git-master · Skill · 67,387 stars
Handles git work: atomic commits, rebase, squash, blame, bisect, reflog, and history questions. Use whenever a task needs a commit or a git-history investi
- github-triage · Skill · 67,387 stars
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tm
- github-triage · Skill · 67,387 stars
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tm
- give-me-tips · Skill · 67,387 stars
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can se
- hyperplan · Skill · 67,387 stars
Adversarial multi-agent planning: a hostile team cross-critiques a plan before it is formalized. Use when planning needs maximum rigor or the user asks for
- hyperplan · Skill · 67,387 stars
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via te
- hyperplan · Skill · 67,387 stars
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via te
- init-deep · Skill · 67,387 stars
Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.
- init-deep · Skill · 67,387 stars
Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.
- init-deep · Skill · 67,387 stars
Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.
- lcx · Collection · 67,387 stars
- lcx-contribute-bug-fix · Skill · 67,387 stars
Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR only for upstream o
- lcx-doctor · Skill · 67,387 stars
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, l
- lcx-report-bug · Skill · 67,387 stars
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazyco
- lsp · Skill · 67,387 stars
Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.
- lsp · Collection · 67,387 stars
- lsp-setup · Skill · 67,387 stars
Configures a language server so editor/agent tooling (diagnostics, go-to-definition, references, rename) works. Use when a project needs an LSP installed o
- oh-my-opencode · Collection · 67,387 stars
- omo-codex · Collection · 67,387 stars
- omo-senpi · Collection · 67,387 stars
- omomomo · Skill · 67,387 stars
Easter egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.
- opencode-qa · Skill · 67,387 stars
QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event
- packages · Collection · 67,387 stars
- pi-goal · Skill · 67,387 stars
Persistent Codex-style goal tracking for pi. Use when the user explicitly asks to set, continue, audit, pause, resume, complete, or inspect a long-running
- plugin · Collection · 67,387 stars
- pre-publish-review · Skill · 67,387 stars
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain age
- pre-publish-review · Skill · 67,387 stars
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain age
- programming · Skill · 67,387 stars
Applies strict, modern language practice (typed errors, exhaustive match, TDD) for Python, Rust, TypeScript, and Go. Use for work on .py, .rs, .ts, or .go
- publish · Skill · 67,387 stars
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re
- refactor · Skill · 67,387 stars
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
- remove-ai-slops · Skill · 67,387 stars
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remov
- remove-deadcode · Skill · 67,387 stars
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unuse
- review-work · Skill · 67,387 stars
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code
- rules · Skill · 67,387 stars
Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.
- rules · Collection · 67,387 stars
- security-research · Skill · 67,387 stars
- security-research · Skill · 67,387 stars
Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploitability, classify
- shared-skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills · Collection · 67,387 stars
- skills-loader-core · Collection · 67,387 stars
- src · Collection · 67,387 stars
- teammode · Skill · 67,387 stars
Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to creat
- teammode · Collection · 67,387 stars
- tech-debt-audit · Skill · 67,387 stars
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECH_DEBT_AUDI
- ultimate-browsing · Skill · 67,387 stars
Reaches web pages a plain fetch cannot: renders JS, drives clicks and forms, captures screenshots, holds a login, and gets past WAF blocks through platform
- ultrawork · Skill · 67,387 stars
The binding ultrawork-mode directive. This file IS the directive; read it only when ultrawork mode is requested and the directive is not already in the con
- ultrawork · Collection · 67,387 stars
- ulw-loop · Skill · 67,387 stars
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed executi
- ulw-loop · Skill · 67,387 stars
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed executi
- ulw-loop · Collection · 67,387 stars
- ulw-plan · Skill · 67,387 stars
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their ow
- ulw-plan · Skill · 67,387 stars
Explore-first planning consultant that writes one decision-complete work plan before coding. Use only on an explicit user request for the ulw-plan workflow
- ulw-plan · Skill · 67,387 stars
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their ow
- ulw-plan · Skill · 67,387 stars
Explore-first planning consultant that writes one decision-complete work plan before coding. Use only on an explicit user request for the ulw-plan workflow
- ulw-research · Skill · 67,387 stars
Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research
- ulw-research · Skill · 67,387 stars
Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research
- visual-qa · Skill · 67,387 stars
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked
- work-with-pr · Skill · 67,387 stars
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English
- work-with-pr · Skill · 67,387 stars
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English
- components · Collection
- dag-library · Skill
Stores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved o
- init-deep · Skill
Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.
- mass-ulw · Skill
Drives dependency-ordered child work through the native workflow tool, one run per phase with retry/amend/send recovery. Use when the user asks for mass-ul
- onboarding · Skill
Guides a first-time omo user through setup and the core workflow. Use when a new user asks to get started with omo.
- onboarding · Skill
Guides a first-time omo user through setup and the core workflow. Use when a new user asks to get started with omo.
- plugin · Collection
- senpi-qa · Skill
QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one c
- skills · Collection
- src · Collection
- ulw-execute · Skill
Executes a written Prometheus work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execut
- x-search · Skill
MUST read before searching X/Twitter with the x_search tool. When xAI is connected: date-bound every time-sensitive query (from_date >= yesterday, widen to
- x-search · Collection