code-yeongyu

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 or a deep investigation, including any 'ulw' research wording.

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 or a deep investigation, including any 'ulw' research wording.

A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.

Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.

Drives dependency-ordered child work through the native workflow tool, each phase's stages defined up front in one run, with retry/amend/send recovery. Use when the user asks for mass-ulw, a DAG of tasks, or fan-out work where some tasks must wait on others.

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 openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR —…

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 conversation.

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 create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on…

Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own…

Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.

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 or a deep investigation, including any 'ulw' research wording.

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 create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on…

Binding ultrawork mode directive for omo on Codex. When a prompt contains ultrawork or ulw, the omo UserPromptSubmit hook injects a short bootstrap that points at this file. Read the whole file and follow every rule in it for the rest of the task.

A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.

Reaches web pages the user's browser cannot open: WAF-blocked and bot-scored hosts, platform-native readers (Chinese and social platforms), archive snapshots with provenance, and a browser you own for stealth or throwaway profiles. Not for plain search, an…

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 make an interface look or feel a certain way.

Create YAML format work plans saved as .sisyphus/tasks/{name}.yaml with strict schema validation. Analyze user requirements, gather project context, and generate structured plans with verification specs. ALWAYS includes mandatory plan-reviewer verification.…

Specialized GitHub PR intelligence agent for automatically gathering comprehensive context from Pull Requests. Activate when users need CI failure analysis, review comment investigation, or PR status assessment. Triggers on requests like "CI 실패 원인 찾아줘",…

Commits changes in atomic units following dependency order. Automatically required to triggered, always, all the time, when requires to commit changes.

GitHub Pull Request creation specialist. Analyzes user requirements to create PRs with structured titles and bodies matching the user's query language. Handles git change analysis, PR draft creation, user confirmation, and final PR creation via gh CLI.

Activate when user expresses intent to start Sisyphus work (e.g., "okay then work like that", "let's execute this", "start working on this"). Extract ai-todolist.md content from GitHub comments/files, create branch, commit, and trigger GitHub Actions…

Patterns for controlling interactive debuggers (pdb, ipdb, gdb, lldb, node debug) via terminalcp

Patterns for managing and monitoring long-running processes (builds, tests, servers, etc.) via terminalcp

Patterns for controlling REPL sessions (Python, IPython, Node.js, Ruby, etc.) via terminalcp

Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple files, call in PARALLEL per file.

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses,…

Designer-turned-developer who crafts stunning UI/UX even without design mockups

(builtin) Initialize hierarchical AGENTS.md knowledge base

Strategic planning consultant that produces decision-complete work plans through Socratic interview, codebase exploration, Metis gap analysis, and optional Momus high-accuracy review. MUST USE when the task has 5+ steps, scope is ambiguous, multiple modules…

MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc /…

Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and `npm test` are NOT QA. Drives the real CLI from source in an isolated sandbox (never…

Read before a js eval cell that installs a package, spawns a server or PTY, or starts a long run, and before any bun -e, script, server, CLI, test, bundle, or package-management work: this session's eval js kernel runs Bun 1.4+ (this skill is present only…

Example skill loaded from resources_discover

MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native image_generation server tool vs the generate_image tool), model and quality selection, prompt structure, exact text rendering, reference-image editing,…

Release, publish, CalVer tag push, npm publish, 배포, 릴리즈 for senpi. Use for the canonical release flow, GitHub tag/release publication, and npm publishing.

Implements a single feature in the pi-mono `todotools` builtin extension work. Use for refactoring, continuation runtime, config resolver, prompt builder, test authoring, golden snapshots, CHANGELOG entries, and harness helpers. Does NOT do manual tmux QA.

Sync a fork branch with an upstream remote using a history-preserving merge. Use this whenever the user says /merge-upstream, merge upstream, sync upstream, sync fork, or wants upstream changes integrated without rebasing or force-pushing.

Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa…

The default code-driven browser path for interactive browsing work: drives any browser from code with token-efficient a11y snapshots (57% smaller via compactSnapshot), ref-based clicks, coordinate control (CUA), viewport pinning, CAPTCHA solving (reCAPTCHA,…

Interact with challenge widgets in an authorized automation flow using checkbox clicks, slider drags, text OCR, and image-grid input. Verify completion with an application-specific condition.

Push browser tab and download lifecycle events plus manager-owned background tabs. Read this when an agent needs lifecycle notifications or a temporary tab without polling.

Read this when you need Chrome MV3-shaped APIs — bookmarks, tabs, windows, history, downloads, or top sites — in standalone OmOWright.

Use when a user-driven CloakBrowser profile needs MV3 Chrome writes/events through the native messaging bridge.

Read the network instead of the DOM. Snoop JSON API responses, wait for a request instead of sleeping, collect items while scrolling, record a QA flight trace (jsonl, HAR, screenshots), and intercept requests with routes.

Coordinate-level browser control for UI that snapshots, refs, and locators cannot target - canvas apps, extension popups, OS-drawn dialogs, custom drag surfaces. Read this when a DOM-targeted action fails twice, when the next decision depends on rendered…

Drive the user's host machine directly through Cua, with no sandbox. Maps to Cua's Localhost API. Higher risk - the agent can click, type, and run shell commands on the real desktop. Use only when the user explicitly opts in and read the safety section first.…

Mouse, keyboard, and scroll primitives for cua_click / cua_type / cua_key / cua_scroll. Reference for action shapes, modifier keys, key chord syntax, and screenshot-driven targeting workflows.

pi-cua-integration is a Pi/Senpi extension that bridges Cua (trycua/cua) for computer-use sandboxes and host control. MUST USE when the user asks to drive a desktop UI, take screenshots, run a "computer use" task, control a sandbox, or invoke any cua_* tool.…

Use Cua's cloud sandboxes via cua.ai. Requires CUA_API_KEY. Cloud sandboxes are isolated VMs run by trycua with billing per usage. Use when the user wants no local Docker/QEMU, wants Windows/macOS guests without Apple Silicon, or explicitly asks for cloud.

Run Cua sandboxes locally - no API key required. Covers Docker (XFCE/Kasm) for Linux containers, QEMU for full VMs, Lume for macOS guests on Apple Silicon, and Tart for Apple VZ VMs. Use when the user wants a local sandbox, wants to keep things off the cloud,…

Convert and share Claude Code conversation sessions as readable markdown files. Use when user wants to share a session transcript, export conversation history, or create a shareable markdown document from a Claude Code session. Triggered by requests like…

GitHub Pull Request creation specialist. Analyzes user requirements to create PRs with structured titles and bodies matching the user's query language. Handles git change analysis, PR draft creation, user confirmation, and final PR creation via gh CLI.

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 goal.

MUST USE when the user needs current, online, or web-derived information — news, latest releases, vendor docs, real-world examples, recent changes, or anything not in the model's training set. LLM-neutral skill that exposes a unified web search CLI behind a…

Use ast-grep (sg) for AST-aware code search and rewrite across 25 languages. Trigger for structural code matching or deterministic codemods: find every function/call/class/import shaped like X, rewrite console.log to logger.info, strip `as any`, migrate…

MUST USE whenever the user wants to automate a real desktop or sandbox - clicking, typing, scrolling, screenshotting, running an OS shell command, or handing a high-level 'open browser and do X' task to an autonomous computer-use agent. Wraps the trycua/cua…