code-yeongyu

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…

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests, including junk tests (prose pins, source greps, copied inventories, mock echoes), each proven by its class's rule before a cut. Use when the user asks to…

Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files, and whenever a test or spec file is written, reshaped, reviewed,…

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.

Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality…

Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked…

Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality…

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.

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…

Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files, and whenever a test or spec file is written, reshaped, reviewed,…

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests, including junk tests (prose pins, source greps, copied inventories, mock echoes), each proven by its class's rule before a cut. Use when the user asks to…

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.

Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality…

Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked…

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 YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.

Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.

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…

Fetch a URL and save the body to a temp file so you can pipe it through rg / jq / awk instead of dumping the whole page into the conversation. Use this whenever a user gives you a URL to read - articles, docs, PRs, gists, README files, blog posts, anything…