cc-plugins

Interactively create `.obsidian.yaml` and install starter templates (task / doc / adr) for this project. Triggers via `/obw:init` or when another obw skill reports missing config.

Unified entry point for Obsidian daily-note captures and long-form notes. Triggers on "記一下 / log / 紀錄 / capture this / 寫到 journal" (→ cap mode) and "建立筆記 / new note / 寫一份筆記 / create a note on" (→ note mode). Also via `/obw:jot`. Requires `.obsidian.yaml`.

Obsidian Workspace PM — tasks, documents, and ADRs in your Obsidian vault. Triggers on task/doc/ADR lifecycle requests ("add a task", "create an ADR", "archive X", "list in-progress tasks", "refresh dashboard") and via `/obw:pm`. Requires `.obsidian.yaml` with a `pm.project` section.

Render markdown or Mermaid content as formatted HTML in the browser. Triggers when the user asks to view, render, or preview a document as HTML; when the user asks to visualize, diagram, chart, or draw architecture, flows, sequence/class/state/ER diagrams; when resolving plan files from ~/.claude/plans/; or proactively when about to output a table with 4+ rows or 3+ columns, a structured comparison, an audit, a feature matrix, or any formatted content exceeding ~50 lines in the terminal.

Offload dispatch to cheap/fast omp models via pi-agent.sh — name-addressed sub-agent verbs (start/send/poll/peek/ls/stop/watch) over background omp workers with idempotent poll, worktree isolation, and distilled reports. Main loads this to write the offload usage it embeds in a builder brief.

Use for live browser automation via the agent-browser CLI — open URLs, snapshot pages, click/fill/screenshot, inspect elements, scrape or read web pages. Ref-based workflow for AI agents. Not for writing Playwright test files (use playwright or web-test).

Use to write or set up Playwright / @playwright/test E2E tests — test specs, locators, assertions, fixtures, config. Focuses on structuring tests with high-precision locator strategies. Not for live page exploration or debugging (use agent-browser or web-test).

Use to debug a live web page and convert findings into Playwright regression tests — investigate UI bugs, fix flaky tests, generate E2E tests from exploration. Orchestrates the debug-to-test workflow. Not for writing standalone tests with no exploration (use playwright).

Use the Fizzy CLI for project management — boards, cards, columns, comments, steps, tags, notifications, pins, webhooks, account. Triggers on any Fizzy task/card/board action or fizzy.do URL.

Use when reading, summarizing, or extracting from non-plain-text files — PDF, Office docs (Word/Excel/PowerPoint), images, audio, HTML, EPUB, archives, and structured data (CSV/JSON/XML). Converts via the markitdown CLI.

Use the `gog` CLI to operate Google Workspace — Gmail (read/search/send/labels/drafts), Calendar (events/RSVP/freebusy/focus-time/out-of-office), and Drive (list/search/upload/ download/share/move). Triggers on any Gmail, inbox, email, calendar, agenda, meeting, schedule, RSVP, Drive, Google Doc/Sheet/Slides, file share, or upload/download request.

Quick advisory scan of markdown files for stale references to superseded/deprecated ADRs. Lightweight check — use the adr skill for full consistency audits.

Create, list, supersede, deprecate, or audit Architecture Decision Records (MADR 4.0). Handles auto-numbering, directory detection, and cross-reference consistency. For quick stale-reference scans in markdown, use adr-ref-guard instead.

Manage project hook-guard installation — set up, diagnose, or update Claude Code hooks, git pre-commit, and commit-msg scripts with security checks, code-quality gates, and CLAUDECODE skip logic. Triggers on "set up hooks", "configure pre-commit", "add linting hooks", "initialize hook-guard", "check hooks", "hook doctor", "verify hook setup", "troubleshoot hooks", "update hooks", "regenerate hooks", "sync hooks with current tools", or similar requests.

This skill should be used when the user is in a Jujutsu (jj) repository and uses Git-specific terminology — such as "commit", "branch", "checkout", "stash", "cherry-pick", "rebase -i", "reset", "push", "pull", "merge", "add", "stage", "log", "diff", "amend", "revert", "tag", "fetch", or "clone". Focuses on explaining conceptual differences between Git and jj, not just command mapping. Translates Git mental models into correct jj equivalents. Do NOT use when the user is already using jj terminology correctly — use jj-workflow instead. Detects .jj directory presence combined with git vocabulary.

This skill should be used when the user asks to "send a Discord notification", "notify Discord", "post to Discord", "send a message to Discord webhook", "alert Discord channel", or when another agent, hook, or skill needs to deliver a notification to a Discord channel via webhook. Provides the complete workflow for reading webhook configuration, formatting messages (plain text or Embed), and sending via HTTP POST.

This skill should be used when the user is in a Jujutsu (jj) repository and describes VCS operations using jj terminology or neutral language — such as splitting a change, squashing changes together, rebasing, creating new changes, editing past changes, setting bookmarks, resolving conflicts, duplicating changes, backing out changes, or managing workspaces. Assumes the user is already thinking in jj terms. Do NOT use when the user uses Git-specific vocabulary (commit, branch, checkout, stash) — use git-to-jj instead for translation. Detects .jj directory presence to confirm jj context.

This skill should be used when the user asks to "validate agent contracts", "check contract compliance", "verify agent input/output", "pre-flight check", "debug agent failure", "why did the agent fail", or "check workflow state". Also triggered during OMT workflow when an agent starts or finishes execution. Validates input/output contracts for OMT agents using the Contract-First pattern.

This skill should be used whenever generating markdown tables, ASCII art, text-based diagrams, box-drawing layouts, or any formatted text intended for raw monospace reading. Applies automatically — no user trigger needed. Ensures column alignment, border consistency, and proper padding.

This skill should be used when the user asks to "download an Apple Podcast episode", "get podcast audio from Apple Podcasts", "fetch podcast MP3", "extract audio URL from Apple Podcasts link", provides an Apple Podcasts URL (podcasts.apple.com), or mentions downloading or extracting audio from Apple Podcasts. Provides the complete iTunes API + RSS feed workflow to resolve episode audio download URLs without a browser.