musingfox
33 verified skills66 total stars
Discord Webhook
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.
development2
gog Drive
This skill should be used when the user asks to "list files on Drive", "search Drive", "upload file to Drive", "download from Drive", "export Google Doc", "share a file", "move file", "rename file", "create folder on Drive", "delete file from Drive", "check file permissions", "copy file on Drive", "get file link", or mentions Google Drive operations. Provides guidance for using the `gog drive` CLI to interact with Google Drive.
tools2
hook-guard-update
This skill should be used when the user asks to "update hooks", "refresh hook configuration", "sync hooks with current tools", "upgrade hooks", "hook-guard update", "regenerate hooks", "update pre-commit", "update Claude Code hooks", or wants to update their existing hook-guard setup after adding new tools, changing languages, or wanting the latest check implementations.
tools2
doc-render
Render markdown content or files as formatted HTML in the browser. Triggers when user asks to view, render, or preview a document as HTML, or when presenting lengthy structured content (tables, diagrams, plans) that would be more readable as a web page than terminal output. Also triggers proactively when about to render a table with 4+ rows or 3+ columns, structured comparisons, audits, or any output exceeding 50 lines of formatted content in the terminal.
development2
viz-router
Routes collaborative document editing to the optimal method based on the user's environment. Activated when the user wants to EDIT content (not just view it), or when Claude wants the user to review and modify a draft. Checks terminal type and available tools to choose between browser editor, terminal split editor, or fallback.
tools2
init
Interactively create .obsidian.yaml for a project and install starter templates (task / doc / adr) into the vault's Templates folder. Skips templates that already exist; never overwrites.
documentation2
note
Create long-form notes in an Obsidian vault at a configured default folder with a chosen filename strategy. Delegates vault I/O to the Obsidian CLI.
tools2
hook-guard
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.
tools2
adr
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.
testing2
adr-ref-guard
Quick advisory scan of markdown files for stale references to superseded/deprecated ADRs. Lightweight check — use the adr skill for full consistency audits.
testing2
Apple Podcasts Fetch
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.
development2
git-to-jj
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.
testing2
gog Calendar
This skill should be used when the user asks to "check my calendar", "show my agenda", "schedule a meeting", "create an event", "list events", "what's on my calendar", "today's schedule", "find free time", "check conflicts", "RSVP to event", "delete event", "update event", "set focus time", "block time", "set out of office", "search calendar", or mentions Google Calendar operations. Provides guidance for using the `gog calendar` CLI to interact with Google Calendar.
tools2
gog Gmail
This skill should be used when the user asks to "check email", "search email", "send email", "read mail", "find emails from", "reply to email", "forward email", "list labels", "create a draft", "send a draft", "download attachment", "manage email labels", "archive email", "delete email", or mentions Gmail, inbox, or email management operations. Provides guidance for using the `gog gmail` CLI to interact with Gmail.
tools2
readable-text-formatting
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.
development2
playwright
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).
development2
jj-workflow
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.
testing2
contract-validation
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.
development2
pm
Project management via Obsidian vault — tasks, documents, ADRs, and dashboards scoped to a `.obsidian.yaml`-bound project. Owns folder layout and property schema; delegates all vault I/O to the Obsidian CLI.
tools2
cap
Quick-capture short entries to today's daily note in an Obsidian vault. Composes a timestamped bullet and delegates the append to the Obsidian CLI's `daily:append`.
tools2
fizzy
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.
tools2
agent-browser
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).
tools2
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).
development2
gog
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.
tools2
MarkItDown Read
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.
tools2
jot
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:cap` and `/obw:note`. Requires `.obsidian.yaml`.
data-ai2
obsidian-pm
This skill should be used when the user mentions tasks, project documents, ADRs, architecture decisions, or project management in the context of development work. Covers creating, listing, updating, completing, and archiving tasks. Also handles writing design docs, specs, and ADR lifecycle (propose, accept, deprecate, supersede). Common triggers: "create a task", "list my tasks", "what am I working on", "write a design doc", "create an ADR", "show project status", "what's in my backlog", "mark task as done", "record this decision", "archive completed tasks", "task priorities", "show dashboard", "專案狀況", "project status", "cross-project status", "跨專案". All operations use the Obsidian CLI against a configured vault.
tools2
hook-guard-doctor
This skill should be used when the user asks to "check hooks", "diagnose hook issues", "verify hook setup", "run hook doctor", "hook health check", "troubleshoot hooks", "are my hooks working", "hook-guard doctor", "check pre-commit status", or wants to verify that their hook configuration is correct and complete. Inspects hook files, permissions, tool availability, and configuration integrity.
tools2
hook-guard-setup
This skill should be used when the user asks to "set up hooks", "configure pre-commit", "add linting hooks", "set up code quality checks", "initialize hook-guard", "add pre-commit hooks", "set up git hooks", "configure Claude Code hooks", "add security checks to commits", "set up conventional commits", "hook-guard setup", "hook guard setup", "add commit checks", "protect my commits", "configure git hooks for this repo", "I need a pre-commit hook", "help me set up code quality automation", or mentions setting up commit hooks, pre-commit scripts, or code quality gates. Detects project language/toolchain and generates Claude Code hooks, git pre-commit scripts, and CLAUDECODE skip logic.
tools2
collab-edit
Collaborate with the user by opening a shared markdown file in their terminal editor. Triggers when asking the user to review/edit content, or when user requests collaborative editing. Detects completion signals in both English and Traditional Chinese.
content-media2
mermaid-display
Display Mermaid diagrams as interactive HTML pages. Activated when the user asks to visualize, diagram, chart, or draw system architecture, data flows, process workflows, sequence diagrams, class diagrams, state machines, ER diagrams, or any relationships better shown graphically. Renders as HTML by default; PNG/SVG only when explicitly requested.
development2
mermaid-theme
Activated when the user asks to set, change, or configure Mermaid diagram colors or themes, mentions theme names like Tokyo Night, Nord, Catppuccin, Dracula, GitHub, or Solarized, or asks about available color schemes for diagrams.
testing2
viz-render
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.
development2