Email, calendars, task management, and automation (7.9K skills)
Intelligent Git Flow branch creator that analyzes git status/diff and creates appropriate branches following the nvie Git Flow branching model. Use when starting a feature, release, or hotfix branch in a repository that follows Git Flow.
The English summary is being prepared. Showing the original description.
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation. Use when writing commit messages for a repository that follows Conventional Commits.
The English summary is being prepared. Showing the original description.
Builds a compact profile of a GitHub user or PR author — identity, activity, company, commit history, and trust signals. Use during pull request review or triage, especially for contributions from unfamiliar authors.
The English summary is being prepared. Showing the original description.
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
The English summary is being prepared. Showing the original description.
Generates a comprehensive .editorconfig from the project's structure and the user's preferences, so editors format files consistently across languages. Use when a repository has no .editorconfig or its formatting is inconsistent across editors.
The English summary is being prepared. Showing the original description.
Handles npm registry and account tasks: npm whoami, package availability, reserving names, publishing, org checks, and auth debugging, with 1Password and tmux for credentials. Use when publishing to npm or diagnosing npm login problems.
The English summary is being prepared. Showing the original description.
Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine. Use when someone shares a screen recording of a repetitive task they want automated.
The English summary is being prepared. Showing the original description.
Expert-level Windows batch file (.bat/.cmd) skill for writing, debugging, and maintaining CMD scripts. Use when asked to "create a batch file", "write a .bat script", "automate a Windows task", "CMD scripting", "batch automation", "scheduled task script", "Windows shell script", or when working with .bat/.cmd files in the workspace. Covers cmd.exe syntax, environment variables, control flow, string processing, error handling, and integration with system tools.
The English summary is being prepared. Showing the original description.
Debugs OpenAI Codex CLI and app behavior by navigating the codex-rs codebase (core, tui, exec, cli, app-server): config parsing, tool invocations, prompts, and MCP wiring. Use when Codex behaves unexpectedly or a Codex runtime bug needs tracing to source.
The English summary is being prepared. Showing the original description.
Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.
The English summary is being prepared. Showing the original description.
Automates the user's existing signed-in Chrome profile through Chrome DevTools MCP (via mcporter): inspecting pages, screenshots, forms, clicks, and running JavaScript, without AppleScript. Use when a task needs a real logged-in browser tab rather than a fresh headless one.
The English summary is being prepared. Showing the original description.
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger: /caveman-compress.
The English summary is being prepared. Showing the original description.
Interactive, input-tool powered, task refinement workflow: interrogates scope, deliverables, constraints before carrying out the task; Requires the Joyride extension. Use before carrying out a vague or high-stakes task in VS Code with Joyride available.
The English summary is being prepared. Showing the original description.
Use when a task feels too large or vague to start, a spec needs breaking into implementable units, work must be parallelized across agents or sessions, or implementation order is unclear. Produces ordered tasks with acceptance criteria. Skip when the spec already contains well-defined tasks.
The English summary is being prepared. Showing the original description.
Use on every code change — commit structure, branching, history hygiene, and versioning. Apply when committing work, opening or splitting a branch, writing commit messages, cutting a release, or recovering from a bad history state.
The English summary is being prepared. Showing the original description.
Use when setting up a project's CI pipeline, adding or changing automated checks, configuring deployment pipelines, or debugging CI failures. Covers quality gates, pipeline stages, and what to verify automatically on every change.
The English summary is being prepared. Showing the original description.
Refine an existing skill in place with minimal diffs. Trigger when asked to improve a skill's trigger description/frontmatter, workflow text, metadata, scripts/references/assets; also for requests to iterate, refactor, rename, or fix a skill using usage/session-mining evidence (for example from /tw-seq).
The English summary is being prepared. Showing the original description.
Run a targeted fresh-eyes blunder pass over code, specs, plans, reviews, closure gates, or skill edits. Use when asked to reread with fresh eyes, find obvious bugs, catch mistakes/oversights/omissions, check for embarrassing misses, or do a second independent pass before closure. Use it as the final falsification/check pass for another workflow, not as a substitute for implementation or verification.
The English summary is being prepared. Showing the original description.
Boss delegates tasks to workers, reviews their output, and approves or requests changes.
The English summary is being prepared. Showing the original description.
Coordinate material messages between explicitly selected desktop-backed agents, including Claude, Codex and bb. Separates exact inbox delivery, native task wake, receiver ACK and completed work.
The English summary is being prepared. Showing the original description.
Run an explicitly authorized overnight collaboration with one desktop portal, a durable CLI writer and independent CLI review. Use for unattended work, not routine short tasks.
The English summary is being prepared. Showing the original description.
Agents work in parallel on the same task; judges evaluate and select the winner.
The English summary is being prepared. Showing the original description.
Author and diagnose YAML, prototype schemas, workflows, manifests, and structured configuration with exact validation.
The English summary is being prepared. Showing the original description.
Preserve user work, scope, metadata, history, and verifiable delivery.
The English summary is being prepared. Showing the original description.