lirrensi
17 verified skills51 total stars
edge-tts
Generate complete, production-ready TTS (Text-to-Speech) scripts and CLI tools using edge-tts — Microsoft's neural voice engine with 400+ natural-sounding voices. Use this skill whenever the user wants to speak text aloud from the terminal/PowerShell, list or search voices, select voices by name/language/gender, control rate/volume/pitch, save speech to MP3/audio files, or pipe text into a speak command. Trigger for ANY request involving TTS, speech synthesis, say command, speak function, voice output, edge-tts, or audio from scripts — even small snippets. Always check installation first and prefer uv tool install for setup.
tools4
essh
Portable SSH profile manager for agents. Run remote commands on saved hosts by friendly name instead of typing user@host -i key every time. Type less crap around your SSH commands.
data-ai4
task-system
Use this skill when you need to manage project tasks — create, update, complete, prioritize, filter, review, track dependencies, or find unblocked work. Trigger on: 'add a task', 'create task', 'show tasks', 'what's next', 'mark done', 'update task', 'task status', 'task history', 'next task', 'task inbox', 'list tasks', 'init tasks', 'task deps', 'ready tasks', 'blocked tasks', 'search tasks', 'tag-any', 'dependency graph'. Also use proactively when starting a new work session — check `tasks status` and `tasks ready` to orient yourself. This skill covers the project's static, file-based task system (persistent, in-repo history) with typed dependency tracking, ready queue, and priority management — NOT ephemeral runtime task tools.
tools4
tmux
Control tmux/psmux sessions for interactive CLIs, SSH connections, and parallel agent orchestration. Works cross-platform: tmux on Linux/macOS, psmux on Windows. Provides sync commands that send keys and automatically capture output. Triggers: "run in tmux", "create tmux session", "tmux", "SSH session", "parallel terminals", "run multiple agents".
tools4
engage
Autonomous execution mode triggered by the word "engage". Use when the user has finished planning and wants the agent to execute autonomously without further questions until the workflow is fully complete. The agent must build, test, verify, and deliver proof of work — never exiting with an incomplete or unverified result. Trigger on: "engage", "go autonomous", "execute the plan", "run it", "make it happen", or any explicit signal to switch from planning mode into fully autonomous build-and-verify mode.
development4
desktop-notifications
Send desktop notifications from the terminal. Use this skill when the user wants to display system notifications, pipe command output to notifications, or get alerts after long-running operations complete. Supports cross-platform (Windows Toast, macOS osascript, Linux notify-send).
tools3
memory-bank
Use this skill to save, recall, or organize memories across conversations. Trigger on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'do you remember', 'recall'. Also use proactively when the user seems to be resuming previous work, referencing past decisions, or when you discover something genuinely worth preserving for future sessions. This skill is NOT limited to code — use it for business decisions, personal notes, meeting recaps, research, project management, creative work, client history, anything.
tools3
crony
Manage cron jobs with natural language scheduling. Use this skill when the user wants to schedule tasks to run later or recurring, manage scheduled jobs, view job logs, or run jobs on-demand. Supports both one-off and recurring schedules with natural language syntax like "in 5m", "every 1h", "every monday".
tools3
bg-jobs
Run and manage background jobs from the terminal. Use this skill when the user wants to execute long-running commands in the background, track job status, read job output, or manage multiple concurrent processes. Provides friendly-name tracking, status monitoring, and output capture for background tasks.
tools3
batch-task-executor
Experimental workflow skill for coordinating many related tasks from any source. Use when the user asks to mass-process, batch-execute, fan out, parallelize, audit, review, summarize, migrate, or solve a list of tasks from a file, issue tracker, pasted list, directory, table, CSV, markdown checklist, Jira export, PR list, or direct instructions. The skill first determines how to read tasks and update their status/comments, then analyzes ordering, conflicts, blockers, and safe execution mode.
testing3
calm-down
Invoke this skill ONLY when you are actively making edits or executing a plan and the user shows clear frustration with the direction things are going: repeated swearing (3+ expletives in a message), phrases like "that's not what I wanted", "you did it again", "wrong", "stop", "undo that", "you don't understand", capitalization explosions (ALL CAPS bursts), or a general tone of mounting anger at what you are doing. DO NOT invoke this at the start of a conversation, during a discussion where no edits have been made, or when the user is frustrated about something unrelated to your current execution. DO NOT invoke for mild frustration or simple correction requests — only when you are clearly heading in the wrong direction and continuing will make things worse.
development3
skill-store
On-demand skill loading from a local skill registry. Trigger on: "skill store", "load skill", "find a skill", "list skills", "import skill", "skill-store", "browse skills", "search skills", or any request to fetch a skill that is NOT currently loaded in the active context. This skill is NOT for managing the already-loaded skills in your prompt. It is for accessing the much larger skill storage (~100s to 1000s) that you only bring into context when you need them. Think of it as a lazy loader: the skills here stay on disk until you explicitly call for them via CLI.
tools3
screenshot
Take screenshots from the terminal using the screenshot CLI tool. Use this skill when the user wants to capture the screen or a region, save screenshots to files, or integrate screenshot capture into scripts. Supports cross-platform (Windows/macOS/Linux) with automatic fallback to native tools.
tools3
best-practices-researcher
A meta-skill for researching current best practices and making technology decisions. Use when the user asks about best practices, coding standards, patterns, or needs to choose between technologies for ANY stack. Trigger on "best practices", "industry standard", "recommended way", "how do people usually do X", "is this the right way", "should I use X or Y", or "review my code against best practices". Also triggers when user pastes code and asks if it's correct or well-structured. No per-technology skills needed — this skill is self-contained for all stacks.
development2
micropatch
Use this skill when the user wants to capture, document, re-apply, or maintain customizations made to a forked upstream project as semantic MicroPatches. Trigger when the user wants to extract intentional fork changes, carry a feature forward onto a newer upstream release, sync a long-lived fork without relying on brittle merges, or document how a fork-specific feature should survive upstream updates.
testing2
document-extractor
Convert hard-to-read files into clear Markdown with MarkItDown. Use for PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, Outlook, and YouTube inputs. Check whether `markitdown` is installed first, prefer `uv tool install`, fall back to `pipx`, and use the upstream docs when needed.
tools2
nexi-search
NEXI provides four useful CLI surfaces - `nexi` for full agent answers with citations, `nexi-search` for direct search-provider results, `nexi-fetch` for direct page fetching, and `nexi-extract` for LLM-guided extraction. Use it when you need current information from the web or want a pipe-friendly search, fetch, and extract toolchain.
tools1