Loading the repository README…
Showing 40 of 40 collected skills.
Runs the portable QRSPI workflow (Question, Research, Structure, Plan, Implement), including Design, Worktree, and PR phases. Use when the user asks for QRSPI, names a /qrspi/ command, or requests its neutral-question research and staged design workflow. Not…
Operate Google Colab environments via the `colab` CLI. Use when asked to create or manage GPU/TPU sessions, run Python/shell on a remote Colab VM, sync files, automate environment setup (packages, auth, Drive), or export session history.
Manage TaskNotes tasks in Obsidian through maintained TaskNotes interfaces or a safe Markdown fallback. Use when the user wants to create, list, search, update, complete, archive, or delete tasks, or asks what they should work on.
Best practices for creating clear, well-structured Mermaid diagrams to visualize hierarchies, file structures, and component relationships.
Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot…
Router for all Remotion skills
Use this skill to get documentation for third-party APIs, SDKs or libraries before writing code that uses them to ensure you have the latest, most accurate documentation. This is a better way to find documentation than doing web search. This includes when a…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as…
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes…
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message",…
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite (default in the lefant bundle), full, ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use…
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
Write a marimo notebook in a Python file in the right format.
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
Rewrite prose (docs, READMEs, PR descriptions, error messages, release notes, comments, tool descriptions, system prompts — never code) into ASD-STE100 Simplified Technical English to remove "AI slop". Use when asked to make writing not sound like AI, make…
Access GitHub repositories programmatically using the exe.dev GitHub integration, gh CLI, or REST API. Use when interacting with GitHub repositories, issues, pull requests, workflows, discussions, or actions. On exe.dev VMs, prefer the tokenless GitHub…
Use when browser automation needs a human checkpoint: the user wants to demonstrate a workflow once, watch and verify an agent-driven browser result before proceeding, log in or complete MFA/credential-sensitive steps manually, connect through VNC, or use…
Use this skill for any task that creates, modifies, inspects, or destroys cloud infrastructure or SaaS configuration, from one-off CLI operations to full multi-resource projects, across providers in the Pulumi ecosystem. A typical project spans many providers…
Use Exa for web search, code context lookup, and company or people research via the official SDK, direct API calls, or MCP. Use when setting up Exa in a coding-agent environment, testing EXA_API_KEY, configuring Exa MCP, or looking up current web information.
Use when creating, extracting, reviewing, or refactoring agent skills. Covers self-contained skill packaging, SKILL.md structure, trigger descriptions, progressive disclosure, gotchas, defaults, bundled scripts, eval design, and with-skill vs baseline…
Zero Framework Cognition Principles
Access WebUntis accounts and APIs for debugging, research, or automation. Use when the user wants to log into a WebUntis tenant, read inbox messages, fetch guardian/dependent timetables, inspect homework or exams, compare WebUntis library implementations, or…
Land a finished implementation cleanly by updating plans and issues, reviewing specs and ADRs, writing session docs, creating changelog fragments when appropriate, and preparing handover context.
Resolve git merge conflicts by inspecting both sides, consulting recent local project context, applying safe resolutions, and completing the merge when the resolution is clear.
Gather pull request review feedback and combine it with recent local project context so reviewer comments can be addressed efficiently.
Generate a concise handover prompt for the next session, ensuring current work context is persisted and the next task is clear.
Summarize recent local project context by reading recently changed documentation from git history. Use when the user asks for recent context from git or wants a compact status summary from local docs.
Migrate from nix-shell to devenv or create new devenv projects. Use when users mention converting shell.nix/default.nix to devenv, setting up devenv environments, or need help with devenv configuration for languages (Python, Elm, Node, etc), services…
Fleet management for exe.dev VMs. Use when the user asks for system status, resource overview, fleet health, or VM inventory across exe.dev machines. Provides scripts for parallel probing of memory, disk, Docker, git repos, and process health.
Write implementation devlogs that capture current session progress, learnings, related artifacts, and next steps. Use when the user asks for a devlog or WIP devlog.
Create and manage Architecture Decision Records (ADRs) to document significant architectural choices and their rationale.
Create and manage changelog fragments to track changes without merge conflicts. Each change gets its own file for parallel development.
Create and manage feature specifications that capture WHAT a feature does and WHY, without prescribing HOW to implement it.
Preserve the RPI workflow commands create_plan, implement_plan, and research_codebase inside a portable skill. Use when the user refers to those exact command names, asks for RPI workflows, or wants the original Claude command behavior preserved as closely as…
Build working mini-app proofs before implementing features. Use when starting non-trivial features, exploring unfamiliar APIs, validating architectural approaches, or when uncertainty exists that code can resolve faster than planning. Triggers on "proof…
Audit documentation for quality issues including outdated information, broken references, contradictions, and inconsistencies. Use when asked to review docs, check documentation health, find stale content, validate cross-references, detect contradictions…
Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.
Analyze test failures from CTRF reports using jq for deterministic parsing
Fetch YouTube video transcripts using uvx and youtube-transcript-api
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/lefant/agent-skills.The repository README could not be loaded. You can still explore its Skills below.