Use when an LLM needs to respect a brand it has never seen — or when a deliverable came back off-brand, colors were guessed, or a font was invented. Also when a brand identity lives only in a PDF manual, a website, or someone's head, and needs to become rules a model can check itself against. Triggers on: "design.md"…
Scan all date columns in Excel and convert datetime values to user-specified text format (yyyymmdd, yyyy-mm-dd, yyyy/mm/dd, yyyy年mm月dd日, or any custom combination). Supports three output positions: insert new column on left, insert new column on right, or replace original column. New column headers can be customized…
Generate, update, and automate think-cell charts and elements in PowerPoint and Excel. Use ANY time the user mentions think-cell, thinkcell, or .ppttc files, or asks to create/update PowerPoint charts following think-cell conventions (waterfall, Mekko, stacked column, Gantt, Harvey ball, scatter/bubble, etc.) …
Query self-hosted OpenPanel analytics — funnel counts, unique users, breakdowns by os/country/path, raw events. Use whenever analytics numbers are needed: funnel conversion, visitor counts, event counts over a window, period-over-period deltas, "how many signups/checkouts/sessions", or any /darkflow:analytics-review…
Use when building, debugging, testing, or shipping an ATAK (Android Team Awareness Kit) plugin - scaffolding from the SDK template, getting it to actually load on a device, running instrumented tests inside ATAK, and preparing a submission to TAK's third-party signing pipeline. Triggers on ATAK plugin work, "plugin…
Generate, review, and improve Moodle quiz questions. Supports GIFT format (compact, 6x fewer tokens) and Moodle XML format (full features with syntax highlighting). Four modes: create (easy/standard/challenging difficulty), review (improve existing MCQs). Handles MCQ, true/false, short answer, matching, numerical, and…
A tool for processing complete book files such as PDFs, EPUBs, MOBI files, DOCX files, and text files. It can produce Chinese translations, detailed reading notes, Obsidian reading vaults, or notes about themes across chapters.
Build a presentation that performs — a self-contained HTML keynote with big type, timed reveals, sound design, and a "one more thing" finale, plus a built-in methodology for what to say. Use when the user wants a talk, keynote, pitch, or conference deck that should feel like an experience, not a document — or wants to…
Use when the user wants to create, set up, or open a Godot project with AI assistance, install the Godot-MCP addon, or connect Godot to ai-game.dev. Covers project creation, plugin install, login, and opening the editor via godot-cli.
Look outside before deciding: search the live web, registries and primary sources at decision time and bring back a report the caller picks from. Use for any question that may have an answer outside this repo — choosing a library or tool ("which one is mainstream now"), prior implementations of a design problem ("is…
Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks) that splits agent context into small per-topic files loaded on demand (progressive disclosure). Use this WHENEVER the…
The llama-swap operations console — durable history, drain-aware control, and measurement commands with three specific guarantees: keep-set unloads are refused statically by id AND alias (never from server ttl), --drain fails closed when slot state is unreadable, and fit/ctx refuse to answer inside their uncertainty…
Render LaTeX math so the user can actually see it. CLI agents do not typeset $...$ or $$...$$. Use when writing or explaining formulas, equations, derivations, integrals, matrices, or when the user mentions LaTeX, KaTeX, or showing math. Run mathshow; do not leave raw TeX as the only view.
Review a research paper, proposal, or technical writeup by spawning five constructive reviewer archetypes — the Steelman-Builder, Assumption Auditor, Mechanism Seeker, Generous Skeptic, and Contextualizer — each of whom reads critically and curiously and writes a focused review, then synthesizes them into a…
The master design engineering skill encoding Emil Kowalski's polish philosophy, Apple's fluid interface principles, Anime.js 3D/timeline motion, Motion spring physics, Kokonut UI component aesthetics, and Backlit UI dark-mode charts. Use when designing, animating, or reviewing web UIs to achieve high-precision craft…
Claude-native multi-model routing — dispatch each task to the right Claude model tier (Fable judgment · Opus orchestrate/review + hard build · Sonnet build · Haiku volume) via model-pinned subagents. Use when routing a Claude task by model or reasoning effort, consulting the advisor at a commitment boundary, or…
Drive and verify a running Bevy game through bevy-agent-feedback-plugin using semantic readiness, deterministic time, and completion-confirmed PNG captures.
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
Reverse-infer OpenSpec specs from this repo's code + git history + local docs (and Jira/Confluence/URLs if available via MCP or host WebFetch). Triggered by /inferspec-scan.
Audit a repository or prepare it for an open-source release. Audit mode reports whether the README matches the code and whether stated rules are actually enforced; launch mode walks a repo to release-ready with opt-in checklist packs and README templates. Use when asked to "audit this repo," "is this repo ready to go…
Create or upgrade an agent skill with SkillsCake. Use when the user wants to improve a skill using SkillsCake, create a skill based on a completed workflow, or says "use SkillsCake".
A set of rules for how Lume learns lasting preferences and keeps its workspace and conversation files organized. Lume is the application whose configuration and memory it manages.
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: