Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Use when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality. Do not use for ordinary task execution when…
A design-production guide for creating high-fidelity visual work in HTML, including prototypes, slide decks, animations, mobile mockups, and visualisations.
A local knowledge-base search and question-answering assistant. It first navigates the directory structure, learns how to handle file types such as PDFs and spreadsheets, and then searches the relevant files.
A skill package for the openclaw-wx-echo project, covering a WeChat assistant, its triggers, prerequisites, architecture, and command-line scripts. WeChat is a messaging platform, and a command-line tool runs from a text-based terminal.
Use when building browser-based presentation slide decks, creating training presentations, generating React+Vite slide decks with animations, or making professional slides. Triggers on slide deck, presentation, training slides, Vite slides, Framer Motion slides, animated presentations.
Use when setting up a new or existing project on @drincs/pixi-vn, wiring the main.ts entry point, or calling the top-level Game API (Game.init, Game.start, Game.onEnd, Game.addOnError, Game.onNavigate, Game.clear) — this is the entry point every Pixi'VN project needs before touching canvas, narration, sound, storage…
Inspect video, audio, or supplied transcripts through raytsystem Tool Hub and return evidence-bound speech, visual, OCR, action, transition, and timeline findings. Use for /watch, a YouTube/Loom/public Zoom/direct media URL, a local video or audio file, a transcript, or requests such as "watch this video", "analyze…
Scaffold a student's own GTM repo and run the weekly build-in-public loop that turns a coding agent into a public go-to-market track record. Invoke on "student gtm", "set up my student workspace", "/student-gtm", "I'm a student and I want to break into GTM", "how do I get a GTM job with no experience", or when someone…
Retrieve login credentials, API keys, and secrets (username, password, TOTP) from the user's Bitwarden vault via aac. Use when you need credentials to sign into a website or service, or need an API key.
Memory consolidation skill for Claude Code. Scans session transcripts for corrections, decisions, preferences, and patterns, then merges findings into persistent memory files. Auto-triggers via native Stop hook every 24hrs. Inspired by how sleep consolidates human memory.
A Japanese-language editing workflow that rewrites text produced by AI so it reads more like ordinary human writing. It focuses on removing exaggerated wording, vague claims, and unnecessary loanwords.
The Socratic spec-refinement front of /feature, and the planning front of /sprint. Routed to BEFORE any code — it takes a one-line idea and drives it to an approved, concrete spec with testable acceptance criteria. Five gated phases — frame, shape, refine, write, review-and-approve. No implementation and no handoff to…
Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b [--base ].
Debug Android apps at the smali level with the avmdbg CLI — attach to debuggable processes over JDWP, set breakpoints at arbitrary dex offsets, and dump parameters, registers and stack traces as JSON. Use when reverse-engineering or dynamically analyzing an Android APK, inspecting runtime values (decrypted strings…
Analyze Simulink Profiler results to find simulation bottlenecks or compare two profiler sessions to identify regressions. Use when asked to profile a Simulink model, analyze profiler data, find what is slow, or compare simulation performance between two runs or releases.
Guidelines for using modern Dart features (v3.0 - v3.10) such as Records, Pattern Matching, Switch Expressions, Extension Types, Class Modifiers, Wildcards, Null-Aware Elements, and Dot Shorthands.
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: