Reviews accessibility mid-design, not as a compliance audit, but as a craft challenge. Use when designing, describing, or building a UI component. Trigger on "I'm designing a component", "does this work", "review this interaction", "how should I handle focus", "is this accessible", or whenever HTML/CSS/React code is…
Senior System Architecture & Design by SAAD. MANDATORY ACTIVATION on: "SAAD", "senior design", "design my system", "architect this", "build from scratch", "full system for", "plan my project", "analyze my idea", "system structure for", "I have an idea for", "help me design", "create a system". Runs a 6-phase elite…
Run and control interactive CLI sessions for AI agents. Handles TUI prompts (select lists, checkboxes, confirms), persistent shell state, and long-running processes. Use when you need to execute terminal commands, respond to interactive prompts, navigate scaffolding wizards like create-vue or create-vite, or manage…
Use when the user asks to set up, install, or migrate to the Unify Theme for reablocks — a production-ready theme pack built on a three-level design-token system (primitives → semantic → Tailwind utilities) synced with the Unify Figma library. Covers the single-file themeUnify.ts TypeScript download, the Reablocks…
Use when driving or testing a packaged Electron desktop app from outside it (no source access, only the .exe/.app), or when a chrome-remote-interface/CDP script hangs forever waiting for page load, throws "Execution context was destroyed", fills an input that the app then ignores, or errors on a :has-text() selector …
Hypothesis-driven experimenter. Designs controlled tests to validate or invalidate ideas before committing to them. Use when an assumption, feature, or strategy should be tested rather than assumed — A/B tests, proofs of concept, feature flag rollouts, market validation, or any decision where evidence beats opinion.…
Maintain a durable, tagged journal of a complex workflow so it can later be distilled into a reusable skill. Use this whenever beginning a complex, multi-step workflow (design work, automation build, CAD, RAG pipeline, website work, or anything non-trivial you might want to repeat), even if the user does not say…
Use when the user says "brain fog mode" or "low-bandwidth mode"; explicitly reports reduced bandwidth such as brain fog, fatigue, overwhelm, trouble focusing, or losing track; asks you to reconstruct task context lost after an interruption; asks to simplify material they describe as complex, overwhelming, or too…
A Chinese-language writing guide for composing deliberately restrained cold emails that point out a company’s documented gap. A cold email is an unsolicited message to someone you do not already know.
Creates a markdown paste on gomarkdown.online and returns the shareable URL. Use when the user wants to share markdown content via a link, create a paste of markdown, publish markdown online, or generate a shareable markdown document URL.
Explicit opt-in only. Translate multilingual requests through lightweight Claude Code subagents, work normally in English, then translate only the final answer back. Trigger on $token-trans invocations or explicit TokTrans references.
Single-CVE applicability triage that evaluates whether a CVE actually applies to the user's environment by reasoning about discriminating conditions against a skill-maintained environment profile; triggers when a user asks whether they are affected by a CVE, whether a CVE applies to them, or wants to assess a CVE…
Use when the user wants to download a paper PDF from a DOI (or title, resolved to a DOI first). Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, Semantic Scholar, and Sci-Hub mirrors as a last-resort fallback.
Automatically calibrate response effort and token usage to match task complexity. Use this skill at the START of every response to classify the incoming task and select the appropriate effort tier before generating any output. Trigger whenever you're about to answer a question or complete a task — this skill saves…
Question-first architecture proposal discipline for AI agents. Use when a user provides a raw idea, product concept, feature request, business goal, or system goal without an existing implementation and needs a reviewable architecture proposal with assumptions, open questions, risks, decision options, workflows…
Use when starting or finishing any coding/editing task in a project that follows a documentation-first AI collaboration workflow — declare scope before editing, log every change afterward with a changelog entry, scaffold a brand-new project with this discipline (AGENTS.md/README/docs skeleton), or audit and reorganize…
Process the garden vault. Files inbox captures into atomic notes, adds wiki-links, dedupes, updates MOCs, and commits. Run on a schedule (cron or routine), not by hand. Reads /garden/meta/gardener-rules.md for heuristics.
This skill should be used when the user requests comprehensive research, deep investigation, or detailed academic-style reports on any topic. Trigger phrases include "deep research", "comprehensive investigation", "detailed report", "academic research", or requests for thorough analysis of complex subjects. The skill…
Author render-deterministic hyperframes compositions. Use when generating HTML/CSS/JS for hyperframes.compose, hyperframes.render, or any pipeline that produces a programmatic MP4 via hyperframes — including builtin.scaffolded-narrated-video, builtin.prompt-video, builtin.prompt-narrated-video. The framework's "render…
A template for turning an exhibition plan into a three-page presentation outline. The pages cover the theme, its explanation and visitor story, and a detailed area-by-area display plan.
Give Claude eyes and ears on any online video, then analyze it. Downloads a video from a URL (YouTube, Instagram, X, Vimeo, and 1000+ yt-dlp sites), extracts key frames, and gets a transcript (native captions, else local Whisper), then hands the frames + timestamped transcript to Claude so it can produce a full…
★not rated 4 1mo agoA149 tokens
originalMIT
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: