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.
Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, repair trajectories, work records, completed optimizations, pending fixes, or pending synchronization exist; when an Agent needs to report a reproducible skill defect; or when the user wants to…
A command-line toolkit for producing AI-generated comic videos, from images and video to audio, prompts, projects, episodes, shots, storyboards, and media assets. CRUD means creating, viewing, editing, and deleting records.
Drive a strict conversational, image-first and image-final brand identity design process. Use when the user asks for brand design, logo inspiration, logo exploration, AI-generated logo images, VI/visual identity systems, brand manuals, identity guidelines, application mockups, or premium HTML brand books. The skill…
Discover better ways to complete tasks. Proactively search SandBase (the sandbasediscover MCP tool, or sandbase discover in a shell) before writing a scraper, before using a generic web fetch for structured data, before telling the user something is inaccessible, and whenever a task needs a capability you do not have…
Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: "browse", "open a page", "take a screenshot", "scrape", "fill form", "click button", "web…
A code-based video renderer that draws HTML or Canvas animations frame by frame and turns them into MP4 files. It also supports GIFs, transparent layers, subtitles, and reusable templates according to the supplied description.
Use when writing or debugging Vue code that imports @tanstack/ai-vue. Covers useChat, createChatHook, the generation composables (image, audio, speech, video, transcription, summarize), useAudioRecorder, useByok, useWebMCPTools, and the @tanstack/ai-vue/ui and /byok subpaths. Provides current API shapes…
Analyze a systing trace database (.duckdb). Use when the user asks about a systing trace — flamegraphs, scheduling latency, CPU hotspots, network behavior, memory/allocation activity, off-CPU time, TPU op/metric data, or any question about what's in a trace.duckdb file. Orchestrates the systing-analyze MCP tools…
Generate or edit raster images through the user's ChatGPT subscription and save or preview workspace PNGs. Use for text-to-image, local-reference generation, edits, follow-up revisions, transparent PNGs, variants, multi-image batches, or subscription-backed setup in Codex, Claude Code, Google Antigravity, and…
A photo-editing style that redraws a photo as a simple flat crayon fashion illustration while keeping the person’s identity, pose, clothing outline, and key accessories.
Keeps an agent building and validating real output instead of servicing its own bookkeeping. Use for multi-stage pipelines, capability roadmaps, long-running implementation loops, migrations, staged data or build runs, and any run where administrative hashes, locks, receipts, dashboards, certification markers, or…
Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.
Turn resume materials and an optional job description into fact-checked, user-approved content and a runnable React + Vite portfolio website. Also use for scoped revisions to an existing portfolio; not for inventing credentials or screening job applicants.
Use when managing Secure Enclave signing keys or encrypted secrets. Use for creating/listing/deleting P-256 keys, signing digests, running commands with secrets injected via vault exec, storing/retrieving encrypted secrets. Also use when an agent needs API keys, private keys, or credentials injected into a subprocess…
Use when a user provides a TikTok profile or account link and asks for account analysis, competitor research, content or commerce performance, operational-logic research, account-launch process reverse engineering, selling guidance, operational diagnosis, or growth opportunities.
Operating rules for the .okf/ knowledge bundle — filing new concepts, the board, the journal, the daily snapshot, closing work, source attribution, and the generated/verified attestation policy. Use before reading from or writing anything into .okf/.
Build Claude + Codex dual AI collaboration framework for new projects. Start from PRD co-creation, generate complete division of labor system (plan design, implementation verification, review process). Suitable for projects with clear requirements and long-term iteration needs.
★not rated 183▲
+1 2mo agoB53 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: