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.
Drive MANTA's built Electron app in a real renderer context (Playwright's electron launcher) and assert that key UI surfaces render correctly — no crash, no blank screen, sidebar/chat/terminal present. Load BEFORE marking any frontend/UI task done, and when manta-pr-workflow or manta-handle-reviewer-return verifies a…
Build complete Dublyobase backends through remote HTTP MCP, admin REST APIs, and public project APIs. Use when an AI agent needs to connect to a live Dublyobase instance, create projects, design Postgres collections and fields, configure rules, seed records, create app users, upload files, configure…
Reproduce a GitHub issue with a failing test, implement the minimal fix, verify tests pass, and open a pull request. Use this skill when given an issue number and a working checkout of the target repository.
Coordinate native subagents for complex coding tasks in Claude Code, Codex, Gemini CLI, Cursor, or Grok Build. Use for independent exploration, review, tests, or bounded implementation work; keep small sequential tasks and tightly coupled edits in the primary agent.
Skill abrangente pra operar o ERP Conta Azul via Conta Azul MCP — vendas, faturamento, contas a pagar/receber, fluxo de caixa, cadastros de pessoas/produtos/serviços, contratos, parcelas/quitações e NF-e. Use sempre que o usuário perguntar ou pedir algo sobre a operação financeira/comercial da empresa dele na Conta…
A Chinese-language AI investment research workflow covering industry-chain research, company analysis, valuation, multi-agent debate, and quantitative backtesting for Chinese, Hong Kong, and US stocks.
Tool-neutral CLI agent rules for TI MSPM0 development with SysConfig, DriverLib, CCS, Keil/uVision, CMake/GCC/OpenOCD, and supported board references. Use when an agent needs to inspect or modify MSPM0 projects, validate SysConfig output, package examples, or work on NUEDC embedded firmware.
Higgsfield image prompt director for Banana Pro, Soul Cinema, and GPT-2. Modes: (0) face lock for new characters — Banana Pro single-pass (default), GPT-2 single-pass (higher fidelity, higher credits), or Soul Cinema two-pass, all on mid-gray seamless (locked default; white on request) with black camisole/tank…
Use this skill when both of these are present: (1) a night or time reference — "tonight", "tomorrow", "this weekend", "Saturday night", or any specific date; (2) observing intent — stargazing, skywatching, telescope or binocular use, wanting to know what's visible or "up", asking whether a specific object (planet…
Use the local stata-cli command for Stata work on this machine. Trigger this skill when the user wants to bootstrap an AI-ready Stata workspace, write or debug .do files, inspect .dta data, export CSVs, or needs Stata syntax/package guidance while staying inside the local stata-cli workflow.
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
Stack jurídica brasileira completa num MCP só: busca de processos por nome/CPF/CNPJ/número, movimentações (CNJ/DataJud), publicações e intimações (DJEN), jurisprudência e súmulas, 16 cálculos judiciais, licitações (PNCP), acórdãos do TCU, certidões de regularidade, marcas e patentes (INPI), compliance/sanções e mais…
Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
Evidence-first academic research workflow for topic ideation, scholarly search, paper reading, literature and systematic reviews, study and experiment design, statistics and data analysis, scientific figures, manuscript drafting and polishing, citation checks, peer review, rebuttals, submission packages, theses, and…
Rewrite, restructure, translate, or audit academic manuscripts so first-time readers can identify the problem, contribution, evidence, value, and limitations without decoding internal jargon or formulaic prose. Use for English or Chinese papers, abstracts, introductions, methods, results, conclusions, highlights…
Use when the learner wants to build understanding of a general programming, software-engineering, systems, or architecture concept — references, recursion, closures, coupling, dependency injection, caching, concurrency, queues, consistency, and similar — through Socratic coaching from their current mental model, with…
Generates a complete pre-production reference brief specifically for character assets. Covers anatomy, facial topology, deformation zones, costume, skin, hair, and rig-readiness reference — the layers ref-brief doesn't go deep enough on. Triggers on "character reference", "I'm modeling a character", "humanoid…
Control Ableton Live through the AbletonMCP tools. Use when the user wants to build tracks, patches, clips, drums, automation, or generative music in Ableton, or asks to change any device, mixer, or transport setting in their Live set. Triggers on "Ableton", "Live set", "make a patch", "build a track", "add a synth"…
Drive a Browser tile on the hivemind canvas from inside an agent session — navigate pages, click, fill forms, read content, and screenshot the SAME browser tile the user is watching, using the Chrome DevTools Protocol. Use this whenever you (an agent running in a hivemind tile) are asked to browse the web, open a…
A diagram-making workflow that turns confirmed process, architecture, and data-flow descriptions into animated, looping GIFs. It uses SVG as an intermediate format and checks the rendered result before delivery.
Spin up a working LiveAvatar demo from a curated catalog — clones the reference repo, installs dependencies, provisions the LiveAvatar account, and fills the env file, then hands off the parts only a human can do. Use when: (1) User wants to try, test, see, or demo LiveAvatar, (2) User asks what LiveAvatar demos or…
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: