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.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…
Guide users through Oqto platform setup, troubleshoot installation issues, and verify deployment configuration. Use when the user is installing Oqto, configuring the platform, or encountering setup-related problems.
A local-first tracker for Chinese graduate-admissions notices, especially recommendation-based admissions (保研/推免) such as summer camps and direct PhD offers. It watches university notice pages and matches announcements to a student's profile.
Patterns for invoking the GitHub CLI (gh v2.103.3+) from agents. Use when the task mentions GitHub, gh, pull requests/PRs, issues, releases, gists, Actions/workflow runs, forks, repo cloning, reviews, or you need exact gh commands. Covers pagination, repo targeting, search vs list, discussions, projects, rulesets…
Use when a user gives one or many WeChat or Xiaohongshu links and wants the parsed notes saved to a specific local path without relying on the Obsidian plugin UI. This skill wraps the repository's import capability as a direct agent tool through the bundled script, including batch import, frontmatter generation, media…
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
Use when optimizing or iterating on prompts for a student LLM — a prompt produces wrong-shaped output, hallucinations, refusals, poor instruction-following, or when migrating a prompt between models with different quirks. Also use when hardening a prompt against indirect prompt injection from untrusted external data.
Methodology reference for Mastermind Bug Bounty runtime. Iron Rules, Safe-First Layering, phase techniques, value pool linkage, SRC compliance, and Hook system.
Comprehensive guide for writing Magpie (.mp) programs, debugging compiler errors, and using the Magpie CLI. Designed for agents who have never seen Magpie before.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
Rules for writing code that coding agents (and humans) can find and understand through plain-text search. Apply whenever writing or renaming code: functions, types, constants, files, error messages, doc comments. Grounded in measurement: agents navigate by plain-text search, not by AST or language server, so every…
Generate declarative multi-agent systems (MAS) using POMASA pattern language. Use when building agent pipelines, orchestrating multiple AI agents, or creating research automation workflows. Supports patterns like Prompt-Defined Agent, Orchestrated Pipeline, Filesystem Data Bus, and Verifiable Data Lineage.
Use when performing BLE security testing on Linux/BlueZ - device scanning, GATT enumeration, read/write/notify interaction, fuzzing, and security assessment (unauthenticated read/write exposure, encryption enforcement, DFU entry, write-without-response abuse, connection parameters). Drives the single Go caeruleus…
A local automation toolkit for Douyin, the Chinese short-video platform, and its creator center. It uses the computer’s Chrome browser to handle account access, content search, publishing, and basic interactions.
Build a research-backed X writing system around a user draft. Use this skill when the user wants rewrite advice grounded in Matt Gray guidelines, their own top posts, topic winners, and trends. Then produce 5 LLM-authored post versions.
Review Uniswap v4 hooks and integrations for permission-bit, callback-authentication, pool-identity, custom-accounting, delta, settlement, dynamic-fee, JIT-liquidity, shared-custody, and liveness bugs. Use when a Solidity system implements IHooks or BaseHook, returns hook deltas, or relies on a v4 hook for pricing…
Use this skill as a quick reference for billing related Google Play Developer API REST endpoints, covering purchases.products, purchases.subscriptionsv2, purchases.voidedpurchases, and monetization endpoints. Lists paths, auth scopes, and typical request shapes.
Complete VPN server setup from scratch — takes a fresh VPS (IP + root password from the hosting provider) through full server hardening and a 3x-ui (Xray) install with two VLESS+Reality inbounds (XHTTP for best DPI resistance, TCP+Vision for iOS), delivered as one subscription link and connected via the Happ client.…
ESP32 debugging via serial log and USB-JTAG (OpenOCD + GDB). Invoke when user encounters bugs, crashes, or unexpected behavior on ESP32 and needs systematic root cause analysis.
A local tool for downloading public videos from Douyin, Bilibili, Kuaishou, Xiaohongshu, and Weibo, then extracting metadata or transcribing speech. Whisper is speech-to-text software, and OpenCC converts between Traditional and Simplified Chinese.
An archived troubleshooting guide for drpy-node video playback links, especially lazy parsing and links that look playable but are not. It has been replaced by drpy-node-coder.
A skill for searching OpenAlex, a free catalog of research papers, authors, institutions, journals, and research topics.
★not rated 60▲
+2 1mo agoA100 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: