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.
Configure or use the aiocache caching layer. Use when: adding cache reads/writes, configuring cache backends, working with TTLs, enabling/disabling caching, or understanding the NoOpCache fallback pattern.
A thinking framework based on Richard Feynman’s published work, talks, interviews, biography, and peer accounts. It uses his approach to examine understanding, decisions, explanations, and arguments.
Skill for expanding ForThePeople.in to new districts. Use when adding Bengaluru Urban, Mysuru, or any new Indian district to the platform. Triggers: 'add district', 'expand to Bangalore', 'expand to Mysore', 'unlock district', 'new city', 'seed data for district', 'add Bengaluru', 'add Mysuru', 'district-specific…
Diagnose broken Hugging Face Gradio Spaces from their actual logs and pinned source, then prepare a minimal verified source fix as candidate files. Use for scheduled Space monitoring, BUILDERROR or RUNTIMEERROR triage, Gradio and ZeroGPU failures, source analysis, and patch preparation. Read-only against the Hub - it…
A guide that turns an idea into shot-by-shot prompts for Seedance 2.0, an AI video-generation tool. It helps define the story, visuals, camera movement, actions, timing, and reference media.
Switch the project's package manager between npm, bun, and pnpm. Updates all config, scripts, documentation, CI workflows, and AI instructions. Use when initializing from template or switching package managers.
L1 trigger - detects non-determinism, state transition completeness violations, and safety/liveness invariant breaks in consensus code. Inject into depth-consensus-invariant or depth-state-trace.
Generate test and suite specifications in the strict FinalRun YAML format. Handles automated test planning, folder grouping by feature, repo app configuration, environment-specific overrides in .finalrun/env/.yaml, and validation via finalrun check.
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user asks about OpenClaw setup, configuration, channel management (WhatsApp/Telegram/Discord/Slack/iMessage/etc.), model provider setup, Gateway operations, multi-agent…
Reads web content and searches the web using Jina AI Reader API. Use when extracting content from URLs, reading social media posts (X/Twitter), or web searching for current information.
A Chinese-language ordering skill for a WeStoreCafe mini-program, where users can search drinks, view drink details, choose sizes or options, and place orders. It returns text and clickable mini-program cards that hand users into the store pages.
A writing guide for official Chinese government documents, such as requests, notices, letters, summaries, and meeting records. It covers the national formatting standard GB/T 9704-2012, templates, language rules, and quality checks.
A presentation-making workflow that turns a speech or slide content into images for polished business-style slides. It first plans each slide and then generates the slide images.
Play board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join…
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: