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.
Audits any website URL for Google AI Search readiness based on Google's official AI optimization guide. Use when the user wants to know if their page is eligible for Google AI Overviews or AI Mode, wants a GEO score, wants to optimize for AI-powered search, or wants to know why they're not being cited in AI search…
Use when the user invokes /steelman or when a high-stakes decision is detected in context (architecture choices, technology selections, business model decisions, strategic pivots). Not for routine planning or implementation tasks.
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, WeChat, or DingTalk so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im"…
Use when the user wants to "productionize", "port", "package", "harden", "clean up", or "make installable" research, academic, or prototype code — loose scripts, notebooks, or a one-off repo — turn scripts/notebooks into a real library, get something pip/uv-installable, or build an HPC/SLURM-friendly tool that runs…
Guide a tricky decision through Socratic dialogue, then produce a structured decision doc. Use when the user says "choose", "help me decide", "I need to make a call on", "decision", "tradeoff", "stuck between", or brings a choice with unclear tradeoffs.
An end-to-end workflow for writing SCI research papers, which are scientific papers intended for journals indexed by the Science Citation Index. It supports brainstorming, novelty checks, paper structure, reviews, bilingual writing, and final document files.
A testing workflow for y3 games, with three mandatory rules: review code before sending it, treat only [run-ok] as success, and ensure every run or Lua command reaches the command-ID success marker.
A method for turning a current newsworthy event or popular product into practical audience-growth and business ideas. It first checks the user's business profile and researches what the topic is, how widely it is spreading, and how people are discussing it.
Generate, modify, validate, execute and triage Flow Forge API test cases. Use when the user wants to turn requirement documents, API documents, table structures or business rules into executable YAML/Excel test cases, revise existing cases after requirement/API changes, run cases with the Flow Forge executor and…
Create, modify, and debug agentic pipelines with Squid. Define multi-agent YAML workflows with spawn (OpenClaw, Claude Code, OpenCode), gates, parallel execution, loops, branching, restart loops, sub-pipelines, and structured approvals. Use when working with .yaml pipeline files or when the user mentions pipelines…
A borderless editorial-design poster generator for opinion summaries, reading-guide cards, and magazine-cover-style content. It creates HTML with a fixed date, QR code, and space for an IP character, then can capture it as a PNG image.
A tool for creating styled presentations as one self-contained HTML file. HTML is the markup format used to display web pages, so the deck can open directly in a browser without extra software or dependencies.
Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions…
Design a focused Markdown loop.md contract for agent/automation loops: goal, termination, progress invariant, approval gates, measurement, residual routing, and optional subagent policy. Use for loop design only; output loop.md; never execute the loop, emit runtime code, or prescribe execution mechanics.
Decompile Android APK/XAPK and extract deeplinks, shortcuts, share APIs with ADB validation. Use this skill whenever the user mentions: analyzing an APK, extracting deeplinks or deep links, decompiling Android apps, finding app shortcuts, reverse engineering APK/XAPK, smali analysis, ADB validation of URIs, batch…
Use when the user wants to read, summarise, extract text/tables from, split, merge, or fill a PDF. Explains when to read a PDF visually vs. extract its text, and how to manipulate PDFs via code execution.
Turn terminal recordings into polished, shareable demos using the reel CLI — record a session once (reel record or asciinema), then edit it like video (trim dead air, cut mistakes, speed-ramp slow parts, zoom, caption) and render a styled, size-budgeted GIF, or a WebM with procedurally synthesized sound, without ever…
Extract and organize frames from a Bilibili video (bangumi episode, UP upload, or a local file) into scenery shots and per-character image groups, using anime-specific person detection + CCIP character-identity embeddings. Two modes — cluster everyone, or pull out one (or several) named characters via reference…
Push the current branch to origin and ensure a PR exists for it (creating or updating one), with the symphony label applied. Use when the workflow says "push" or "open a PR".
Use this skill when the user asks about Clean Architecture in Python — not generic theory, but the specific layer conventions (l1entities, l2usecases, l3interfaceadapters, l4frameworksanddrivers), folder patterns, boundary interfaces, and .importlinter.ini contracts from CJHwong/py-clean-architecture-examples. Fetches…
★not rated 11 2mo agoA113 tokens
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: