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.
A discussion tool for evaluating and improving research-topic ideas for China’s National Natural Science Foundation, known as NSFC. It examines a proposed direction before formal grant writing begins.
Close captured agent-improvement work: triage fleet learnings, select a bounded evidence-backed batch, implement and live-verify fixes, and record leader decisions. Use for 'learn loop', 'fix the learnings', 'process the backlog', or when asked what recurring agent/tool friction to improve.
Reviews AI/ML systems for data privacy and governance risks including training data privacy, PII exposure in prompts and completions, data retention policies, model memorization risks, and regulatory compliance. Auto-invoked when reviewing systems that process personal data through LLMs, train or fine-tune models on…
A workflow for turning story ideas into serialized AI short dramas, comic dramas, or live-action vertical videos. It covers story structure, characters, episodes, and production handoffs.
Flagship orchestrator that launches 5 parallel agents (cashflow, debt, investments, retirement, protection) to produce a comprehensive financial health analysis with a composite Financial Health Score (0-100), letter grade (A+ through F), and a prioritized 90-day action plan. Use when the user says "/finance analyze"…
Audit an existing or proposed premium pass (battle pass, season pass) for value proposition integrity, progression health, free track balance, reward pacing, engagement loop quality, and economy impact. Use when evaluating a pass before launch, diagnosing why a pass is underperforming, reviewing a competitor's pass…
A read-only log and metrics lookup guide for an ad-agent project. It covers campaign performance logs, budget-change records, time-window comparisons, and tracing errors by identifier.
Add persistent, structured long-term memory to AI agents using Maximem Synap. Use this skill whenever the user is building, debugging, or evaluating an AI agent and mentions any of: "memory", "long-term memory", "persistent memory", "agent memory", "remember across sessions", "context window", "agent forgets", "user…
A video-understanding and question-answering tool based on a DeepSeek vision model. It can examine videos such as recordings, surveillance footage, games, films, or animations and refer to events with timestamps.
A relationship-focused conversation and analysis skill. It gathers information at the start, combines several ways of looking at a situation, and supports deeper analysis for complex cases.
Build or substantially modify any code file by working in small incremental steps — plan, skeleton, then ONE feature per turn — instead of writing the whole file in one large write call. Use whenever the user requests a new file, a feature, a UI, or a refactor that would otherwise produce more than 80 lines of output…
A research workflow based on Chan theory, a method of analysing market price structures across several time levels. It turns concepts such as trends, pivots, divergence, and buy or sell points into reproducible study or backtesting rules.
Use when you need to recall past work, previous decisions, error solutions, or project history. Activates the 3-layer memory search workflow for token-efficient retrieval.
Manage Confluence documentation with downloads, uploads, conversions, and diagrams. Use when asked to "download Confluence pages", "upload to Confluence", "convert Wiki Markup", "sync markdown to Confluence", "create Confluence page", or "handle Confluence images".
Creates high-quality Instagram carousels in an X (Twitter) post visual format, delivered as swipeable HTML previews with export-ready slides (1080×1350px PNG). Handles the full workflow: brand setup, slide copy, X-style visual design (profile header, clean background, X engagement bar), HTML generation, and…
Create, debug, review, or evolve LegadoHub Python source plugins and aggregate Reading/Legado source shells. Use when the user asks to adapt a novel site, generate a Python source plugin, inspect public reading sources as references, convert repeated site patterns into templates, repair a special source, or produce…
Run workflow-as-code jobs in Codex for large fanout, release diff review, security review, bug sweeps, adversarial verification, or multi-agent orchestration.
A PDF question-answering and search tool that can understand text, scanned pages, charts, tables, and code. It can point to physical page numbers, quote matching text, and show page images.
Cognitive superposition synthesizing Riehl (∞-categories), Sutskever (compression), Schmidhuber (curiosity-driven), and Bengio (GFlowNets) into unified ASI framework with quantum-inspired measurement collapse.
Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…
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: