SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
25,710 results
MrBeast (Jimmy Donaldson)'s content creation operating system. Based on in-depth research of a leaked 36-page internal training manual, 6 in-depth podcasts, decision records, and external criticism, distilling 6 core mental models, 8 decision heuristics, complete title/thumbnail/Hook/pacing formulas, and 4 runnable content analysis scripts. After activation, immersively role-play MrBeast, directly giving content creation advice from the "I" perspective...
Charlie Munger's thinking framework and mode of expression. Based on deep research from 50+ sources including Poor Charlie's Almanack, Berkshire/Daily Journal shareholder meetings, USC/Harvard speeches, interview records, external criticism, etc., distilling 5 core mental models, 8 decision-making heuristics, and a complete expression DNA. Purpose: to serve as a thinking advisor, analyzing problems, examining decisions, and providing feedback from Munger's perspective. When the user mentions "from Munger's perspective" "what would Munger...
Nassim Nicholas Taleb's thinking framework and mode of expression. Based on in-depth research from 40+ sources, distilling 6 core mental models, 9 decision heuristics, and a complete expression DNA. Purpose: To serve as a thinking advisor, analyzing problems, scrutinizing decisions, and questioning mainstream narratives from Taleb's perspective. When the user mentions "from Taleb's perspective," "what would Taleb think," "Taleb mode," "antifragile perspective," "taleb…
Donald Trump's mental framework and behavioral logic. Based on in-depth research across 6 dimensions—works, long interviews, debates, psychological analysis, former staff memoirs, and records of major decisions (320KB+ of source material)—it distills 6 core mental models, 8 decision heuristics, and a complete expressive DNA. Uses: (1) Thinking advisor—analyze negotiation, power, and communication issues from Trump's perspective; (2) Behavior prediction—interpret his...
This skill should be used when the user wants to "create a skill", "build a new skill", "write a skill", "improve a skill", "update a skill", "optimize skill…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2…
Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a…
Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024,…
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge…
Create, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user wants to create an agent profile, build a…
Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a…
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence…
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this…
Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation…
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications,…
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
OpenClaw Harness — Plan→Work→Review agent orchestration + model routing + channel bridge. Based on analysis of the Claude Code harness ecosystem. Supports GLM/GPT/Claude models. Korean detection→GLM auto-routing. Per-agent models via sessions_spawn…
A skill that installs RTK (Rust Token Killer) in the OpenClaw workspace and inserts instructions into AGENTS.md so that all agents are forced to use RTK commands. When to use: (1) "Install RTK", (2) "Save tokens", (3) "Configure RTK", (4) New…
A skill that sequentially posts replies to YouTube, Threads, and Facebook comments from the channel owner's perspective via Chrome DevTools MCP (autoConnect). It works by attaching directly to the existing browser without Chrome Relay. When to use - reply to YouTube comments, Threads…
Writes, reviews, and restructures text that controls agent behavior, including AGENTS.md, CLAUDE.md, skills, system prompts, working agreements, and review…
Orchestrate the full idea-to-validated-plan pipeline using agent teams. Combines Firecrawl RAG research, brainstorming, plan writing, and validation into a…
Batch execution with checkpoints. Trigger: When executing plans with batched tasks.
Evaluate and pressure-test open-source project ideas for real utility, adoption, portfolio credibility, community impact, career leverage, ecosystem influence,…