Agent skill

AI Super Intelligence

by coco-research in coco-research/coco

Your AI research and engineering brain trust. An agent skill from coco-research/coco.

Custom licenceAuto-check passedAI & LLM Engineering

Install AI Super Intelligence

skills CLI
$ npx skills add coco-research/coco --skill ai-super-intelligence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install coco-research/coco ai-super-intelligence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .claude/skills && cp -r skills-src/systems/superintelligence/ai .claude/skills/ai-super-intelligence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai-super-intelligence
GitHub stars
503
Token cost
~3.7k tokens
SKILL.md length
1,308 words
Files
556 (incl. scripts)
Skills in repo
63
Repo updated
First seen
Licence
Custom licence

At a glance

Your AI research and engineering brain trust. An agent skill from coco-research/coco.

  • Works in 5 steps: Registry is source of truth. Re-read… → Attribution at every line. No "the team… → Approval gate mandatory for action verbs… → …
  • Tasks that involve Reinforcement learning
  • SKILL.md covers What this team is for, Cells (8), Personas (59) and Files in this team, plus 4 more sections
  • Calls python3

What it does

AI Super Intelligence is an agent skill from coco-research/coco. Your AI research and engineering brain trust. 59 named personas across 8 cells covering frontier labs, applied product, model architecture, reasoning/RL/agents, alignment and interpretability, theory and science of DL, multimodal and…

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 557 other files, including scripts (for example `EXPANSION.md`, `ROSTER.md` and `VALIDATION-OFFLINE.md`).

It sits in AI & LLM Engineering, covering Reinforcement learning, AI interpretability and Hooks and plugins. The repository describes itself as: CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands…

When your agent uses it

  • Tasks that involve Reinforcement learning
  • Tasks that involve AI interpretability
  • Tasks that involve Hooks and plugins

Example prompts

  • “/ai-super-intelligence”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Registry is source of truth. Re-read every invocation; no caching.
  2. Attribution at every line. No "the team said" — name a persona or a cell.
  3. Approval gate mandatory for action verbs unless an explicit flag bypasses.
  4. Hard 16-32 size band on orchestrator output.
  5. Full English prose — no caveman compression in command output.

What it can do on your machine

Read from SKILL.md and the folder at commit d79d33a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Super Intelligence loads about 3.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,308 words (~3,746 tokens).

“Your AI research + engineering brain trust and decision-making partner. 59 named personas drawn from the world's frontier model labs (US, UK, China, France), top AI universities, the open-source ecosystem, the independent-evaluation and AI-governance ecosystem, and product-history archetypes. Reusable across…”

— opening of SKILL.md by coco-research, Custom licence
name
ai-super-intelligence
team_id
ai-super-intelligence
team_name
AI Super Intelligence Team
last_updated
2026-05-28
schema_version
1.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 555 other files (scripts) in systems/superintelligence/ai of coco-research/coco.

  • SKILL.md
  • EXPANSION.md
  • ROSTER.md
  • VALIDATION-OFFLINE.md
  • cells/alignment-interp-safety.md
  • cells/applied-ai-leadership.md
  • cells/frontier-labs-research.md
  • cells/model-architects.md
  • cells/multimodal-embodied.md
  • cells/reasoning-rl-agents.md
  • cells/systems-kernels-serving.md
  • cells/theory-science.md
  • personas/aditya-ramesh.md
  • personas/aidan-gomez.md
  • personas/albert-gu.md
  • personas/aleksander-madry.md
  • personas/andrej-karpathy.md
  • personas/andrew-feldman.md
  • personas/aravind-srinivas.md
  • … and 537 more

Open the folder on GitHubat commit d79d33a

Compare with similar skills

AI Super Intelligence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Super Intelligence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Super Intelligence this skillcoco-research/coco503—~3.7kAutomated safety check: PassCustom licence
Richard S SuttonK-Dense-AI/mimeo282—~1.8kAutomated safety check: PassMIT
Prompt Template Authoringnicobailon/pi-prompt-template-model321—~1.3kAutomated safety check: PassMIT
Vmas Simulator Guidewentorai/research-plugins2981 repos~960Automated safety check: PassMIT
Writing Rulesathola/claude-night-market341—~1.4kAutomated safety check: NotesMIT
Git Guardrails Claude Codefossasia/eventyay-interpretation1.6k12 repos~578Automated safety check: PassApache-2.0

Similar skills

  • Richard S Sutton

    K-Dense-AI/mimeo

    Reach for this skill whenever you are discussing reinforcement learning, agentic AI systems, AI alignment, continual learning, or the philosophical limits of large language models.

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Prompt Template Authoring

    nicobailon/pi-prompt-template-model

    Write and run custom Pi prompt templates (slash commands) for this extension.

    321 GitHub stars~1.3k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed
  • Vmas Simulator Guide

    wentorai/research-plugins

    Vectorized multi-agent reinforcement learning simulator. An agent skill from wentorai/research-plugins.

    298 GitHub starsUsed in 1 repo~960 tokens
    AI & LLM EngineeringAuto-check passed
  • Writing Rules

    athola/claude-night-market

    Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior.

    341 GitHub stars~1.4k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes
  • Git Guardrails Claude Code

    fossasia/eventyay-interpretation

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

    1.6k GitHub starsUsed in 12 repos~578 tokens
    AI & LLM EngineeringAuto-check passed
  • Cline SDK Guide

    cline/cline

    Reference for building AI agents with the Cline SDK: the Agent runtime, ClineCore sessions, custom tools, plugins, events, providers, scheduling and multi-agent teams.

    70k GitHub stars~2.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from coco-research/coco

All 63 skills in this repo
  • Coco Ads

    coco-research/coco

    Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames.

    503 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Arch Index

    coco-research/coco

    Build and validate .arch/index.json — a committed map from each architectural component of this repository to the real directories and files that implement it, pinned to a git commit, with every…

    503 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Openai Agents

    coco-research/coco

    Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming.

    503 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Skill Evolution

    coco-research/coco

    A skill your agent uses when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one…

    503 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Coco Diagram

    coco-research/coco

    A skill your agent uses for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources.

    503 GitHub stars~9.2k tokensUpdated today
    Auto-check passed
  • API Design Principles

    coco-research/coco

    A skill your agent uses when designing a new REST or GraphQL API, reviewing an API spec before implementation, setting team API standards, or migrating REST to GraphQL.

    503 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

Questions about AI Super Intelligence

What does AI Super Intelligence do?

Your AI research and engineering brain trust. An agent skill from coco-research/coco. AI Super Intelligence is an agent skill from coco-research/coco. Your AI research and engineering brain trust.

When should I use AI Super Intelligence?

AI Super Intelligence fits situations like: tasks that involve Reinforcement learning; tasks that involve AI interpretability; tasks that involve Hooks and plugins.

How do I install AI Super Intelligence in Claude Code?

Run `npx skills add coco-research/coco --skill ai-super-intelligence -a claude-code`. Or copy the skill folder (systems/superintelligence/ai in coco-research/coco) into .claude/skills/ai-super-intelligence in your project. Claude Code loads it when a task matches its description.

How do I install AI Super Intelligence in Codex?

Run `npx skills add coco-research/coco --skill ai-super-intelligence -a codex`. Or copy the skill folder (systems/superintelligence/ai in coco-research/coco) into .agents/skills/ai-super-intelligence in your project. Codex loads it when a task matches its description.

Can I use AI Super Intelligence in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add coco-research/coco --skill ai-super-intelligence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-super-intelligence, .gemini/skills/ai-super-intelligence, .github/skills/ai-super-intelligence and .opencode/skills/ai-super-intelligence in your project.

What does AI Super Intelligence need to run?

Going by SKILL.md and its folder, AI Super Intelligence needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does AI Super Intelligence access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Super Intelligence safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AI Super Intelligence use?

AI Super Intelligence has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does AI Super Intelligence use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Super Intelligence?

Skills that share tags, products or a category with AI Super Intelligence: Richard S Sutton (K-Dense-AI/mimeo, 282 stars), Prompt Template Authoring (nicobailon/pi-prompt-template-model, 321 stars), Vmas Simulator Guide (wentorai/research-plugins, 298 stars) and Writing Rules (athola/claude-night-market, 341 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Super Intelligence?

coco-research (a GitHub user) maintains it in coco-research/coco, which has 503 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.

Source: coco-research/coco on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.