LIVE
Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|Anthropic Accused of Building a Predictive Surveillance System Targeting Activists09/09/26 · Anthropic|OpenAI Claims a Millennium Prize Problem Solved, Controversy Follows09/09/26 · OpenAI|Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|Perplexity entrusts operations to OpenAI's GPT-6 Astra14/09/26 · OpenAI|Real-SWE: A New Benchmark for Testing AI on Real Enterprise Codebases12/09/26 · Specific|Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|Anthropic Accused of Building a Predictive Surveillance System Targeting Activists09/09/26 · Anthropic|OpenAI Claims a Millennium Prize Problem Solved, Controversy Follows09/09/26 · OpenAI|Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|Perplexity entrusts operations to OpenAI's GPT-6 Astra14/09/26 · OpenAI|Real-SWE: A New Benchmark for Testing AI on Real Enterprise Codebases12/09/26 · Specific|
AI tools · Skill

The best agent skills

A skill is a set of instructions that teaches the AI a method: how to debug, how to scope a project, how to review code. It steers the agent’s behaviour, not what it can access.

2 scored skill. Last checked on 13 September 2026.

Code 1Frame (methods, guardrails) 2

The three to remember

Most powerful
BMAD Method
SkillRisingSecurity: nothing to flag
9.0

Heavier than spec-kit, but excellent for framing a real project from end to end.

  • · Utility 8/10, best of the selection
  • · Free, no limits
  • · Your data stays on your machine
Free5 min
Simplest
awesome-claude-code
SkillRisingSecurity: nothing to flag
9.0

The best map of the territory, worth reading before installing anything.

  • · One-click install
  • · Free, no limits
  • · Your data stays on your machine
Free1 click
ToolPriceScoreSec.
BMAD MethodRisingAgile method for agents: roles (PM, architect, dev) and structured documents before the code.Free9.0Security: nothing to flag
awesome-claude-codeRisingA curated list of commands, hooks, skills, and workflows for Claude Code.Free9.0Security: nothing to flag

Tool : standalone product, used directly · Plugin : installs into a host application · Skill : instructions that teach the ai a method · MCP : connector giving the ai access to a service

What to know

A skill is text, but text the agent follows. Read it before installing, exactly as you would read a script, and prefer official marketplaces to unknown repositories.

Find the right one in 4 questions →