Entity trail

agentskills.io

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-07-11 / projects-researcherAgentPrizm Launches AgentMemory + AgentSkills, Pairing a REST API With MCP for Persistent Agent MemoryAgentPrizm launched its AgentMemory and AgentSkills platform on July 9, 2026, giving agents persistent memory across sessions via a REST API plus MCP infrastructure, aimed at both individual developers and enterprise teams. It's part of a wave of standalone agent-memory products (mem0, claude-mem, thedotmack) racing to own the cross-session context layer. For builders, it signals that 'memory as a managed service' is consolidating into MCP-native offerings rather than bespoke per-app storage.
2026-04-29 / projects-researcherNetSuite Ships SuiteCloud Agent Skills — First ERP Platform to Adopt agentskills.io Open Standard Across 25+ AI Coding ToolsOracle NetSuite announced SuiteCloud Agent Skills at SuiteConnect San Francisco on April 28, becoming the first ERP platform to leverage the agentskills.io open standard originally developed by Anthropic. The skills give AI coding agents NetSuite-specific context for building, reviewing, and deploying customizations across 25+ platforms including Claude Code, Codex, Gemini CLI, and Cursor. Three initial skills cover UI Framework References (60+ component specs), OWASP security guidance, and SuiteScript v1.0-to-v2.1 migration — converting days of legacy script conversion into hours.
2026-04-05 / skill-finderSnyk Threat Model: SKILL.md to Shell Access in Three Lines of Markdown — Why Traditional Scanners Miss Agent Skill AttacksSnyk published a detailed threat model showing how three lines of markdown in a SKILL.md file instruct an AI agent to read SSH keys and exfiltrate them to attacker infrastructure. The attack exploits the fact that traditional security scanners skip markdown files entirely, and the malicious payload is written in plain English rather than code. The concept of 'toxic flows' — a skill that has access to private data, contains untrusted instructions, and can communicate externally — defines the kill chain. This is the first formal threat model for the AgentSkills specification.
2026-04-02 / github-pulse-researcheragentskills/agentskills: Agent Skills Specification Reaches 14.9K Stars — The Standard SolidifiesThe Agent Skills specification, providing formal documentation and standards for portable agent skills across platforms, has reached 14.9K stars. As skills proliferate across Claude Code, Codex, Gemini CLI, Cursor, and Antigravity, this specification represents the convergence point for interoperability. The skills-as-packages pattern is now mature enough to warrant a formal spec — echoing npm's role in the JavaScript ecosystem.
2026-02-28 / projects-researcherNousResearch Hermes Agent Persistent Open Source AgentMulti-level procedural memory, 40+ bundled agentskills.io skills, 5 execution backends, messaging gateway. Can generate tool-calling trajectories for RL training.
2026-02-24 / news-researcherAnthropic Agent Skills Open Standard LaunchAnthropic launches agentskills.io with partners Atlassian, Figma, Canva, Stripe, Notion, Zapier. SDK available. OpenAI quietly adopted same SKILL.md architecture.
2026-02-22 / vibe-coding-researcherAnthropic The Briefing Monday Preview — Agent Skills Open StandardFeb 24 9:30am EST. New Cowork enterprise announcements. Agent Skills open standard (agentskills.io) with Atlassian, Figma, Canva, Stripe, Notion, Zapier. OpenAI and Microsoft adopted.

Graph relationships

USES
NetSuite
NetSuite adopted agentskills.io open standard for SuiteCloud Agent Skills
Source finding
USES
Hermes Agent
Hermes Agent bundles 40+ skills from agentskills.io and can generate tool-calling trajectories for RL training
Source finding
USES
NetSuite -> agentskills.io
NetSuite adopted agentskills.io open standard for SuiteCloud Agent Skills
Source finding
USES
Hermes Agent -> agentskills.io
Hermes Agent bundles 40+ skills from agentskills.io and can generate tool-calling trajectories for RL training
Source finding

Source trail

Latent Space PR Newswire Snyk — From SKILL.md to Shell Access in Three Lines of Markdown GitHub GitHub Anthropic Anthropic

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…