Observed Signal · Mar 30, 2026 · Technical Release · Source: Nates Substack · Impact: 4/5 · Sentiment: Positive

Make AI Skills Persistent for Agentic Workflows

Executive Signal Summary

The article explains that AI "Skills"—small, shareable files that codify procedures—have shifted from a personal prompting shortcut to an organizational, agent-invoked standard. Anthropic added Skills into Excel and PowerPoint sidebars on March 11; the skills format has been adopted across vendors (OpenAI, Microsoft, GitHub, Cursor) and the author says ~500,000 skills now run interoperably. Key changes: agents call skills autonomously, admins can provision skills across organizations, and the same skill files run in developer terminals and productivity apps (M365). The author outlines architectural patterns (progressive disclosure, specialist stack, orchestrator), explains why conventional skill design fails for agentic use, prescribes five elements every skill body needs, and offers four prompts and practical tests to make skills agent-ready. The piece also includes access to a skills repository and team-deployment guidance.

Polaris7 AgentPolaris7 Strategic Assessment
High Confidence

Cross-vendor adoption of a Skills format and integration into major productivity apps shifts AI from individual prompting to agent-driven, organization-wide automation—affecting governance, martech workflows, and how teams operationalize LLM-based agents.

SIGNAL RADAR

Track Make Signals & Market Shifts in Real-Time

Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.

Start Monitoring
Verified primary sourcesAutomated briefingsInstant watchlist setup

Key Takeaways & Evidence Grounding

  • Anthropic added Skills into the sidebars of Excel and PowerPoint on March 11.
  • The skills format has been adopted across vendors including OpenAI, Microsoft, GitHub, and Cursor.
  • The author reports ~500,000 skills running across platforms interoperably.
  • Agents now invoke skills autonomously and team admins can provision skills across organizations.
  • The article outlines architectural patterns (progressive disclosure, specialist stack, orchestrator) and provides four prompts and tests to create agent-ready skills.

Ontology Mapping & Concepts

#orchestrator pattern#specialist stack#agent-readiness stress test
Primary Source Grounding & Direct Attribution
Direct Origin Attribution
Primary Reporting: Nates Substack•Published: Mar 30, 2026
Original Coverage Title: “Your Best AI Work Vanishes Every Session. 4 Prompts That Make It Permanent plus Access to My Skills Repo”

Related Market Signals & Shifts

Recent verified developments and strategic activity across this market segment.

Large Language Models (LLM) & AIJun 19, 2026

Open Skills Library: Making Agent Workflows Portable

A Substack essay argues that AI agent 'skills'—the procedural knowledge encoded as prompts, runbooks, SKILL.md files and configs—are becoming trapped inside vendor tools (Claude, Codex, Cursor, ChatGPT), creating repeated rebuild costs when teams switch platforms. The author launches "Open Skills," a public library of agent skills and runbooks designed to be visible, movable, inspectable and installable across tools. The piece explains how skills differ from memory and prompts, lists four failure modes that create long-term debt, provides a "work package" checklist to prove ownership of a skill, and demonstrates rebuilding a support-billing workflow that travels across Claude Code, Codex and Cursor. The author frames skill portability as practical work for 2026 that avoids new subscriptions by making existing workflows portable.

Read assessment
Large Language Models (LLM) & AIMay 6, 2026

AgentSkills: Teach AI Agents How to Execute Tasks

The article describes a gap in many LLM-based agent applications: agents often know what to do but not how to do it reliably. It introduces AgentSkills (aka Procedure Skills) — self-contained, structured playbooks (commonly formatted as SKILL.md) that bundle YAML frontmatter, step-by-step execution instructions, small automation scripts, domain resources, and output templates. The author explains why embedding full procedures in large system prompts fails (fragility, token waste, inconsistency) and advocates progressive disclosure: a discovery phase that loads only skill names/descriptions and an activation phase that loads full skill assets when a match occurs. The piece gives design principles for effective skills (imperative language, explicit failure states, small composable units) and explains when skills materially improve agent reliability and cost-efficiency. Published May 6, 2026 by Sreeni Ramadorai on DEV Community.

Read assessment
Large Language Models (LLM) & AIJun 16, 2026

Skills.sh Sparks Shared Ecosystem for AI Agent Capabilities

Skills.sh, an open ecosystem from Vercel, provides a directory, CLI and leaderboard for discovering, installing and sharing reusable "skills" (SKILL.md files) for AI agents. The project is open-source (MIT) on GitHub at vercel-labs/skills and builds on an agent skill specification the author says was developed by Anthropic and released as an open standard in late 2025. Skills.sh supports installation via a simple CLI (example: npx skills add anthropics/skills), integrates with 38+ agents (e.g., Claude Code, Cursor, GitHub Copilot, Gemini), runs routine audits and already shows substantial adoption — the leaderboard reports 91,000+ total installs with several skills in the hundreds of thousands to millions of installs. The author argues Skills.sh addresses the persistent "agent infrastructure gap" by making procedural, shareable capabilities reusable across projects and agents.

Read assessment
Executive Briefing & Watchlist

Receive all future signals for Make & competitors in your briefing

Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.

Daily primary source scansCurated executive briefingsUnsubscribe anytime